[clang] 9ce931b - [HIP] Fix no matching constructor for init of shared_ptr and malloc

2021-07-22 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2021-07-22T14:32:41Z
New Revision: 9ce931bd71855ced2146f77120df07e4bf381cec

URL: 
https://github.com/llvm/llvm-project/commit/9ce931bd71855ced2146f77120df07e4bf381cec
DIFF: 
https://github.com/llvm/llvm-project/commit/9ce931bd71855ced2146f77120df07e4bf381cec.diff

LOG: [HIP] Fix no matching constructor for init of shared_ptr and malloc

Allow standard header versions of malloc and free to be defined
before introducing the device versions.

Fixes: SWDEV-295901

Reviewed By: yaxunl

Differential Revision: https://reviews.llvm.org/D106463

Added: 


Modified: 
clang/lib/Headers/__clang_hip_runtime_wrapper.h

Removed: 




diff  --git a/clang/lib/Headers/__clang_hip_runtime_wrapper.h 
b/clang/lib/Headers/__clang_hip_runtime_wrapper.h
index 59d5cfef2df8..73021d256cba 100644
--- a/clang/lib/Headers/__clang_hip_runtime_wrapper.h
+++ b/clang/lib/Headers/__clang_hip_runtime_wrapper.h
@@ -46,6 +46,28 @@ extern "C" {
 }
 #endif //__cplusplus
 
+#if !defined(__HIPCC_RTC__)
+#include 
+#include 
+#include 
+#else
+typedef __SIZE_TYPE__ size_t;
+// Define macros which are needed to declare HIP device API's without standard
+// C/C++ headers. This is for readability so that these API's can be written
+// the same way as non-hipRTC use case. These macros need to be popped so that
+// they do not pollute users' name space.
+#pragma push_macro("NULL")
+#pragma push_macro("uint32_t")
+#pragma push_macro("uint64_t")
+#pragma push_macro("CHAR_BIT")
+#pragma push_macro("INT_MAX")
+#define NULL (void *)0
+#define uint32_t __UINT32_TYPE__
+#define uint64_t __UINT64_TYPE__
+#define CHAR_BIT __CHAR_BIT__
+#define INT_MAX __INTMAX_MAX__
+#endif // __HIPCC_RTC__
+
 typedef __SIZE_TYPE__ __hip_size_t;
 
 #ifdef __cplusplus
@@ -64,11 +86,11 @@ __attribute__((weak)) inline __device__ void *free(void 
*__ptr) {
 #else
 __attribute__((weak)) inline __device__ void *malloc(__hip_size_t __size) {
   __builtin_trap();
-  return nullptr;
+  return (void *)0;
 }
 __attribute__((weak)) inline __device__ void *free(void *__ptr) {
   __builtin_trap();
-  return nullptr;
+  return (void *)0;
 }
 #endif
 
@@ -76,28 +98,6 @@ __attribute__((weak)) inline __device__ void *free(void 
*__ptr) {
 } // extern "C"
 #endif //__cplusplus
 
-#if !defined(__HIPCC_RTC__)
-#include 
-#include 
-#include 
-#else
-typedef __SIZE_TYPE__ size_t;
-// Define macros which are needed to declare HIP device API's without standard
-// C/C++ headers. This is for readability so that these API's can be written
-// the same way as non-hipRTC use case. These macros need to be popped so that
-// they do not pollute users' name space.
-#pragma push_macro("NULL")
-#pragma push_macro("uint32_t")
-#pragma push_macro("uint64_t")
-#pragma push_macro("CHAR_BIT")
-#pragma push_macro("INT_MAX")
-#define NULL (void *)0
-#define uint32_t __UINT32_TYPE__
-#define uint64_t __UINT64_TYPE__
-#define CHAR_BIT __CHAR_BIT__
-#define INT_MAX __INTMAX_MAX__
-#endif // __HIPCC_RTC__
-
 #include <__clang_hip_libdevice_declares.h>
 #include <__clang_hip_math.h>
 



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] ccb1026 - [HIP] Move std headers after device malloc/free

2021-07-09 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2021-07-09T21:20:16Z
New Revision: ccb10266f56bc34123eb7741c6ebcd5ba8ed3dcc

URL: 
https://github.com/llvm/llvm-project/commit/ccb10266f56bc34123eb7741c6ebcd5ba8ed3dcc
DIFF: 
https://github.com/llvm/llvm-project/commit/ccb10266f56bc34123eb7741c6ebcd5ba8ed3dcc.diff

LOG: [HIP] Move std headers after device malloc/free

Set the device malloc and free functions as weak,
and move the std headers after device malloc/free
to avoid issues with std malloc/free.

Fixes: SWDEV-293590

Reviewed By: yaxunl

Differential Revision: https://reviews.llvm.org/D105707

Added: 


Modified: 
clang/lib/Headers/__clang_hip_runtime_wrapper.h
clang/test/Headers/hip-header.hip

Removed: 




diff  --git a/clang/lib/Headers/__clang_hip_runtime_wrapper.h 
b/clang/lib/Headers/__clang_hip_runtime_wrapper.h
index c557796c8fa0a..6aefbeaec566f 100644
--- a/clang/lib/Headers/__clang_hip_runtime_wrapper.h
+++ b/clang/lib/Headers/__clang_hip_runtime_wrapper.h
@@ -18,28 +18,6 @@
 
 #if __HIP__
 
-#if !defined(__HIPCC_RTC__)
-#include 
-#include 
-#include 
-#else
-typedef __SIZE_TYPE__ size_t;
-// Define macros which are needed to declare HIP device API's without standard
-// C/C++ headers. This is for readability so that these API's can be written
-// the same way as non-hipRTC use case. These macros need to be popped so that
-// they do not pollute users' name space.
-#pragma push_macro("NULL")
-#pragma push_macro("uint32_t")
-#pragma push_macro("uint64_t")
-#pragma push_macro("CHAR_BIT")
-#pragma push_macro("INT_MAX")
-#define NULL (void *)0
-#define uint32_t __UINT32_TYPE__
-#define uint64_t __UINT64_TYPE__
-#define CHAR_BIT __CHAR_BIT__
-#define INT_MAX __INTMAX_MAX__
-#endif // __HIPCC_RTC__
-
 #define __host__ __attribute__((host))
 #define __device__ __attribute__((device))
 #define __global__ __attribute__((global))
@@ -68,24 +46,58 @@ extern "C" {
 }
 #endif //__cplusplus
 
+typedef __SIZE_TYPE__ __hip_size_t;
+
+#ifdef __cplusplus
+extern "C" {
+#endif //__cplusplus
+
 #if __HIP_ENABLE_DEVICE_MALLOC__
-extern "C" __device__ void *__hip_malloc(size_t __size);
-extern "C" __device__ void *__hip_free(void *__ptr);
-static inline __device__ void *malloc(size_t __size) {
+__device__ void *__hip_malloc(__hip_size_t __size);
+__device__ void *__hip_free(void *__ptr);
+__attribute__((weak)) inline __device__ void *malloc(__hip_size_t __size) {
   return __hip_malloc(__size);
 }
-static inline __device__ void *free(void *__ptr) { return __hip_free(__ptr); }
+__attribute__((weak)) inline __device__ void *free(void *__ptr) {
+  return __hip_free(__ptr);
+}
 #else
-static inline __device__ void *malloc(size_t __size) {
+__attribute__((weak)) inline __device__ void *malloc(__hip_size_t __size) {
   __builtin_trap();
   return nullptr;
 }
-static inline __device__ void *free(void *__ptr) {
+__attribute__((weak)) inline __device__ void *free(void *__ptr) {
   __builtin_trap();
   return nullptr;
 }
 #endif
 
+#ifdef __cplusplus
+} // extern "C"
+#endif //__cplusplus
+
+#if !defined(__HIPCC_RTC__)
+#include 
+#include 
+#include 
+#else
+typedef __SIZE_TYPE__ size_t;
+// Define macros which are needed to declare HIP device API's without standard
+// C/C++ headers. This is for readability so that these API's can be written
+// the same way as non-hipRTC use case. These macros need to be popped so that
+// they do not pollute users' name space.
+#pragma push_macro("NULL")
+#pragma push_macro("uint32_t")
+#pragma push_macro("uint64_t")
+#pragma push_macro("CHAR_BIT")
+#pragma push_macro("INT_MAX")
+#define NULL (void *)0
+#define uint32_t __UINT32_TYPE__
+#define uint64_t __UINT64_TYPE__
+#define CHAR_BIT __CHAR_BIT__
+#define INT_MAX __INTMAX_MAX__
+#endif // __HIPCC_RTC__
+
 #include <__clang_hip_libdevice_declares.h>
 #include <__clang_hip_math.h>
 

diff  --git a/clang/test/Headers/hip-header.hip 
b/clang/test/Headers/hip-header.hip
index 0e95d58d55700..aa7abcedb7ae4 100644
--- a/clang/test/Headers/hip-header.hip
+++ b/clang/test/Headers/hip-header.hip
@@ -115,3 +115,19 @@ __device__ double test_isnan() {
 
   return r ;
 }
+
+// Check that device malloc and free do not conflict with std headers.
+#include 
+// CHECK-LABEL: define{{.*}}@_Z11test_malloc
+// CHECK: call {{.*}}i8* @malloc(i64
+// CHECK: define weak {{.*}}i8* @malloc(i64
+__device__ void test_malloc(void *a) {
+  a = malloc(42);
+}
+
+// CHECK-LABEL: define{{.*}}@_Z9test_free
+// CHECK: call {{.*}}i8* @free(i8*
+// CHECK: define weak {{.*}}i8* @free(i8*
+__device__ void test_free(void *a) {
+  free(a);
+}



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] f2cc042 - [HIP] Fix --hip-version flag with 0 as component

2021-06-11 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2021-06-11T16:25:03Z
New Revision: f2cc0427b13ef10e67eed6eab9eefb58e8aef3d9

URL: 
https://github.com/llvm/llvm-project/commit/f2cc0427b13ef10e67eed6eab9eefb58e8aef3d9
DIFF: 
https://github.com/llvm/llvm-project/commit/f2cc0427b13ef10e67eed6eab9eefb58e8aef3d9.diff

LOG: [HIP] Fix --hip-version flag with 0 as component

Allow the usage of minor version 0, for hip versions
such as 4.0. Change the default values when performing
version checks.

Reviewed By: yaxunl

Differential Revision: https://reviews.llvm.org/D104062

Added: 


Modified: 
clang/lib/Driver/ToolChains/AMDGPU.cpp
clang/test/Driver/hip-version.hip

Removed: 




diff  --git a/clang/lib/Driver/ToolChains/AMDGPU.cpp 
b/clang/lib/Driver/ToolChains/AMDGPU.cpp
index ea3a4b4a8fd1..2e92be51f69e 100644
--- a/clang/lib/Driver/ToolChains/AMDGPU.cpp
+++ b/clang/lib/Driver/ToolChains/AMDGPU.cpp
@@ -316,8 +316,8 @@ RocmInstallationDetector::RocmInstallationDetector(
   HIPPathArg = Args.getLastArgValue(clang::driver::options::OPT_hip_path_EQ);
   if (auto *A = Args.getLastArg(clang::driver::options::OPT_hip_version_EQ)) {
 HIPVersionArg = A->getValue();
-unsigned Major = 0;
-unsigned Minor = 0;
+unsigned Major = ~0U;
+unsigned Minor = ~0U;
 SmallVector Parts;
 HIPVersionArg.split(Parts, '.');
 if (Parts.size())
@@ -328,7 +328,9 @@ RocmInstallationDetector::RocmInstallationDetector(
   VersionPatch = Parts[2].str();
 if (VersionPatch.empty())
   VersionPatch = "0";
-if (Major == 0 || Minor == 0)
+if (Major != ~0U && Minor == ~0U)
+  Minor = 0;
+if (Major == ~0U || Minor == ~0U)
   D.Diag(diag::err_drv_invalid_value)
   << A->getAsString(Args) << HIPVersionArg;
 

diff  --git a/clang/test/Driver/hip-version.hip 
b/clang/test/Driver/hip-version.hip
index eb1295210cfc..83b8dbddf228 100644
--- a/clang/test/Driver/hip-version.hip
+++ b/clang/test/Driver/hip-version.hip
@@ -36,6 +36,16 @@
 
 // SPECIFIED2: Found HIP installation: {{.*Driver}}, version 3.7.0
 
+// RUN: %clang -v --rocm-path=%S --hip-version=4.0.21025 2>&1 \
+// RUN:   | FileCheck -check-prefixes=SPECIFIED3 %s
+
+// SPECIFIED3: Found HIP installation: {{.*Driver}}, version 4.0.21025
+
+// RUN: %clang -v --rocm-path=%S --hip-version=4 2>&1 \
+// RUN:   | FileCheck -check-prefixes=SPECIFIED4 %s
+
+// SPECIFIED4: Found HIP installation: {{.*Driver}}, version 4.0.0
+
 // RUN: not %clang -v --rocm-path=%S --hip-version=x.y 2>&1 \
 // RUN:   | FileCheck -check-prefixes=INVALID %s
 



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] a249ffa - [HIP] Clean up llvm intrinsics using __asm

2021-05-13 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2021-05-13T18:55:51Z
New Revision: a249ffa42137431d44d7db1d04f122300bc51533

URL: 
https://github.com/llvm/llvm-project/commit/a249ffa42137431d44d7db1d04f122300bc51533
DIFF: 
https://github.com/llvm/llvm-project/commit/a249ffa42137431d44d7db1d04f122300bc51533.diff

LOG: [HIP] Clean up llvm intrinsics using __asm

Instead of using inline asm, use clang builtins
for llvm intrinsics.

Differential Revision: https://reviews.llvm.org/D102427

Added: 


Modified: 
clang/lib/Headers/__clang_hip_libdevice_declares.h

Removed: 




diff  --git a/clang/lib/Headers/__clang_hip_libdevice_declares.h 
b/clang/lib/Headers/__clang_hip_libdevice_declares.h
index ac98907ad5de6..8be848ba2aa36 100644
--- a/clang/lib/Headers/__clang_hip_libdevice_declares.h
+++ b/clang/lib/Headers/__clang_hip_libdevice_declares.h
@@ -138,14 +138,22 @@ __device__ __attribute__((const)) float 
__ocml_fma_rtn_f32(float, float, float);
 __device__ __attribute__((const)) float __ocml_fma_rtp_f32(float, float, 
float);
 __device__ __attribute__((const)) float __ocml_fma_rtz_f32(float, float, 
float);
 
-__device__ __attribute__((const)) float
-__llvm_amdgcn_cos_f32(float) __asm("llvm.amdgcn.cos.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_rcp_f32(float) __asm("llvm.amdgcn.rcp.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_rsq_f32(float) __asm("llvm.amdgcn.rsq.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_sin_f32(float) __asm("llvm.amdgcn.sin.f32");
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_cos_f32(float __x) {
+  return __builtin_amdgcn_cosf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_rcp_f32(float __x) {
+  return __builtin_amdgcn_rcpf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_rsq_f32(float __x) {
+  return __builtin_amdgcn_rsqf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_sin_f32(float __x) {
+  return __builtin_amdgcn_sinf(__x);
+}
 // END INTRINSICS
 // END FLOAT
 
@@ -269,10 +277,14 @@ __device__ __attribute__((const)) double 
__ocml_fma_rtp_f64(double, double,
 __device__ __attribute__((const)) double __ocml_fma_rtz_f64(double, double,
 double);
 
-__device__ __attribute__((const)) double
-__llvm_amdgcn_rcp_f64(double) __asm("llvm.amdgcn.rcp.f64");
-__device__ __attribute__((const)) double
-__llvm_amdgcn_rsq_f64(double) __asm("llvm.amdgcn.rsq.f64");
+__device__ inline __attribute__((const)) double
+__llvm_amdgcn_rcp_f64(double __x) {
+  return __builtin_amdgcn_rcp(__x);
+}
+__device__ inline __attribute__((const)) double
+__llvm_amdgcn_rsq_f64(double __x) {
+  return __builtin_amdgcn_rsq(__x);
+}
 
 __device__ __attribute__((const)) _Float16 __ocml_ceil_f16(_Float16);
 __device__ _Float16 __ocml_cos_f16(_Float16);



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] 6a67e05 - [HIP] Add __builtin_amdgcn_groupstaticsize

2021-05-13 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2021-05-13T15:50:08Z
New Revision: 6a67e05a26eb5f58665bd6d063b9f389e7dd28a7

URL: 
https://github.com/llvm/llvm-project/commit/6a67e05a26eb5f58665bd6d063b9f389e7dd28a7
DIFF: 
https://github.com/llvm/llvm-project/commit/6a67e05a26eb5f58665bd6d063b9f389e7dd28a7.diff

LOG: [HIP] Add __builtin_amdgcn_groupstaticsize

Differential Revision: https://reviews.llvm.org/D102403

Added: 


Modified: 
clang/include/clang/Basic/BuiltinsAMDGPU.def
clang/test/CodeGenOpenCL/builtins-amdgcn-ci.cl
clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl
clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl

Removed: 




diff  --git a/clang/include/clang/Basic/BuiltinsAMDGPU.def 
b/clang/include/clang/Basic/BuiltinsAMDGPU.def
index 7dcbf9a096961..e3782fc403bdd 100644
--- a/clang/include/clang/Basic/BuiltinsAMDGPU.def
+++ b/clang/include/clang/Basic/BuiltinsAMDGPU.def
@@ -65,6 +65,7 @@ BUILTIN(__builtin_amdgcn_ds_gws_sema_v, "vUi", "n")
 BUILTIN(__builtin_amdgcn_ds_gws_sema_br, "vUiUi", "n")
 BUILTIN(__builtin_amdgcn_ds_gws_sema_p, "vUi", "n")
 BUILTIN(__builtin_amdgcn_fence, "vUicC*", "n")
+BUILTIN(__builtin_amdgcn_groupstaticsize, "Ui", "n")
 
 BUILTIN(__builtin_amdgcn_atomic_inc32, "UZiUZiD*UZiUicC*", "n")
 BUILTIN(__builtin_amdgcn_atomic_inc64, "UWiUWiD*UWiUicC*", "n")

diff  --git a/clang/test/CodeGenOpenCL/builtins-amdgcn-ci.cl 
b/clang/test/CodeGenOpenCL/builtins-amdgcn-ci.cl
index 56da7eceb6deb..15ddd17316a71 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn-ci.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-ci.cl
@@ -62,3 +62,9 @@ int test_is_shared_global(const global int* ptr) {
 int test_is_private_global(const global int* ptr) {
   return __builtin_amdgcn_is_private(ptr);
 }
+
+// CHECK-LABEL: @test_groupstaticsize
+// CHECK: call i32 @llvm.amdgcn.groupstaticsize()
+void test_groupstaticsize(global uint* out) {
+  *out = __builtin_amdgcn_groupstaticsize();
+}

diff  --git a/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl 
b/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl
index a9bbaa9c3f54f..3b21d41659bbd 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx10.cl
@@ -30,3 +30,10 @@ void test_s_memtime(global ulong* out)
 {
   *out = __builtin_amdgcn_s_memtime();
 }
+
+// CHECK-LABEL: @test_groupstaticsize
+// CHECK: call i32 @llvm.amdgcn.groupstaticsize()
+void test_groupstaticsize(global uint* out)
+{
+  *out = __builtin_amdgcn_groupstaticsize();
+}

diff  --git a/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl 
b/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
index 420506ec083c1..3bc1811a35b71 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
@@ -3,6 +3,7 @@
 // RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -S 
-emit-llvm -o - %s | FileCheck %s
 
 #pragma OPENCL EXTENSION cl_khr_fp16 : enable
+typedef unsigned int uint;
 typedef unsigned long ulong;
 
 // CHECK-LABEL: @test_fmed3_f16
@@ -18,3 +19,10 @@ void test_s_memtime(global ulong* out)
 {
   *out = __builtin_amdgcn_s_memtime();
 }
+
+// CHECK-LABEL: @test_groupstaticsize
+// CHECK: call i32 @llvm.amdgcn.groupstaticsize()
+void test_groupstaticsize(global uint* out)
+{
+  *out = __builtin_amdgcn_groupstaticsize();
+}

diff  --git a/clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl 
b/clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
index be594585fad6d..fe2c1692fbcc4 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
@@ -145,3 +145,10 @@ void test_perm(global uint* out, uint a, uint b, uint s)
 {
   *out = __builtin_amdgcn_perm(a, b, s);
 }
+
+// CHECK-LABEL: @test_groupstaticsize
+// CHECK: call i32 @llvm.amdgcn.groupstaticsize()
+void test_groupstaticsize(global uint* out)
+{
+  *out = __builtin_amdgcn_groupstaticsize();
+}



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] df59850 - [HIP] Fix rocm-detect.hip test path

2021-04-07 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2021-04-07T17:20:59Z
New Revision: df59850038d800e8e8b062a5fc2e3d4ed624b526

URL: 
https://github.com/llvm/llvm-project/commit/df59850038d800e8e8b062a5fc2e3d4ed624b526
DIFF: 
https://github.com/llvm/llvm-project/commit/df59850038d800e8e8b062a5fc2e3d4ed624b526.diff

LOG: [HIP] Fix rocm-detect.hip test path

The ROCm installation directory may be another
directory, llvm/ inside the build directory.

Reviewed By: yaxunl

Differential Revision: https://reviews.llvm.org/D100045

Added: 


Modified: 
clang/test/Driver/rocm-detect.hip

Removed: 




diff  --git a/clang/test/Driver/rocm-detect.hip 
b/clang/test/Driver/rocm-detect.hip
index 1e21323ba218..5df5d2a9be06 100644
--- a/clang/test/Driver/rocm-detect.hip
+++ b/clang/test/Driver/rocm-detect.hip
@@ -81,7 +81,7 @@
 
 // SPACK: ROCm installation search path (Spack 4.0.0): [[DIR:.*]]
 // SPACK: ROCm installation search path: [[CLANG:.*]]
-// SPACK: ROCm installation search path: [[CLANG]]/lib/clang/{{[0-9.]+}}
+// SPACK: ROCm installation search path: 
[[CLANG]]/{{(llvm/)?}}lib/clang/{{[0-9.]+}}
 // SPACK: ROCm installation search path: /opt/rocm
 // SPACK: InstalledDir: 
[[DIR]]/llvm-amdgpu-4.0.0-ieagcs7inf7runpyfvepqkurasoglq4z/bin
 // SPACK: Found HIP installation: 
[[DIR]]/hip-4.0.0-5f63slrursbrvfe2txrrjkynbsywsob5, version 4.0.20214-a2917cd



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] be40c12 - [HIP] Add signbit(long double) decl

2021-01-14 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2021-01-14T18:23:37Z
New Revision: be40c12040a0d5551bf3430cbb184b5ef23e25fd

URL: 
https://github.com/llvm/llvm-project/commit/be40c12040a0d5551bf3430cbb184b5ef23e25fd
DIFF: 
https://github.com/llvm/llvm-project/commit/be40c12040a0d5551bf3430cbb184b5ef23e25fd.diff

LOG: [HIP] Add signbit(long double) decl

An _MSC_VER version of signbit(long double) is required for MSVC headers.

Fixes: SWDEV-256409

Differential Revision: https://reviews.llvm.org/D93062

Added: 


Modified: 
clang/lib/Headers/__clang_cuda_math_forward_declares.h

Removed: 




diff  --git a/clang/lib/Headers/__clang_cuda_math_forward_declares.h 
b/clang/lib/Headers/__clang_cuda_math_forward_declares.h
index 8a270859e4a5..c0f1f47cc993 100644
--- a/clang/lib/Headers/__clang_cuda_math_forward_declares.h
+++ b/clang/lib/Headers/__clang_cuda_math_forward_declares.h
@@ -160,6 +160,9 @@ __DEVICE__ double scalbln(double, long);
 __DEVICE__ float scalbln(float, long);
 __DEVICE__ double scalbn(double, int);
 __DEVICE__ float scalbn(float, int);
+#ifdef _MSC_VER
+__DEVICE__ bool signbit(long double);
+#endif
 __DEVICE__ bool signbit(double);
 __DEVICE__ bool signbit(float);
 __DEVICE__ double sin(double);



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] ba2612c - [HIP] cmath demote long double args to double

2020-12-03 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-12-03T23:00:14Z
New Revision: ba2612ce01eae5859ae7adb99161775fb2c4e0b2

URL: 
https://github.com/llvm/llvm-project/commit/ba2612ce01eae5859ae7adb99161775fb2c4e0b2
DIFF: 
https://github.com/llvm/llvm-project/commit/ba2612ce01eae5859ae7adb99161775fb2c4e0b2.diff

LOG: [HIP] cmath demote long double args to double

Since there is no ROCm Device Library support for
long double, demote them to double, and use the fp64
math functions.

Differential Revision: https://reviews.llvm.org/D92130

Added: 


Modified: 
clang/lib/Headers/__clang_hip_cmath.h

Removed: 




diff  --git a/clang/lib/Headers/__clang_hip_cmath.h 
b/clang/lib/Headers/__clang_hip_cmath.h
index 00519a9795bc..3a702587ee17 100644
--- a/clang/lib/Headers/__clang_hip_cmath.h
+++ b/clang/lib/Headers/__clang_hip_cmath.h
@@ -224,6 +224,8 @@ template  struct __numeric_type {
   static double __test(long long);
   static double __test(unsigned long long);
   static double __test(double);
+  // No support for long double, use double instead.
+  static double __test(long double);
 
   typedef decltype(__test(std::declval<_Tp>())) type;
   static const bool value = !std::is_same::value;



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] cd5897d - [HIP] Fix static-lib test CHECK bug

2020-12-01 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-12-01T15:49:39Z
New Revision: cd5897d55908827faf3e16c505bd79732a8f6eb6

URL: 
https://github.com/llvm/llvm-project/commit/cd5897d55908827faf3e16c505bd79732a8f6eb6
DIFF: 
https://github.com/llvm/llvm-project/commit/cd5897d55908827faf3e16c505bd79732a8f6eb6.diff

LOG: [HIP] Fix static-lib test CHECK bug

Fix hip test failures that were introduced by
previous changes to hip-toolchain-rdc-static-lib.hip
test. The .*lld.* is matching a longer string than
expected.

Differential Revision: https://reviews.llvm.org/D92342

Added: 


Modified: 
clang/test/Driver/hip-toolchain-rdc-static-lib.hip

Removed: 




diff  --git a/clang/test/Driver/hip-toolchain-rdc-static-lib.hip 
b/clang/test/Driver/hip-toolchain-rdc-static-lib.hip
index 533d3457d5b4..b698ec763249 100644
--- a/clang/test/Driver/hip-toolchain-rdc-static-lib.hip
+++ b/clang/test/Driver/hip-toolchain-rdc-static-lib.hip
@@ -47,7 +47,9 @@
 // CHECK-NOT: "*.llvm-link"
 // CHECK-NOT: ".*opt"
 // CHECK-NOT: ".*llc"
-// CHECK: [[LLD: ".*lld.*"]] {{.*}} "-o" "[[IMG_DEV1:.*out]]" [[A_BC1]] 
[[B_BC1]]
+// CHECK: [[LLD: ".*lld.*"]] {{.*}} "-plugin-opt=-amdgpu-internalize-symbols"
+// CHECK-SAME: "-plugin-opt=mcpu=gfx803"
+// CHECK-SAME: "-o" "[[IMG_DEV1:.*out]]" [[A_BC1]] [[B_BC1]]
 
 // generate image for device side path on gfx900
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
@@ -71,7 +73,9 @@
 // CHECK-NOT: "*.llvm-link"
 // CHECK-NOT: ".*opt"
 // CHECK-NOT: ".*llc"
-// CHECK: [[LLD]] {{.*}} "-o" "[[IMG_DEV2:.*out]]" [[A_BC2]] [[B_BC2]]
+// CHECK: [[LLD]] {{.*}} "-plugin-opt=-amdgpu-internalize-symbols"
+// CHECK-SAME: "-plugin-opt=mcpu=gfx900"
+// CHECK-SAME: "-o" "[[IMG_DEV2:.*out]]" [[A_BC2]] [[B_BC2]]
 
 // combine images generated into hip fat binary object
 // CHECK: [[BUNDLER:".*clang-offload-bundler"]] "-type=o"



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] f89e9c8 - [HIP] Fix HIP test on windows due to lld suffix

2020-11-30 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-11-30T21:05:26Z
New Revision: f89e9c8201ea5a5b63af854c92ed26bc7ab4b8db

URL: 
https://github.com/llvm/llvm-project/commit/f89e9c8201ea5a5b63af854c92ed26bc7ab4b8db
DIFF: 
https://github.com/llvm/llvm-project/commit/f89e9c8201ea5a5b63af854c92ed26bc7ab4b8db.diff

LOG: [HIP] Fix HIP test on windows due to lld suffix

On Windows, lld is instead named lld.exe, therefore
a few HIP tests are failing. Instead the wildcard should
be modified to .*lld.* to handle .exe. This fixes the
bug: https://bugs.llvm.org/show_bug.cgi?id=48289.

Differential Revision: https://reviews.llvm.org/D92342

Added: 


Modified: 
clang/test/Driver/hip-toolchain-rdc-static-lib.hip
clang/test/Driver/hip-toolchain-rdc.hip

Removed: 




diff  --git a/clang/test/Driver/hip-toolchain-rdc-static-lib.hip 
b/clang/test/Driver/hip-toolchain-rdc-static-lib.hip
index dc29b0f87e36..533d3457d5b4 100644
--- a/clang/test/Driver/hip-toolchain-rdc-static-lib.hip
+++ b/clang/test/Driver/hip-toolchain-rdc-static-lib.hip
@@ -47,7 +47,7 @@
 // CHECK-NOT: "*.llvm-link"
 // CHECK-NOT: ".*opt"
 // CHECK-NOT: ".*llc"
-// CHECK: [[LLD: ".*lld"]] {{.*}} "-o" "[[IMG_DEV1:.*out]]" [[A_BC1]] [[B_BC1]]
+// CHECK: [[LLD: ".*lld.*"]] {{.*}} "-o" "[[IMG_DEV1:.*out]]" [[A_BC1]] 
[[B_BC1]]
 
 // generate image for device side path on gfx900
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
@@ -78,6 +78,6 @@
 // CHECK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
+// CHECK: [[MC:".*llvm-mc.*"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
 
 // CHECK: [[AR:".*llvm-ar.*"]] "rcsD" "{{.*}}.out" [[A_OBJ_HOST]] 
[[B_OBJ_HOST]] [[OBJBUNDLE]]

diff  --git a/clang/test/Driver/hip-toolchain-rdc.hip 
b/clang/test/Driver/hip-toolchain-rdc.hip
index 8d8e67514035..d6d47ec1b07e 100644
--- a/clang/test/Driver/hip-toolchain-rdc.hip
+++ b/clang/test/Driver/hip-toolchain-rdc.hip
@@ -95,7 +95,7 @@
 // CHECK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
+// CHECK: [[MC:".*llvm-mc.*"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
 
 // output the executable
 // CHECK: [[LD:".*ld.*"]] {{.*}}"-o" "a.out" {{.*}} [[A_OBJ_HOST]] 
[[B_OBJ_HOST]] [[OBJBUNDLE]]



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] ca5b315 - [HIP] Math Headers to use type promotion

2020-11-03 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-11-03T18:40:26Z
New Revision: ca5b31502c828f8e7160a77f54a5a131dc298005

URL: 
https://github.com/llvm/llvm-project/commit/ca5b31502c828f8e7160a77f54a5a131dc298005
DIFF: 
https://github.com/llvm/llvm-project/commit/ca5b31502c828f8e7160a77f54a5a131dc298005.diff

LOG: [HIP] Math Headers to use type promotion

Similar to libcxx implementation of cmath function
overloads, use type promotion templates to determine
return types of multi-argument math functions.

Fixes: SWDEV-256825

Reviewed By: tra, yaxunl

Differential Revision: https://reviews.llvm.org/D90409

Added: 


Modified: 
clang/lib/Headers/__clang_hip_cmath.h

Removed: 




diff  --git a/clang/lib/Headers/__clang_hip_cmath.h 
b/clang/lib/Headers/__clang_hip_cmath.h
index fea799ead32f..00519a9795bc 100644
--- a/clang/lib/Headers/__clang_hip_cmath.h
+++ b/clang/lib/Headers/__clang_hip_cmath.h
@@ -16,6 +16,8 @@
 
 #if defined(__cplusplus)
 #include 
+#include 
+#include 
 #endif
 #include 
 #include 
@@ -205,6 +207,72 @@ template  struct 
__hip_enable_if {};
 
 template  struct __hip_enable_if { typedef __T type; };
 
+// decltype is only available in C++11 and above.
+#if __cplusplus >= 201103L
+// __hip_promote
+namespace __hip {
+
+template  struct __numeric_type {
+  static void __test(...);
+  static _Float16 __test(_Float16);
+  static float __test(float);
+  static double __test(char);
+  static double __test(int);
+  static double __test(unsigned);
+  static double __test(long);
+  static double __test(unsigned long);
+  static double __test(long long);
+  static double __test(unsigned long long);
+  static double __test(double);
+
+  typedef decltype(__test(std::declval<_Tp>())) type;
+  static const bool value = !std::is_same::value;
+};
+
+template <> struct __numeric_type { static const bool value = true; };
+
+template ::value &&__numeric_type<_A2>::value
+  &&__numeric_type<_A3>::value>
+class __promote_imp {
+public:
+  static const bool value = false;
+};
+
+template 
+class __promote_imp<_A1, _A2, _A3, true> {
+private:
+  typedef typename __promote_imp<_A1>::type __type1;
+  typedef typename __promote_imp<_A2>::type __type2;
+  typedef typename __promote_imp<_A3>::type __type3;
+
+public:
+  typedef decltype(__type1() + __type2() + __type3()) type;
+  static const bool value = true;
+};
+
+template  class __promote_imp<_A1, _A2, void, true> {
+private:
+  typedef typename __promote_imp<_A1>::type __type1;
+  typedef typename __promote_imp<_A2>::type __type2;
+
+public:
+  typedef decltype(__type1() + __type2()) type;
+  static const bool value = true;
+};
+
+template  class __promote_imp<_A1, void, void, true> {
+public:
+  typedef typename __numeric_type<_A1>::type type;
+  static const bool value = true;
+};
+
+template 
+class __promote : public __promote_imp<_A1, _A2, _A3> {};
+
+} // namespace __hip
+#endif //__cplusplus >= 201103L
+
 // __HIP_OVERLOAD1 is used to resolve function calls with integer argument to
 // avoid compilation error due to ambibuity. e.g. floor(5) is resolved with
 // floor(double).
@@ -219,6 +287,18 @@ template  struct __hip_enable_if { 
typedef __T type; };
 // __HIP_OVERLOAD2 is used to resolve function calls with mixed float/double
 // or integer argument to avoid compilation error due to ambibuity. e.g.
 // max(5.0f, 6.0) is resolved with max(double, double).
+#if __cplusplus >= 201103L
+#define __HIP_OVERLOAD2(__retty, __fn) 
\
+  template   
\
+  __DEVICE__ typename __hip_enable_if< 
\
+  std::numeric_limits<__T1>::is_specialized && 
\
+  std::numeric_limits<__T2>::is_specialized,   
\
+  typename __hip::__promote<__T1, __T2>::type>::type   
\
+  __fn(__T1 __x, __T2 __y) {   
\
+typedef typename __hip::__promote<__T1, __T2>::type __result_type; 
\
+return __fn((__result_type)__x, (__result_type)__y);   
\
+  }
+#else
 #define __HIP_OVERLOAD2(__retty, __fn) 
\
   template   
\
   __DEVICE__   
\
@@ -228,6 +308,7 @@ template  struct __hip_enable_if { 
typedef __T type; };
   __fn(__T1 __x, __T2 __y) {   
\
 return __fn((double)__x, (double)__y); 
\
   }
+#endif
 
 __HIP_OVERLOAD1(double, abs)
 __HIP_OVERLOAD1(double, acos)
@@ -296,6 +377,18 @@ __HIP_OVERLOAD2(double, max)
 __HIP_OVERLOAD2(double, min)
 
 // Additional Overloads that don't quite match HIP_OVERLOAD.
+#if __cplusplus >= 201103L
+template 
+__DEVICE__ typename __hip_enable_if<
+

[clang] 3700556 - [HIP][NFC] Use correct max in cuda_complex_builtins

2020-10-27 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-10-27T19:35:09Z
New Revision: 3700556ecb062abf786ad52a5474c27b22c19107

URL: 
https://github.com/llvm/llvm-project/commit/3700556ecb062abf786ad52a5474c27b22c19107
DIFF: 
https://github.com/llvm/llvm-project/commit/3700556ecb062abf786ad52a5474c27b22c19107.diff

LOG: [HIP][NFC] Use correct max in cuda_complex_builtins

Update the clang complex builtins for OpenMP to use the
correct max function from either __nv_* or __ocml_*.

Added: 


Modified: 
clang/lib/Headers/__clang_cuda_complex_builtins.h

Removed: 




diff  --git a/clang/lib/Headers/__clang_cuda_complex_builtins.h 
b/clang/lib/Headers/__clang_cuda_complex_builtins.h
index 8c10ff6b461f..9b254f700b9d 100644
--- a/clang/lib/Headers/__clang_cuda_complex_builtins.h
+++ b/clang/lib/Headers/__clang_cuda_complex_builtins.h
@@ -41,6 +41,27 @@
 #define _ABSf std::abs
 #define _LOGBd std::logb
 #define _LOGBf std::logb
+// Rather than pulling in std::max from algorithm everytime, use available 
::max.
+#define _fmaxd max
+#define _fmaxf max
+#else
+#ifdef __AMDGCN__
+#define _ISNANd __ocml_isnan_f64
+#define _ISNANf __ocml_isnan_f32
+#define _ISINFd __ocml_isinf_f64
+#define _ISINFf __ocml_isinf_f32
+#define _ISFINITEd __ocml_isfinite_f64
+#define _ISFINITEf __ocml_isfinite_f32
+#define _COPYSIGNd __ocml_copysign_f64
+#define _COPYSIGNf __ocml_copysign_f32
+#define _SCALBNd __ocml_scalbn_f64
+#define _SCALBNf __ocml_scalbn_f32
+#define _ABSd __ocml_fabs_f64
+#define _ABSf __ocml_fabs_f32
+#define _LOGBd __ocml_logb_f64
+#define _LOGBf __ocml_logb_f32
+#define _fmaxd __ocml_fmax_f64
+#define _fmaxf __ocml_fmax_f32
 #else
 #define _ISNANd __nv_isnand
 #define _ISNANf __nv_isnanf
@@ -56,6 +77,9 @@
 #define _ABSf __nv_fabsf
 #define _LOGBd __nv_logb
 #define _LOGBf __nv_logbf
+#define _fmaxd __nv_fmax
+#define _fmaxf __nv_fmaxf
+#endif
 #endif
 
 #if defined(__cplusplus)
@@ -167,7 +191,7 @@ __DEVICE__ double _Complex __divdc3(double __a, double __b, 
double __c,
   // Can't use std::max, because that's defined in , and we don't
   // want to pull that in for every compile.  The CUDA headers define
   // ::max(float, float) and ::max(double, double), which is sufficient for us.
-  double __logbw = _LOGBd(max(_ABSd(__c), _ABSd(__d)));
+  double __logbw = _LOGBd(_fmaxd(_ABSd(__c), _ABSd(__d)));
   if (_ISFINITEd(__logbw)) {
 __ilogbw = (int)__logbw;
 __c = _SCALBNd(__c, -__ilogbw);
@@ -200,7 +224,7 @@ __DEVICE__ double _Complex __divdc3(double __a, double __b, 
double __c,
 
 __DEVICE__ float _Complex __divsc3(float __a, float __b, float __c, float __d) 
{
   int __ilogbw = 0;
-  float __logbw = _LOGBf(max(_ABSf(__c), _ABSf(__d)));
+  float __logbw = _LOGBf(_fmaxf(_ABSf(__c), _ABSf(__d)));
   if (_ISFINITEf(__logbw)) {
 __ilogbw = (int)__logbw;
 __c = _SCALBNf(__c, -__ilogbw);
@@ -249,6 +273,8 @@ __DEVICE__ float _Complex __divsc3(float __a, float __b, 
float __c, float __d) {
 #undef _ABSf
 #undef _LOGBd
 #undef _LOGBf
+#undef _fmaxd
+#undef _fmaxf
 
 #ifdef _OPENMP
 #pragma omp end declare target



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] b2524eb - [HIP] Fix HIP rounding math intrinsics

2020-10-22 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-10-22T15:57:09Z
New Revision: b2524eb9445a4487115c8f94fd946d2c4c95f652

URL: 
https://github.com/llvm/llvm-project/commit/b2524eb9445a4487115c8f94fd946d2c4c95f652
DIFF: 
https://github.com/llvm/llvm-project/commit/b2524eb9445a4487115c8f94fd946d2c4c95f652.diff

LOG: [HIP] Fix HIP rounding math intrinsics

The __ocml_*_rte_f32 and __ocml_*_rte_f64 functions are not
available if OCML_BASIC_ROUNDED_OPERATIONS is not defined.

Reviewed By: b-sumner, yaxunl

Fixes: SWDEV-257235

Differential Revision: https://reviews.llvm.org/D89966

Added: 


Modified: 
clang/lib/Headers/__clang_hip_math.h

Removed: 




diff  --git a/clang/lib/Headers/__clang_hip_math.h 
b/clang/lib/Headers/__clang_hip_math.h
index f2365e8844fe..14d91c66b352 100644
--- a/clang/lib/Headers/__clang_hip_math.h
+++ b/clang/lib/Headers/__clang_hip_math.h
@@ -547,102 +547,117 @@ float __expf(float __x) { return 
__ocml_native_exp_f32(__x); }
 #if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
 float __fadd_rd(float __x, float __y) { return __ocml_add_rtn_f32(__x, __y); }
-#endif
 __DEVICE__
 float __fadd_rn(float __x, float __y) { return __ocml_add_rte_f32(__x, __y); }
-#if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
 float __fadd_ru(float __x, float __y) { return __ocml_add_rtp_f32(__x, __y); }
-
 __DEVICE__
 float __fadd_rz(float __x, float __y) { return __ocml_add_rtz_f32(__x, __y); }
+#else
+__DEVICE__
+float __fadd_rn(float __x, float __y) { return __x + __y; }
+#endif
 
+#if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
 float __fdiv_rd(float __x, float __y) { return __ocml_div_rtn_f32(__x, __y); }
-#endif
 __DEVICE__
 float __fdiv_rn(float __x, float __y) { return __ocml_div_rte_f32(__x, __y); }
-#if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
 float __fdiv_ru(float __x, float __y) { return __ocml_div_rtp_f32(__x, __y); }
-
 __DEVICE__
 float __fdiv_rz(float __x, float __y) { return __ocml_div_rtz_f32(__x, __y); }
+#else
+__DEVICE__
+float __fdiv_rn(float __x, float __y) { return __x / __y; }
 #endif
+
 __DEVICE__
 float __fdividef(float __x, float __y) { return __x / __y; }
+
 #if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
 float __fmaf_rd(float __x, float __y, float __z) {
   return __ocml_fma_rtn_f32(__x, __y, __z);
 }
-#endif
 __DEVICE__
 float __fmaf_rn(float __x, float __y, float __z) {
   return __ocml_fma_rte_f32(__x, __y, __z);
 }
-#if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
 float __fmaf_ru(float __x, float __y, float __z) {
   return __ocml_fma_rtp_f32(__x, __y, __z);
 }
-
 __DEVICE__
 float __fmaf_rz(float __x, float __y, float __z) {
   return __ocml_fma_rtz_f32(__x, __y, __z);
 }
+#else
+__DEVICE__
+float __fmaf_rn(float __x, float __y, float __z) {
+  return __ocml_fma_f32(__x, __y, __z);
+}
+#endif
 
+#if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
 float __fmul_rd(float __x, float __y) { return __ocml_mul_rtn_f32(__x, __y); }
-#endif
 __DEVICE__
 float __fmul_rn(float __x, float __y) { return __ocml_mul_rte_f32(__x, __y); }
-#if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
 float __fmul_ru(float __x, float __y) { return __ocml_mul_rtp_f32(__x, __y); }
-
 __DEVICE__
 float __fmul_rz(float __x, float __y) { return __ocml_mul_rtz_f32(__x, __y); }
-
+#else
 __DEVICE__
-float __frcp_rd(float __x) { return __llvm_amdgcn_rcp_f32(__x); }
+float __fmul_rn(float __x, float __y) { return __x * __y; }
 #endif
-__DEVICE__
-float __frcp_rn(float __x) { return __llvm_amdgcn_rcp_f32(__x); }
+
 #if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
-float __frcp_ru(float __x) { return __llvm_amdgcn_rcp_f32(__x); }
-
+float __frcp_rd(float __x) { return __ocml_div_rtn_f32(1.0f, __x); }
+__DEVICE__
+float __frcp_rn(float __x) { return __ocml_div_rte_f32(1.0f, __x); }
 __DEVICE__
-float __frcp_rz(float __x) { return __llvm_amdgcn_rcp_f32(__x); }
+float __frcp_ru(float __x) { return __ocml_div_rtp_f32(1.0f, __x); }
+__DEVICE__
+float __frcp_rz(float __x) { return __ocml_div_rtz_f32(1.0f, __x); }
+#else
+__DEVICE__
+float __frcp_rn(float __x) { return 1.0f / __x; }
 #endif
+
 __DEVICE__
 float __frsqrt_rn(float __x) { return __llvm_amdgcn_rsq_f32(__x); }
+
 #if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
 float __fsqrt_rd(float __x) { return __ocml_sqrt_rtn_f32(__x); }
-#endif
 __DEVICE__
 float __fsqrt_rn(float __x) { return __ocml_sqrt_rte_f32(__x); }
-#if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
 float __fsqrt_ru(float __x) { return __ocml_sqrt_rtp_f32(__x); }
-
 __DEVICE__
 float __fsqrt_rz(float __x) { return __ocml_sqrt_rtz_f32(__x); }
+#else
+__DEVICE__
+float __fsqrt_rn(float __x) { return __ocml_native_sqrt_f32(__x); }
+#endif
 
+#if defined OCML_BASIC_ROUNDED_OPERATIONS
 __DEVICE__
 float __fsub_rd(float __x, float __y) { return __ocml_sub_rtn_f32(__x, __y); }
-#endif
 __DEVICE__
 float __fsub_rn(float __x, float __y) { return __ocml_sub_rte_f32(__x,

[clang] 8d2a0c1 - [HIP] NFC Add comments to cmath functions

2020-10-06 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-10-06T15:26:56Z
New Revision: 8d2a0c115e245e86bba4ea1c70e6d34b552031a9

URL: 
https://github.com/llvm/llvm-project/commit/8d2a0c115e245e86bba4ea1c70e6d34b552031a9
DIFF: 
https://github.com/llvm/llvm-project/commit/8d2a0c115e245e86bba4ea1c70e6d34b552031a9.diff

LOG: [HIP] NFC Add comments to cmath functions

Add missing comments to cmath functions.

Differential Revision: https://reviews.llvm.org/D88837

Added: 


Modified: 
clang/lib/Headers/__clang_hip_cmath.h

Removed: 




diff  --git a/clang/lib/Headers/__clang_hip_cmath.h 
b/clang/lib/Headers/__clang_hip_cmath.h
index 067c7e6c9d1b..fea799ead32f 100644
--- a/clang/lib/Headers/__clang_hip_cmath.h
+++ b/clang/lib/Headers/__clang_hip_cmath.h
@@ -370,7 +370,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
 #endif
 
 // Pull the new overloads we defined above into namespace std.
-// using ::abs;
+// using ::abs; - This may be considered for C++.
 using ::acos;
 using ::acosh;
 using ::asin;
@@ -419,8 +419,8 @@ using ::logb;
 using ::lrint;
 using ::lround;
 using ::modf;
-// using ::nan;
-// using ::nanf;
+// using ::nan; - This may be considered for C++.
+// using ::nanf; - This may be considered for C++.
 // using ::nanl; - This is not yet defined.
 using ::nearbyint;
 using ::nextafter;



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] aa2b593 - [HIP] Restructure hip headers to add cmath

2020-10-06 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-10-06T14:48:53Z
New Revision: aa2b593f1495a972a4a592952760ec9d5f7c01f1

URL: 
https://github.com/llvm/llvm-project/commit/aa2b593f1495a972a4a592952760ec9d5f7c01f1
DIFF: 
https://github.com/llvm/llvm-project/commit/aa2b593f1495a972a4a592952760ec9d5f7c01f1.diff

LOG: [HIP] Restructure hip headers to add cmath

Separate __clang_hip_math.h header into __clang_hip_cmath.h
and __clang_hip_math.h. Improve the math function definition,
and add missing definitions or declarations. Add missing
overloads.

Reviewed By: tra, JonChesterfield

Differential Review: https://reviews.llvm.org/D88837

Added: 
clang/lib/Headers/__clang_hip_cmath.h

Modified: 
clang/lib/Headers/CMakeLists.txt
clang/lib/Headers/__clang_hip_libdevice_declares.h
clang/lib/Headers/__clang_hip_math.h
clang/lib/Headers/__clang_hip_runtime_wrapper.h

Removed: 




diff  --git a/clang/lib/Headers/CMakeLists.txt 
b/clang/lib/Headers/CMakeLists.txt
index 95047e7069e7..533ff4506ffe 100644
--- a/clang/lib/Headers/CMakeLists.txt
+++ b/clang/lib/Headers/CMakeLists.txt
@@ -47,6 +47,7 @@ set(files
   __clang_cuda_math_forward_declares.h
   __clang_cuda_runtime_wrapper.h
   __clang_hip_libdevice_declares.h
+  __clang_hip_cmath.h
   __clang_hip_math.h
   __clang_hip_runtime_wrapper.h
   cetintrin.h

diff  --git a/clang/lib/Headers/__clang_hip_cmath.h 
b/clang/lib/Headers/__clang_hip_cmath.h
new file mode 100644
index ..067c7e6c9d1b
--- /dev/null
+++ b/clang/lib/Headers/__clang_hip_cmath.h
@@ -0,0 +1,521 @@
+/*=== __clang_hip_cmath.h - HIP cmath decls 
-===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM 
Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===---===
+ */
+
+#ifndef __CLANG_HIP_CMATH_H__
+#define __CLANG_HIP_CMATH_H__
+
+#if !defined(__HIP__)
+#error "This file is for HIP and OpenMP AMDGCN device compilation only."
+#endif
+
+#if defined(__cplusplus)
+#include 
+#endif
+#include 
+#include 
+
+#pragma push_macro("__DEVICE__")
+#define __DEVICE__ static __device__ inline __attribute__((always_inline))
+
+// Start with functions that cannot be defined by DEF macros below.
+#if defined(__cplusplus)
+__DEVICE__ double abs(double __x) { return ::fabs(__x); }
+__DEVICE__ float abs(float __x) { return ::fabsf(__x); }
+__DEVICE__ long long abs(long long __n) { return ::llabs(__n); }
+__DEVICE__ long abs(long __n) { return ::labs(__n); }
+__DEVICE__ float fma(float __x, float __y, float __z) {
+  return ::fmaf(__x, __y, __z);
+}
+__DEVICE__ int fpclassify(float __x) {
+  return __builtin_fpclassify(FP_NAN, FP_INFINITE, FP_NORMAL, FP_SUBNORMAL,
+  FP_ZERO, __x);
+}
+__DEVICE__ int fpclassify(double __x) {
+  return __builtin_fpclassify(FP_NAN, FP_INFINITE, FP_NORMAL, FP_SUBNORMAL,
+  FP_ZERO, __x);
+}
+__DEVICE__ float frexp(float __arg, int *__exp) {
+  return ::frexpf(__arg, __exp);
+}
+__DEVICE__ bool isfinite(float __x) { return ::__finitef(__x); }
+__DEVICE__ bool isfinite(double __x) { return ::__finite(__x); }
+__DEVICE__ bool isgreater(float __x, float __y) {
+  return __builtin_isgreater(__x, __y);
+}
+__DEVICE__ bool isgreater(double __x, double __y) {
+  return __builtin_isgreater(__x, __y);
+}
+__DEVICE__ bool isgreaterequal(float __x, float __y) {
+  return __builtin_isgreaterequal(__x, __y);
+}
+__DEVICE__ bool isgreaterequal(double __x, double __y) {
+  return __builtin_isgreaterequal(__x, __y);
+}
+__DEVICE__ bool isinf(float __x) { return ::__isinff(__x); }
+__DEVICE__ bool isinf(double __x) { return ::__isinf(__x); }
+__DEVICE__ bool isless(float __x, float __y) {
+  return __builtin_isless(__x, __y);
+}
+__DEVICE__ bool isless(double __x, double __y) {
+  return __builtin_isless(__x, __y);
+}
+__DEVICE__ bool islessequal(float __x, float __y) {
+  return __builtin_islessequal(__x, __y);
+}
+__DEVICE__ bool islessequal(double __x, double __y) {
+  return __builtin_islessequal(__x, __y);
+}
+__DEVICE__ bool islessgreater(float __x, float __y) {
+  return __builtin_islessgreater(__x, __y);
+}
+__DEVICE__ bool islessgreater(double __x, double __y) {
+  return __builtin_islessgreater(__x, __y);
+}
+__DEVICE__ bool isnan(float __x) { return ::__isnanf(__x); }
+__DEVICE__ bool isnan(double __x) { return ::__isnan(__x); }
+__DEVICE__ bool isnormal(float __x) { return __builtin_isnormal(__x); }
+__DEVICE__ bool isnormal(double __x) { return __builtin_isnormal(__x); }
+__DEVICE__ bool isunordered(float __x, float __y) {
+  return __builtin_isunordered(__x, __y);
+}
+__DEVICE__ bool isunordered(double __x, double __y) {
+  return __builtin_isunordered(__x, __y);
+}
+__DEVICE__ float modf(float __x, float *__iptr) { return

[clang] 96c2d5e - [HIP] Ignore invalid ar linker options

2020-08-06 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-08-06T17:39:41Z
New Revision: 96c2d5e99e32340be1379959977f2d6247788db6

URL: 
https://github.com/llvm/llvm-project/commit/96c2d5e99e32340be1379959977f2d6247788db6
DIFF: 
https://github.com/llvm/llvm-project/commit/96c2d5e99e32340be1379959977f2d6247788db6.diff

LOG: [HIP] Ignore invalid ar linker options

Instead of accepting the same arguments as regular linker,
the static linker will only accept input files.

Reviewed By: yaxunl

Differential Revision: https://reviews.llvm.org/D85442

Added: 


Modified: 
clang/lib/Driver/ToolChains/Gnu.cpp
clang/test/Driver/hip-link-static-library.hip

Removed: 




diff  --git a/clang/lib/Driver/ToolChains/Gnu.cpp 
b/clang/lib/Driver/ToolChains/Gnu.cpp
index 9ca674511dab..d423a71b5cca 100644
--- a/clang/lib/Driver/ToolChains/Gnu.cpp
+++ b/clang/lib/Driver/ToolChains/Gnu.cpp
@@ -341,12 +341,17 @@ void tools::gnutools::StaticLibTool::ConstructJob(
   // Silence warnings when linking C code with a C++ '-stdlib' argument.
   Args.ClaimAllArgs(options::OPT_stdlib_EQ);
 
-  // GNU ar tool command "ar   ".
+  // ar tool command "llvm-ar   ".
   ArgStringList CmdArgs;
   // Create and insert file members with a deterministic index.
   CmdArgs.push_back("rcsD");
   CmdArgs.push_back(Output.getFilename());
-  AddLinkerInputs(getToolChain(), Inputs, Args, CmdArgs, JA);
+
+  for (const auto  : Inputs) {
+if (II.isFilename()) {
+   CmdArgs.push_back(II.getFilename());
+}
+  }
 
   // Delete old output archive file if it already exists before generating a 
new
   // archive file.

diff  --git a/clang/test/Driver/hip-link-static-library.hip 
b/clang/test/Driver/hip-link-static-library.hip
index 55c5a5acc5ca..e670980fa486 100644
--- a/clang/test/Driver/hip-link-static-library.hip
+++ b/clang/test/Driver/hip-link-static-library.hip
@@ -25,3 +25,14 @@
 
 // NORDC-NOT: offload bundler
 // NORDC: # "x86_64-unknown-linux-gnu" - "GNU::StaticLibTool", inputs: 
["{{.*o}}"], output: "a.out"
+
+// RUN: %clang --hip-link -### -target x86_64-linux-gnu \
+// RUN:   --emit-static-lib -lgcc \
+// RUN:   -Wl,--enable-new-dtags -Wl,--rpath=/opt \
+// RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 -fgpu-rdc %t.o\
+// RUN: 2>&1 | FileCheck -check-prefix=NOFLAG %s
+
+// NOFLAG-NOT: .*lgcc
+// NOFLAG-NOT: .*enable-new-dtags
+// NOFLAG-NOT: .*rpath=/opt
+// NOFLAG: "{{.*}}llvm-ar{{.*}}" "rcsD" "{{.*}}.out" "{{.*o}}" "{{.*o}}"



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] c64bb3f - [HIP] Use default triple in llvm-mc for system ld

2020-07-07 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-07-07T16:44:51Z
New Revision: c64bb3f7367a924e9d17dfc1c92897e6cbe1

URL: 
https://github.com/llvm/llvm-project/commit/c64bb3f7367a924e9d17dfc1c92897e6cbe1
DIFF: 
https://github.com/llvm/llvm-project/commit/c64bb3f7367a924e9d17dfc1c92897e6cbe1.diff

LOG: [HIP] Use default triple in llvm-mc for system ld

The Ubuntu system ld does not recognize the amdgcn-amd-amdhsa target.
Instead the host object with embedded device fat binary should not be
assembled by that triple. It should use default triple, so that the
object is compatible with system ld.

Reviewed By: yaxunl

Differential Revision: https://reviews.llvm.org/D83145

Added: 


Modified: 
clang/lib/Driver/ToolChains/HIP.cpp
clang/test/Driver/hip-link-save-temps.hip
clang/test/Driver/hip-toolchain-rdc-separate.hip
clang/test/Driver/hip-toolchain-rdc-static-lib.hip
clang/test/Driver/hip-toolchain-rdc.hip

Removed: 




diff  --git a/clang/lib/Driver/ToolChains/HIP.cpp 
b/clang/lib/Driver/ToolChains/HIP.cpp
index f75be81622bf..15c9dbf3488d 100644
--- a/clang/lib/Driver/ToolChains/HIP.cpp
+++ b/clang/lib/Driver/ToolChains/HIP.cpp
@@ -193,8 +193,7 @@ void 
AMDGCN::Linker::constructGenerateObjFileFromHIPFatBinary(
 
   Objf << ObjBuffer;
 
-  ArgStringList McArgs{"-triple", Args.MakeArgString(TC.getTripleString()),
-   "-o",  Output.getFilename(),
+  ArgStringList McArgs{"-o",  Output.getFilename(),
McinFile,  "--filetype=obj"};
   const char *Mc = Args.MakeArgString(TC.GetProgramPath("llvm-mc"));
   C.addCommand(std::make_unique(JA, *this, 
ResponseFileSupport::None(),

diff  --git a/clang/test/Driver/hip-link-save-temps.hip 
b/clang/test/Driver/hip-link-save-temps.hip
index 60f71d0c5249..f2d3630dd119 100644
--- a/clang/test/Driver/hip-link-save-temps.hip
+++ b/clang/test/Driver/hip-link-save-temps.hip
@@ -45,8 +45,7 @@
 // CHECK-SAME: "-o" "a.out-hip-amdgcn-amd-amdhsa-gfx900" 
"obj1-hip-amdgcn-amd-amdhsa-gfx900.o" "obj2-hip-amdgcn-amd-amdhsa-gfx900.o"
 // CHECK: "{{.*lld.*}}" {{.*}} "-plugin-opt=-amdgpu-internalize-symbols"
 // CHECK-SAME: "-o" "a.out-hip-amdgcn-amd-amdhsa-gfx906" 
"obj1-hip-amdgcn-amd-amdhsa-gfx906.o" "obj2-hip-amdgcn-amd-amdhsa-gfx906.o"
-// CHECK: {{".*llvm-mc.*"}} "-triple" "amdgcn-amd-amdhsa" "-o"
-// CHECK-SAME: "[[OBJBUNDLE:.*.o]]" "{{.*}}.mcin" "--filetype=obj"
+// CHECK: {{".*llvm-mc.*"}} "-o" "[[OBJBUNDLE:.*.o]]" "{{.*}}.mcin" 
"--filetype=obj"
 // OUT: "{{.*ld.*}}" {{.*}} "-o" "executable" {{.*}} "[[OBJBUNDLE]]"
 // NOUT: "{{.*ld.*}}" {{.*}} "-o" "a.out" {{.*}} "[[OBJBUNDLE]]"
 // SLO: "{{.*llvm-ar.*}}" "rcsD" "libTest.a" {{.*}} "[[OBJBUNDLE]]"

diff  --git a/clang/test/Driver/hip-toolchain-rdc-separate.hip 
b/clang/test/Driver/hip-toolchain-rdc-separate.hip
index f65b95c7de77..ab89e19256be 100644
--- a/clang/test/Driver/hip-toolchain-rdc-separate.hip
+++ b/clang/test/Driver/hip-toolchain-rdc-separate.hip
@@ -122,8 +122,7 @@
 // LINK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // LINK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// LINK: {{".*llvm-mc.*"}} "-triple" "amdgcn-amd-amdhsa" "-o"
-// LINK-SAME: "[[OBJBUNDLE:.*o]]" "{{.*}}.mcin" "--filetype=obj"
+// LINK: {{".*llvm-mc.*"}} "-o" "[[OBJBUNDLE:.*o]]" "{{.*}}.mcin" 
"--filetype=obj"
 
 // LINK: [[LD:".*ld.*"]] {{.*}} "-o" "a.out" {{.*}} "[[A_OBJ_HOST]]"
 // LINK-SAME: "[[B_OBJ_HOST]]" "[[OBJBUNDLE]]"

diff  --git a/clang/test/Driver/hip-toolchain-rdc-static-lib.hip 
b/clang/test/Driver/hip-toolchain-rdc-static-lib.hip
index 56b54afbf29f..dc29b0f87e36 100644
--- a/clang/test/Driver/hip-toolchain-rdc-static-lib.hip
+++ b/clang/test/Driver/hip-toolchain-rdc-static-lib.hip
@@ -78,7 +78,6 @@
 // CHECK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-triple" "amdgcn-amd-amdhsa"
-// CHECK-SAME: "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
+// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" 
"--filetype=obj"
 
 // CHECK: [[AR:".*llvm-ar.*"]] "rcsD" "{{.*}}.out" [[A_OBJ_HOST]] 
[[B_OBJ_HOST]] [[OBJBUNDLE]]

diff  --git a/clang/test/Driver/hip-toolchain-rdc.hip 
b/clang/test/Driver/hip-toolchain-rdc.hip
index 045bbf44ae91..97d5e59c0c4b 100644
--- a/clang/test/Driver/hip-toolchain-rdc.hip
+++ b/clang/test/Driver/hip-toolchain-rdc.hip
@@ -90,8 +90,7 @@
 // CHECK-SAME: 
"-targets={{.*}},hip-amdgcn-amd-amdhsa-gfx803,hip-amdgcn-amd-amdhsa-gfx900"
 // CHECK-SAME: "-inputs={{.*}},[[IMG_DEV1]],[[IMG_DEV2]]" 
"-outputs=[[BUNDLE:.*hipfb]]"
 
-// CHECK: [[MC:".*llvm-mc"]] "-triple" "amdgcn-amd-amdhsa"
-// CHECK-SAME: "-o" [[OBJBUNDLE:".*o"]] "{{.*}}.mcin" "--filetype=obj"
+// CHECK: [[MC:".*llvm-mc"]] "-o" [[OBJBUNDLE:".*o"]]

[clang] 77df5a8 - [HIP] Move HIP Linking Logic into HIP ToolChain

2020-06-22 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-06-22T19:48:48Z
New Revision: 77df5a8283edbfc33ad3b12df3bd42d54d7ba4f4

URL: 
https://github.com/llvm/llvm-project/commit/77df5a8283edbfc33ad3b12df3bd42d54d7ba4f4
DIFF: 
https://github.com/llvm/llvm-project/commit/77df5a8283edbfc33ad3b12df3bd42d54d7ba4f4.diff

LOG: [HIP] Move HIP Linking Logic into HIP ToolChain

This patch is a follow up on https://reviews.llvm.org/D78759.

Extract the HIP Linker script from generic GNU linker,
and move it into HIP ToolChain. Update OffloadActionBuilder
Link actions feature to apply device linking and host linking
actions separately. Using MC Directives, embed the device images
and define symbols.

Reviewers: JonChesterfield, yaxunl

Subscribers: tra, echristo, jdoerfert, msearles, scchan

Differential Revision: https://reviews.llvm.org/D81963

Added: 


Modified: 
clang/lib/Driver/Driver.cpp
clang/lib/Driver/ToolChains/CommonArgs.cpp
clang/lib/Driver/ToolChains/CommonArgs.h
clang/lib/Driver/ToolChains/Gnu.cpp
clang/lib/Driver/ToolChains/HIP.cpp
clang/lib/Driver/ToolChains/HIP.h
clang/test/Driver/hip-binding.hip
clang/test/Driver/hip-link-save-temps.hip
clang/test/Driver/hip-link-shared-library.hip
clang/test/Driver/hip-phases.hip
clang/test/Driver/hip-save-temps.hip
clang/test/Driver/hip-toolchain-rdc-separate.hip
clang/test/Driver/hip-toolchain-rdc.hip

Removed: 




diff  --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index a48761af400f..de732918fc76 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -2325,8 +2325,11 @@ class OffloadingActionBuilder final {
 /// Append top level actions generated by the builder.
 virtual void appendTopLevelActions(ActionList ) {}
 
-/// Append linker actions generated by the builder.
-virtual void appendLinkActions(ActionList ) {}
+/// Append linker device actions generated by the builder.
+virtual void appendLinkDeviceActions(ActionList ) {}
+
+/// Append linker host action generated by the builder.
+virtual Action* appendLinkHostActions(ActionList ) { return nullptr; }
 
 /// Append linker actions generated by the builder.
 virtual void appendLinkDependences(OffloadAction::DeviceDependences ) {}
@@ -2796,17 +2799,45 @@ class OffloadingActionBuilder final {
: ABRT_Success;
 }
 
-void appendLinkDependences(OffloadAction::DeviceDependences ) override {
+void appendLinkDeviceActions(ActionList ) override {
+  if (DeviceLinkerInputs.size() == 0)
+return;
+
+  assert(DeviceLinkerInputs.size() == GpuArchList.size() &&
+ "Linker inputs and GPU arch list sizes do not match.");
+
   // Append a new link action for each device.
   unsigned I = 0;
   for (auto  : DeviceLinkerInputs) {
+// Each entry in DeviceLinkerInputs corresponds to a GPU arch.
 auto *DeviceLinkAction =
 C.MakeAction(LI, types::TY_Image);
-DA.add(*DeviceLinkAction, *ToolChains[0],
-   CudaArchToString(GpuArchList[I]), AssociatedOffloadKind);
+// Linking all inputs for the current GPU arch.
+// LI contains all the inputs for the linker.
+OffloadAction::DeviceDependences DeviceLinkDeps;
+DeviceLinkDeps.add(*DeviceLinkAction, *ToolChains[0],
+CudaArchToString(GpuArchList[I]), AssociatedOffloadKind);
+AL.push_back(C.MakeAction(DeviceLinkDeps,
+DeviceLinkAction->getType()));
 ++I;
   }
+  DeviceLinkerInputs.clear();
+
+  // Create a host object from all the device images by embedding them
+  // in a fat binary.
+  OffloadAction::DeviceDependences DDeps;
+  auto *TopDeviceLinkAction =
+  C.MakeAction(AL, types::TY_Object);
+  DDeps.add(*TopDeviceLinkAction, *ToolChains[0],
+  nullptr, AssociatedOffloadKind);
+
+  // Offload the host object to the host linker.
+  AL.push_back(C.MakeAction(DDeps, 
TopDeviceLinkAction->getType()));
 }
+
+Action* appendLinkHostActions(ActionList ) override { return AL.back(); 
}
+
+void appendLinkDependences(OffloadAction::DeviceDependences ) override 
{}
   };
 
   /// OpenMP action builder. The host bitcode is passed to the device frontend
@@ -2934,7 +2965,7 @@ class OffloadingActionBuilder final {
   OpenMPDeviceActions.clear();
 }
 
-void appendLinkActions(ActionList ) override {
+void appendLinkDeviceActions(ActionList ) override {
   assert(ToolChains.size() == DeviceLinkerInputs.size() &&
  "Toolchains and linker inputs sizes do not match.");
 
@@ -2953,6 +2984,14 @@ class OffloadingActionBuilder final {
   DeviceLinkerInputs.clear();
 }
 
+Action* appendLinkHostActions(ActionList ) override {
+  // Create wrapper bitcode from the result of device

[clang] 4bafb0a - Add Statically Linked Libraries

2020-06-22 Thread Aaron En Ye Shi via cfe-commits 

Author: Aaron En Ye Shi
Date: 2020-06-22T19:48:49Z
New Revision: 4bafb0adcf38cf268208ea58eb7e11402d5632e2

URL: 
https://github.com/llvm/llvm-project/commit/4bafb0adcf38cf268208ea58eb7e11402d5632e2
DIFF: 
https://github.com/llvm/llvm-project/commit/4bafb0adcf38cf268208ea58eb7e11402d5632e2.diff

LOG: Add Statically Linked Libraries

Add GNU Static Lib Tool, which supports the --emit-static-lib
flag. For HIP, a static library archive will be created and
consist of HIP Fat Binary host object with the device images embedded.
Using llvm-ar to create the static archive. Also, delete existing
output file to ensure a new archive is created each time.

Reviewers: yaxunl, tra, rjmccall, echristo

Subscribers: echristo, JonChesterfield, scchan, msearles

Differential Revision: https://reviews.llvm.org/D78759

Added: 
clang/test/Driver/hip-link-static-library.hip
clang/test/Driver/hip-toolchain-rdc-static-lib.hip

Modified: 
clang/include/clang/Driver/Action.h
clang/include/clang/Driver/Driver.h
clang/include/clang/Driver/Options.td
clang/include/clang/Driver/ToolChain.h
clang/lib/Driver/Action.cpp
clang/lib/Driver/Driver.cpp
clang/lib/Driver/ToolChain.cpp
clang/lib/Driver/ToolChains/Gnu.cpp
clang/lib/Driver/ToolChains/Gnu.h
clang/lib/Driver/ToolChains/Linux.cpp
clang/lib/Driver/ToolChains/Linux.h
clang/test/Driver/bindings.c
clang/test/Driver/hip-link-save-temps.hip

Removed: 




diff  --git a/clang/include/clang/Driver/Action.h 
b/clang/include/clang/Driver/Action.h
index 8ccbb6c2bbfa..27c95c6f89d4 100644
--- a/clang/include/clang/Driver/Action.h
+++ b/clang/include/clang/Driver/Action.h
@@ -73,9 +73,10 @@ class Action {
 OffloadBundlingJobClass,
 OffloadUnbundlingJobClass,
 OffloadWrapperJobClass,
+StaticLibJobClass,
 
 JobClassFirst = PreprocessJobClass,
-JobClassLast = OffloadWrapperJobClass
+JobClassLast = StaticLibJobClass
   };
 
   // The offloading kind determines if this action is binded to a particular
@@ -637,6 +638,17 @@ class OffloadWrapperJobAction : public JobAction {
   }
 };
 
+class StaticLibJobAction : public JobAction {
+  void anchor() override;
+
+public:
+  StaticLibJobAction(ActionList , types::ID Type);
+
+  static bool classof(const Action *A) {
+return A->getKind() == StaticLibJobClass;
+  }
+};
+
 } // namespace driver
 } // namespace clang
 

diff  --git a/clang/include/clang/Driver/Driver.h 
b/clang/include/clang/Driver/Driver.h
index 90a0c871140a..b024d6a0d3a3 100644
--- a/clang/include/clang/Driver/Driver.h
+++ b/clang/include/clang/Driver/Driver.h
@@ -548,6 +548,9 @@ class Driver {
   /// handle this action.
   bool ShouldUseFlangCompiler(const JobAction ) const;
 
+  /// ShouldEmitStaticLibrary - Should the linker emit a static library.
+  bool ShouldEmitStaticLibrary(const llvm::opt::ArgList ) const;
+
   /// Returns true if we are performing any kind of LTO.
   bool isUsingLTO() const { return LTOMode != LTOK_None; }
 

diff  --git a/clang/include/clang/Driver/Options.td 
b/clang/include/clang/Driver/Options.td
index 8ad582c84c60..c6474c1e5ccd 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -605,6 +605,8 @@ def hip_link : Flag<["--"], "hip-link">,
 def no_offload_arch_EQ : Joined<["--"], "no-offload-arch=">, 
Flags<[DriverOption]>,
   HelpText<"Remove CUDA/HIP offloading device architecture (e.g. sm_35, 
gfx906) from the list of devices to compile for. "
"'all' resets the list to its default value.">;
+def emit_static_lib : Flag<["--"], "emit-static-lib">,
+  HelpText<"Enable linker job to emit a static library.">;
 def no_cuda_gpu_arch_EQ : Joined<["--"], "no-cuda-gpu-arch=">, 
Flags<[DriverOption]>,
   Alias;
 def cuda_noopt_device_debug : Flag<["--"], "cuda-noopt-device-debug">,

diff  --git a/clang/include/clang/Driver/ToolChain.h 
b/clang/include/clang/Driver/ToolChain.h
index f33ed991f493..7495e08fe6e6 100644
--- a/clang/include/clang/Driver/ToolChain.h
+++ b/clang/include/clang/Driver/ToolChain.h
@@ -139,6 +139,7 @@ class ToolChain {
   mutable std::unique_ptr Flang;
   mutable std::unique_ptr Assemble;
   mutable std::unique_ptr Link;
+  mutable std::unique_ptr StaticLibTool;
   mutable std::unique_ptr IfsMerge;
   mutable std::unique_ptr OffloadBundler;
   mutable std::unique_ptr OffloadWrapper;
@@ -147,6 +148,7 @@ class ToolChain {
   Tool *getFlang() const;
   Tool *getAssemble() const;
   Tool *getLink() const;
+  Tool *getStaticLibTool() const;
   Tool *getIfsMerge() const;
   Tool *getClangAs() const;
   Tool *getOffloadBundler() const;
@@ -174,6 +176,7 @@ class ToolChain {
 
   virtual Tool *buildAssembler() const;
   virtual Tool *buildLinker() const;
+  virtual Tool *buildStaticLibTool() const;
   virtual Tool *getTool(Action::ActionClass AC) const;
 
   /// \name Utilities for implementing subclasses.
@@ -326,6 +329,9 @@ class

[PATCH] D23573: [OpenCL] Add extension cl_khr_subgroups to clang

2016-08-16 Thread Aaron En Ye Shi via cfe-commits 
ashi1 created this revision.
ashi1 added reviewers: yaxunl, Anastasia.
ashi1 added a subscriber: cfe-commits.
ashi1 set the repository for this revision to rL LLVM.

Adding extension cl_khr_subgroups to clang's OpenCL Extensions and initiated 
inside AMDGPU Target. Similar to https://reviews.llvm.org/D22637 

Repository:
  rL LLVM

https://reviews.llvm.org/D23573

Files:
  lib/Basic/Targets.cpp
  test/Misc/amdgcn.languageOptsOpenCL.cl
  test/SemaOpenCL/extension-version.cl

Index: test/SemaOpenCL/extension-version.cl
===
--- test/SemaOpenCL/extension-version.cl
+++ test/SemaOpenCL/extension-version.cl
@@ -247,6 +247,9 @@
 #error "Missing cl_khr_subgroups define"
 #endif
 #else
+#ifdef cl_khr_subgroups
+#error "Incorrect cl_khr_subgroups define"
+#endif
 // expected-warning@+2{{unsupported OpenCL extension 'cl_khr_subgroups' - 
ignoring}}
 #endif
 #pragma OPENCL EXTENSION cl_khr_subgroups: enable
Index: test/Misc/amdgcn.languageOptsOpenCL.cl
===
--- test/Misc/amdgcn.languageOptsOpenCL.cl
+++ test/Misc/amdgcn.languageOptsOpenCL.cl
@@ -199,11 +199,17 @@
 #pragma OPENCL EXTENSION cl_khr_srgb_image_writes: enable
 // expected-warning@-1{{unsupported OpenCL extension 
'cl_khr_srgb_image_writes' - ignoring}}
 
+#if (__OPENCL_C_VERSION__ >= 200)
+#ifndef cl_khr_subgroups
+#error "Missing cl_khr_subgroups define"
+#endif
+#else
 #ifdef cl_khr_subgroups
 #error "Incorrect cl_khr_subgroups define"
 #endif
+// expected-warning@+2{{unsupported OpenCL extension 'cl_khr_subgroups' - 
ignoring}}
+#endif
 #pragma OPENCL EXTENSION cl_khr_subgroups: enable
-// expected-warning@-1{{unsupported OpenCL extension 'cl_khr_subgroups' - 
ignoring}}
 
 #ifdef cl_khr_terminate_context
 #error "Incorrect cl_khr_terminate_context define"
Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2127,6 +2127,7 @@
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
   Opts.cl_khr_mipmap_image = 1;
+  Opts.cl_khr_subgroups = 1;
   Opts.cl_khr_3d_image_writes = 1;
 }
   }


Index: test/SemaOpenCL/extension-version.cl
===
--- test/SemaOpenCL/extension-version.cl
+++ test/SemaOpenCL/extension-version.cl
@@ -247,6 +247,9 @@
 #error "Missing cl_khr_subgroups define"
 #endif
 #else
+#ifdef cl_khr_subgroups
+#error "Incorrect cl_khr_subgroups define"
+#endif
 // expected-warning@+2{{unsupported OpenCL extension 'cl_khr_subgroups' - ignoring}}
 #endif
 #pragma OPENCL EXTENSION cl_khr_subgroups: enable
Index: test/Misc/amdgcn.languageOptsOpenCL.cl
===
--- test/Misc/amdgcn.languageOptsOpenCL.cl
+++ test/Misc/amdgcn.languageOptsOpenCL.cl
@@ -199,11 +199,17 @@
 #pragma OPENCL EXTENSION cl_khr_srgb_image_writes: enable
 // expected-warning@-1{{unsupported OpenCL extension 'cl_khr_srgb_image_writes' - ignoring}}
 
+#if (__OPENCL_C_VERSION__ >= 200)
+#ifndef cl_khr_subgroups
+#error "Missing cl_khr_subgroups define"
+#endif
+#else
 #ifdef cl_khr_subgroups
 #error "Incorrect cl_khr_subgroups define"
 #endif
+// expected-warning@+2{{unsupported OpenCL extension 'cl_khr_subgroups' - ignoring}}
+#endif
 #pragma OPENCL EXTENSION cl_khr_subgroups: enable
-// expected-warning@-1{{unsupported OpenCL extension 'cl_khr_subgroups' - ignoring}}
 
 #ifdef cl_khr_terminate_context
 #error "Incorrect cl_khr_terminate_context define"
Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2127,6 +2127,7 @@
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
   Opts.cl_khr_mipmap_image = 1;
+  Opts.cl_khr_subgroups = 1;
   Opts.cl_khr_3d_image_writes = 1;
 }
   }
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D23086: [OpenCL] Generate concrete struct type for ndrange_t

2016-08-02 Thread Aaron En Ye Shi via cfe-commits 
ashi1 created this revision.
ashi1 added reviewers: bader, Anastasia, yaxunl.
ashi1 added a subscriber: cfe-commits.
ashi1 set the repository for this revision to rL LLVM.

ndrange_t needs to be emitted as a struct type since it has to be allocated on 
a stack as a local variable or function return.

Repository:
  rL LLVM

https://reviews.llvm.org/D23086

Files:
  lib/CodeGen/CGOpenCLRuntime.cpp
  test/CodeGenOpenCL/cl20-device-side-enqueue.cl

Index: test/CodeGenOpenCL/cl20-device-side-enqueue.cl
===
--- test/CodeGenOpenCL/cl20-device-side-enqueue.cl
+++ test/CodeGenOpenCL/cl20-device-side-enqueue.cl
@@ -9,7 +9,7 @@
   queue_t default_queue;
   // CHECK: %flags = alloca i32
   unsigned flags = 0;
-  // CHECK: %ndrange = alloca %opencl.ndrange_t*
+  // CHECK: %ndrange = alloca %ndrange_t
   ndrange_t ndrange;
   // CHECK: %clk_event = alloca %opencl.clk_event_t*
   clk_event_t clk_event;
@@ -20,10 +20,10 @@
 
   // CHECK: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t*, %opencl.queue_t** %default_queue
   // CHECK: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
-  // CHECK: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
+  // CHECK: [[NDR:%[0-9]+]] = load %ndrange_t, %ndrange_t* %ndrange
   // CHECK: [[BL:%[0-9]+]] = bitcast <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block to void ()*
   // CHECK: [[BL_I8:%[0-9]+]] = bitcast void ()* [[BL]] to i8*
-  // CHECK: call i32 @__enqueue_kernel_basic(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* [[BL_I8]])
+  // CHECK: call i32 @__enqueue_kernel_basic(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %ndrange_t [[NDR]], i8* [[BL_I8]])
   enqueue_kernel(default_queue, flags, ndrange,
  ^(void) {
a[i] = b[i];
@@ -31,10 +31,10 @@
 
   // CHECK: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t*, %opencl.queue_t** %default_queue
   // CHECK: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
-  // CHECK: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
+  // CHECK: [[NDR:%[0-9]+]] = load %ndrange_t, %ndrange_t* %ndrange
   // CHECK: [[BL:%[0-9]+]] = bitcast <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32{{.*}}, i32{{.*}}, i32{{.*}} }>* %block3 to void ()*
   // CHECK: [[BL_I8:%[0-9]+]] = bitcast void ()* [[BL]] to i8*
-  // CHECK: call i32 @__enqueue_kernel_basic_events(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i32 2, %opencl.clk_event_t** %event_wait_list, %opencl.clk_event_t** %clk_event, i8* [[BL_I8]])
+  // CHECK: call i32 @__enqueue_kernel_basic_events(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %ndrange_t [[NDR]], i32 2, %opencl.clk_event_t** %event_wait_list, %opencl.clk_event_t** %clk_event, i8* [[BL_I8]])
   enqueue_kernel(default_queue, flags, ndrange, 2, _wait_list, _event,
  ^(void) {
a[i] = b[i];
@@ -42,8 +42,8 @@
 
   // CHECK: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t*, %opencl.queue_t** %default_queue
   // CHECK: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
-  // CHECK: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
-  // CHECK: call i32 (%opencl.queue_t*, i32, %opencl.ndrange_t*, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 256)
+  // CHECK: [[NDR:%[0-9]+]] = load %ndrange_t, %ndrange_t* %ndrange
+  // CHECK: call i32 (%opencl.queue_t*, i32, %ndrange_t, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %ndrange_t [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 256)
   enqueue_kernel(default_queue, flags, ndrange,
  ^(local void *p) {
return;
@@ -52,9 +52,9 @@
   char c;
   // CHECK: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t*, %opencl.queue_t** %default_queue
   // CHECK: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
-  // CHECK: [[NDR:%[0-9]+]] = load %opencl.ndrange_t*, %opencl.ndrange_t** %ndrange
+  // CHECK: [[NDR:%[0-9]+]] = load %ndrange_t, %ndrange_t* %ndrange
   // CHECK: [[SIZE:%[0-9]+]] = zext i8 {{%[0-9]+}} to i32
-  // CHECK: call i32 (%opencl.queue_t*, i32, %opencl.ndrange_t*, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %opencl.ndrange_t* [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 [[SIZE]])
+  // CHECK: call i32 (%opencl.queue_t*, i32, %ndrange_t, i8*, i32, ...) @__enqueue_kernel_vaargs(%opencl.queue_t* [[DEF_Q]], i32 [[FLAGS]], %ndrange_t [[NDR]], i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global{{(.[0-9]+)?}} to i8*), i32 1, i32 [[SIZE]])

[PATCH] D23071: [OpenCL] Remove extra native_ functions from opencl-c.h

2016-08-02 Thread Aaron En Ye Shi via cfe-commits 
ashi1 created this revision.
ashi1 added reviewers: Anastasia, yaxunl, nhaustov.
ashi1 added a subscriber: cfe-commits.
ashi1 set the repository for this revision to rL LLVM.

There should be no native_ builtin functions with double type arguments.

Repository:
  rL LLVM

https://reviews.llvm.org/D23071

Files:
  lib/Headers/opencl-c.h

Index: lib/Headers/opencl-c.h
===
--- lib/Headers/opencl-c.h
+++ lib/Headers/opencl-c.h
@@ -9810,14 +9810,6 @@
 float4 __ovld __cnfn native_cos(float4 x);
 float8 __ovld __cnfn native_cos(float8 x);
 float16 __ovld __cnfn native_cos(float16 x);
-#ifdef cl_khr_fp64
-double __ovld __cnfn native_cos(double x);
-double2 __ovld __cnfn native_cos(double2 x);
-double3 __ovld __cnfn native_cos(double3 x);
-double4 __ovld __cnfn native_cos(double4 x);
-double8 __ovld __cnfn native_cos(double8 x);
-double16 __ovld __cnfn native_cos(double16 x);
-#endif //cl_khr_fp64
 
 /**
  * Compute x / y over an implementation-defined range.
@@ -9829,14 +9821,6 @@
 float4 __ovld __cnfn native_divide(float4 x, float4 y);
 float8 __ovld __cnfn native_divide(float8 x, float8 y);
 float16 __ovld __cnfn native_divide(float16 x, float16 y);
-#ifdef cl_khr_fp64
-double __ovld __cnfn native_divide(double x, double y);
-double2 __ovld __cnfn native_divide(double2 x, double2 y);
-double3 __ovld __cnfn native_divide(double3 x, double3 y);
-double4 __ovld __cnfn native_divide(double4 x, double4 y);
-double8 __ovld __cnfn native_divide(double8 x, double8 y);
-double16 __ovld __cnfn native_divide(double16 x, double16 y);
-#endif //cl_khr_fp64
 
 /**
  * Compute the base- e exponential of x over an
@@ -9849,14 +9833,6 @@
 float4 __ovld __cnfn native_exp(float4 x);
 float8 __ovld __cnfn native_exp(float8 x);
 float16 __ovld __cnfn native_exp(float16 x);
-#ifdef cl_khr_fp64
-double __ovld __cnfn native_exp(double x);
-double2 __ovld __cnfn native_exp(double2 x);
-double3 __ovld __cnfn native_exp(double3 x);
-double4 __ovld __cnfn native_exp(double4 x);
-double8 __ovld __cnfn native_exp(double8 x);
-double16 __ovld __cnfn native_exp(double16 x);
-#endif //cl_khr_fp64
 
 /**
  * Compute the base- 2 exponential of x over an
@@ -9869,14 +9845,6 @@
 float4 __ovld __cnfn native_exp2(float4 x);
 float8 __ovld __cnfn native_exp2(float8 x);
 float16 __ovld __cnfn native_exp2(float16 x);
-#ifdef cl_khr_fp64
-double __ovld __cnfn native_exp2(double x);
-double2 __ovld __cnfn native_exp2(double2 x);
-double3 __ovld __cnfn native_exp2(double3 x);
-double4 __ovld __cnfn native_exp2(double4 x);
-double8 __ovld __cnfn native_exp2(double8 x);
-double16 __ovld __cnfn native_exp2(double16 x);
-#endif //cl_khr_fp64
 
 /**
  * Compute the base- 10 exponential of x over an
@@ -9889,14 +9857,6 @@
 float4 __ovld __cnfn native_exp10(float4 x);
 float8 __ovld __cnfn native_exp10(float8 x);
 float16 __ovld __cnfn native_exp10(float16 x);
-#ifdef cl_khr_fp64
-double __ovld __cnfn native_exp10(double x);
-double2 __ovld __cnfn native_exp10(double2 x);
-double3 __ovld __cnfn native_exp10(double3 x);
-double4 __ovld __cnfn native_exp10(double4 x);
-double8 __ovld __cnfn native_exp10(double8 x);
-double16 __ovld __cnfn native_exp10(double16 x);
-#endif //cl_khr_fp64
 
 /**
  * Compute natural logarithm over an implementationdefined
@@ -9909,14 +9869,6 @@
 float4 __ovld __cnfn native_log(float4 x);
 float8 __ovld __cnfn native_log(float8 x);
 float16 __ovld __cnfn native_log(float16 x);
-#ifdef cl_khr_fp64
-double __ovld __cnfn native_log(double x);
-double2 __ovld __cnfn native_log(double2 x);
-double3 __ovld __cnfn native_log(double3 x);
-double4 __ovld __cnfn native_log(double4 x);
-double8 __ovld __cnfn native_log(double8 x);
-double16 __ovld __cnfn native_log(double16 x);
-#endif //cl_khr_fp64
 
 /**
  * Compute a base 2 logarithm over an implementationdefined
@@ -9928,14 +9880,6 @@
 float4 __ovld __cnfn native_log2(float4 x);
 float8 __ovld __cnfn native_log2(float8 x);
 float16 __ovld __cnfn native_log2(float16 x);
-#ifdef cl_khr_fp64
-double __ovld __cnfn native_log2(double x);
-double2 __ovld __cnfn native_log2(double2 x);
-double3 __ovld __cnfn native_log2(double3 x);
-double4 __ovld __cnfn native_log2(double4 x);
-double8 __ovld __cnfn native_log2(double8 x);
-double16 __ovld __cnfn native_log2(double16 x);
-#endif //cl_khr_fp64
 
 /**
  * Compute a base 10 logarithm over an implementationdefined
@@ -9947,14 +9891,6 @@
 float4 __ovld __cnfn native_log10(float4 x);
 float8 __ovld __cnfn native_log10(float8 x);
 float16 __ovld __cnfn native_log10(float16 x);
-#ifdef cl_khr_fp64
-double __ovld __cnfn native_log10(double x);
-double2 __ovld __cnfn native_log10(double2 x);
-double3 __ovld __cnfn native_log10(double3 x);
-double4 __ovld __cnfn native_log10(double4 x);
-double8 __ovld __cnfn native_log10(double8 x);
-double16 __ovld __cnfn native_log10(double16 x);
-#endif //cl_khr_fp64
 
 /**
  * Compute x to the power y, where x is >= 0. The range of
@@ -9967,14 +9903,6 @@

Re: [PATCH] D22637: [OpenCL] Add extension cl_khr_mipmap_image to clang

2016-07-27 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 65773.
ashi1 marked an inline comment as done.
ashi1 added a comment.

Removed indentation as per Anastasia's comments.


Repository:
  rL LLVM

https://reviews.llvm.org/D22637

Files:
  include/clang/Basic/OpenCLExtensions.def
  lib/Basic/Targets.cpp
  test/Misc/amdgcn.languageOptsOpenCL.cl
  test/SemaOpenCL/extension-version.cl

Index: test/SemaOpenCL/extension-version.cl
===
--- test/SemaOpenCL/extension-version.cl
+++ test/SemaOpenCL/extension-version.cl
@@ -222,6 +222,18 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 
 #if (__OPENCL_C_VERSION__ >= 200)
+#ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+#endif
+#else
+#ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+#endif
+// expected-warning@+2{{unsupported OpenCL extension 'cl_khr_mipmap_image' - 
ignoring}}
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
+#if (__OPENCL_C_VERSION__ >= 200)
 #ifndef cl_khr_srgb_image_writes
 #error "Missing cl_khr_srgb_image_writes define"
 #endif
Index: test/Misc/amdgcn.languageOptsOpenCL.cl
===
--- test/Misc/amdgcn.languageOptsOpenCL.cl
+++ test/Misc/amdgcn.languageOptsOpenCL.cl
@@ -181,6 +181,18 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 // expected-warning@-1{{unsupported OpenCL extension 'cl_khr_egl_image' - 
ignoring}}
 
+#if (__OPENCL_C_VERSION__ >= 200)
+#ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+#endif
+#else
+#ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+#endif
+// expected-warning@+2{{unsupported OpenCL extension 'cl_khr_mipmap_image' - 
ignoring}}
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
 #ifdef cl_khr_srgb_image_writes
 #error "Incorrect cl_khr_srgb_image_writes define"
 #endif
Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2115,6 +2115,7 @@
   Opts.cl_khr_fp16 = 1;
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
+  Opts.cl_khr_mipmap_image = 1;
   Opts.cl_khr_3d_image_writes = 1;
 }
   }
Index: include/clang/Basic/OpenCLExtensions.def
===
--- include/clang/Basic/OpenCLExtensions.def
+++ include/clang/Basic/OpenCLExtensions.def
@@ -67,6 +67,7 @@
 // OpenCL 2.0.
 OPENCLEXT_INTERNAL(cl_khr_egl_event, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_egl_image, 200, ~0U)
+OPENCLEXT_INTERNAL(cl_khr_mipmap_image, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_srgb_image_writes, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_subgroups, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_terminate_context, 200, ~0U)


Index: test/SemaOpenCL/extension-version.cl
===
--- test/SemaOpenCL/extension-version.cl
+++ test/SemaOpenCL/extension-version.cl
@@ -222,6 +222,18 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 
 #if (__OPENCL_C_VERSION__ >= 200)
+#ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+#endif
+#else
+#ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+#endif
+// expected-warning@+2{{unsupported OpenCL extension 'cl_khr_mipmap_image' - ignoring}}
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
+#if (__OPENCL_C_VERSION__ >= 200)
 #ifndef cl_khr_srgb_image_writes
 #error "Missing cl_khr_srgb_image_writes define"
 #endif
Index: test/Misc/amdgcn.languageOptsOpenCL.cl
===
--- test/Misc/amdgcn.languageOptsOpenCL.cl
+++ test/Misc/amdgcn.languageOptsOpenCL.cl
@@ -181,6 +181,18 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 // expected-warning@-1{{unsupported OpenCL extension 'cl_khr_egl_image' - ignoring}}
 
+#if (__OPENCL_C_VERSION__ >= 200)
+#ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+#endif
+#else
+#ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+#endif
+// expected-warning@+2{{unsupported OpenCL extension 'cl_khr_mipmap_image' - ignoring}}
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
 #ifdef cl_khr_srgb_image_writes
 #error "Incorrect cl_khr_srgb_image_writes define"
 #endif
Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2115,6 +2115,7 @@
   Opts.cl_khr_fp16 = 1;
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
+  Opts.cl_khr_mipmap_image = 1;
   Opts.cl_khr_3d_image_writes = 1;
 }
   }
Index: include/clang/Basic/OpenCLExtensions.def
===
--- include/clang/Basic/OpenCLExtensions.def
+++

Re: [PATCH] D22637: [OpenCL] Add extension cl_khr_mipmap_image to clang

2016-07-26 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 65582.
ashi1 added a comment.

Revised based on Anastasia's comments. Restructured the if statements in test 
cases.


Repository:
  rL LLVM

https://reviews.llvm.org/D22637

Files:
  include/clang/Basic/OpenCLExtensions.def
  lib/Basic/Targets.cpp
  test/Misc/amdgcn.languageOptsOpenCL.cl
  test/SemaOpenCL/extension-version.cl

Index: test/SemaOpenCL/extension-version.cl
===
--- test/SemaOpenCL/extension-version.cl
+++ test/SemaOpenCL/extension-version.cl
@@ -222,6 +222,18 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 
 #if (__OPENCL_C_VERSION__ >= 200)
+  #ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+  #endif
+#else
+  #ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+  #endif
+  // expected-warning@+2{{unsupported OpenCL extension 'cl_khr_mipmap_image' - 
ignoring}}
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
+#if (__OPENCL_C_VERSION__ >= 200)
 #ifndef cl_khr_srgb_image_writes
 #error "Missing cl_khr_srgb_image_writes define"
 #endif
Index: test/Misc/amdgcn.languageOptsOpenCL.cl
===
--- test/Misc/amdgcn.languageOptsOpenCL.cl
+++ test/Misc/amdgcn.languageOptsOpenCL.cl
@@ -181,6 +181,18 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 // expected-warning@-1{{unsupported OpenCL extension 'cl_khr_egl_image' - 
ignoring}}
 
+#if (__OPENCL_C_VERSION__ >= 200)
+  #ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+  #endif
+#else
+  #ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+  #endif
+  // expected-warning@+2{{unsupported OpenCL extension 'cl_khr_mipmap_image' - 
ignoring}}
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
 #ifdef cl_khr_srgb_image_writes
 #error "Incorrect cl_khr_srgb_image_writes define"
 #endif
Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2115,6 +2115,7 @@
   Opts.cl_khr_fp16 = 1;
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
+  Opts.cl_khr_mipmap_image = 1;
   Opts.cl_khr_3d_image_writes = 1;
 }
   }
Index: include/clang/Basic/OpenCLExtensions.def
===
--- include/clang/Basic/OpenCLExtensions.def
+++ include/clang/Basic/OpenCLExtensions.def
@@ -67,6 +67,7 @@
 // OpenCL 2.0.
 OPENCLEXT_INTERNAL(cl_khr_egl_event, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_egl_image, 200, ~0U)
+OPENCLEXT_INTERNAL(cl_khr_mipmap_image, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_srgb_image_writes, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_subgroups, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_terminate_context, 200, ~0U)


Index: test/SemaOpenCL/extension-version.cl
===
--- test/SemaOpenCL/extension-version.cl
+++ test/SemaOpenCL/extension-version.cl
@@ -222,6 +222,18 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 
 #if (__OPENCL_C_VERSION__ >= 200)
+  #ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+  #endif
+#else
+  #ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+  #endif
+  // expected-warning@+2{{unsupported OpenCL extension 'cl_khr_mipmap_image' - ignoring}}
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
+#if (__OPENCL_C_VERSION__ >= 200)
 #ifndef cl_khr_srgb_image_writes
 #error "Missing cl_khr_srgb_image_writes define"
 #endif
Index: test/Misc/amdgcn.languageOptsOpenCL.cl
===
--- test/Misc/amdgcn.languageOptsOpenCL.cl
+++ test/Misc/amdgcn.languageOptsOpenCL.cl
@@ -181,6 +181,18 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 // expected-warning@-1{{unsupported OpenCL extension 'cl_khr_egl_image' - ignoring}}
 
+#if (__OPENCL_C_VERSION__ >= 200)
+  #ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+  #endif
+#else
+  #ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+  #endif
+  // expected-warning@+2{{unsupported OpenCL extension 'cl_khr_mipmap_image' - ignoring}}
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
 #ifdef cl_khr_srgb_image_writes
 #error "Incorrect cl_khr_srgb_image_writes define"
 #endif
Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2115,6 +2115,7 @@
   Opts.cl_khr_fp16 = 1;
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
+  Opts.cl_khr_mipmap_image = 1;
   Opts.cl_khr_3d_image_writes = 1;
 }
   }
Index: include/clang/Basic/OpenCLExtensions.def

Re: [PATCH] D22637: [OpenCL] Add extension cl_khr_mipmap_image to clang

2016-07-25 Thread Aaron En Ye Shi via cfe-commits 
ashi1 added inline comments.


Comment at: test/Misc/amdgcn.languageOptsOpenCL.cl:188
@@ +187,3 @@
+#endif
+// expected-warning@+6{{unsupported OpenCL extension 'cl_khr_mipmap_image' - 
ignoring}}
+#else

yaxunl wrote:
> Anastasia wrote:
> > Can you move this error message down instead of adding 6 lines offset.
> > Also the extension seems to be set by default although it's hard to see 
> > without the full diff. So why do you get this warning at all?
> This warning is only for opencl version < 200. The extension is supported by 
> OpenCL 2.0 and above only.
I've added this error message here because I am following the order inside 
include/clang/Basic/OpenCLExtensions.def. Seems it is alphabetical there and in 
same order here. What do you think?


Comment at: test/SemaOpenCL/extension-version.cl:228
@@ +227,3 @@
+#endif
+// expected-warning@+6{{unsupported OpenCL extension 'cl_khr_mipmap_image' - 
ignoring}}
+#else

Anastasia wrote:
> Can you move this error message down instead of adding 6 lines offset.
I've added this error message here because I am following the order inside 
include/clang/Basic/OpenCLExtensions.def. Seems it is alphabetical there and in 
same order here. What do you think?


Repository:
  rL LLVM

https://reviews.llvm.org/D22637



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D22767: [OpenCL] Added CLK_ABGR definition for get_image_channel_order return value

2016-07-25 Thread Aaron En Ye Shi via cfe-commits 
ashi1 created this revision.
ashi1 added reviewers: yaxunl, Anastasia.
ashi1 added a subscriber: cfe-commits.
ashi1 set the repository for this revision to rL LLVM.

Added CLK_ABGR definition for get_image_channel_order return value inside 
opencl-c.h file

Repository:
  rL LLVM

https://reviews.llvm.org/D22767

Files:
  lib/Headers/opencl-c.h

Index: lib/Headers/opencl-c.h
===
--- lib/Headers/opencl-c.h
+++ lib/Headers/opencl-c.h
@@ -16493,6 +16493,7 @@
 #define CLK_sRGBA 0x10C1
 #define CLK_sRGBx 0x10C0
 #define CLK_sBGRA 0x10C2
+#define CLK_ABGR  0x10C3
 #endif //__OPENCL_C_VERSION__ >= CL_VERSION_2_0
 
 int __ovld __cnfn get_image_channel_order(read_only image1d_t image);


Index: lib/Headers/opencl-c.h
===
--- lib/Headers/opencl-c.h
+++ lib/Headers/opencl-c.h
@@ -16493,6 +16493,7 @@
 #define CLK_sRGBA 0x10C1
 #define CLK_sRGBx 0x10C0
 #define CLK_sBGRA 0x10C2
+#define CLK_ABGR  0x10C3
 #endif //__OPENCL_C_VERSION__ >= CL_VERSION_2_0
 
 int __ovld __cnfn get_image_channel_order(read_only image1d_t image);
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Re: [PATCH] D22637: [OpenCL] Add extension cl_khr_mipmap_image to clang

2016-07-22 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 65126.
ashi1 marked an inline comment as done.
ashi1 added a comment.

Revised based on Sam's comments.


Repository:
  rL LLVM

https://reviews.llvm.org/D22637

Files:
  include/clang/Basic/OpenCLExtensions.def
  lib/Basic/Targets.cpp
  test/Misc/amdgcn.languageOptsOpenCL.cl
  test/SemaOpenCL/extension-version.cl

Index: test/SemaOpenCL/extension-version.cl
===
--- test/SemaOpenCL/extension-version.cl
+++ test/SemaOpenCL/extension-version.cl
@@ -221,6 +221,18 @@
 #endif
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 
+#if (__OPENCL_C_VERSION__ < 200)
+#ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+#endif
+// expected-warning@+6{{unsupported OpenCL extension 'cl_khr_mipmap_image' - 
ignoring}}
+#else
+#ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+#endif
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
 #if (__OPENCL_C_VERSION__ >= 200)
 #ifndef cl_khr_srgb_image_writes
 #error "Missing cl_khr_srgb_image_writes define"
Index: test/Misc/amdgcn.languageOptsOpenCL.cl
===
--- test/Misc/amdgcn.languageOptsOpenCL.cl
+++ test/Misc/amdgcn.languageOptsOpenCL.cl
@@ -181,6 +181,18 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 // expected-warning@-1{{unsupported OpenCL extension 'cl_khr_egl_image' - 
ignoring}}
 
+#if (__OPENCL_C_VERSION__ < 200)
+#ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+#endif
+// expected-warning@+6{{unsupported OpenCL extension 'cl_khr_mipmap_image' - 
ignoring}}
+#else
+#ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+#endif
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
 #ifdef cl_khr_srgb_image_writes
 #error "Incorrect cl_khr_srgb_image_writes define"
 #endif
Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2115,6 +2115,7 @@
   Opts.cl_khr_fp16 = 1;
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
+  Opts.cl_khr_mipmap_image = 1;
   Opts.cl_khr_3d_image_writes = 1;
 }
   }
Index: include/clang/Basic/OpenCLExtensions.def
===
--- include/clang/Basic/OpenCLExtensions.def
+++ include/clang/Basic/OpenCLExtensions.def
@@ -67,6 +67,7 @@
 // OpenCL 2.0.
 OPENCLEXT_INTERNAL(cl_khr_egl_event, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_egl_image, 200, ~0U)
+OPENCLEXT_INTERNAL(cl_khr_mipmap_image, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_srgb_image_writes, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_subgroups, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_terminate_context, 200, ~0U)


Index: test/SemaOpenCL/extension-version.cl
===
--- test/SemaOpenCL/extension-version.cl
+++ test/SemaOpenCL/extension-version.cl
@@ -221,6 +221,18 @@
 #endif
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 
+#if (__OPENCL_C_VERSION__ < 200)
+#ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+#endif
+// expected-warning@+6{{unsupported OpenCL extension 'cl_khr_mipmap_image' - ignoring}}
+#else
+#ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+#endif
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
 #if (__OPENCL_C_VERSION__ >= 200)
 #ifndef cl_khr_srgb_image_writes
 #error "Missing cl_khr_srgb_image_writes define"
Index: test/Misc/amdgcn.languageOptsOpenCL.cl
===
--- test/Misc/amdgcn.languageOptsOpenCL.cl
+++ test/Misc/amdgcn.languageOptsOpenCL.cl
@@ -181,6 +181,18 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 // expected-warning@-1{{unsupported OpenCL extension 'cl_khr_egl_image' - ignoring}}
 
+#if (__OPENCL_C_VERSION__ < 200)
+#ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+#endif
+// expected-warning@+6{{unsupported OpenCL extension 'cl_khr_mipmap_image' - ignoring}}
+#else
+#ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+#endif
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
 #ifdef cl_khr_srgb_image_writes
 #error "Incorrect cl_khr_srgb_image_writes define"
 #endif
Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2115,6 +2115,7 @@
   Opts.cl_khr_fp16 = 1;
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
+  Opts.cl_khr_mipmap_image = 1;
   Opts.cl_khr_3d_image_writes = 1;
 }
   }
Index: include/clang/Basic/OpenCLExtensions.def
===
--- include/clang/Basic/OpenCLExtensions.def
+++

Re: [PATCH] D22637: [OpenCL] Add extension cl_khr_mipmap_image to clang

2016-07-22 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 65118.
ashi1 marked an inline comment as done.
ashi1 added a comment.

Revised based on Sam's comments. Added to tests 
Misc\amdgcn.languageOptsOpenCL.cl and SemaOpenCL\extension-version.cl


Repository:
  rL LLVM

https://reviews.llvm.org/D22637

Files:
  include/clang/Basic/OpenCLExtensions.def
  lib/Basic/Targets.cpp
  test/Misc/amdgcn.languageOptsOpenCL.cl
  test/SemaOpenCL/extension-version.cl

Index: test/SemaOpenCL/extension-version.cl
===
--- test/SemaOpenCL/extension-version.cl
+++ test/SemaOpenCL/extension-version.cl
@@ -222,6 +222,15 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 
 #if (__OPENCL_C_VERSION__ >= 200)
+#ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+#endif
+#else
+// expected-warning@+2{{unsupported OpenCL extension 'cl_khr_mipmap_image' - 
ignoring}}
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
+#if (__OPENCL_C_VERSION__ >= 200)
 #ifndef cl_khr_srgb_image_writes
 #error "Missing cl_khr_srgb_image_writes define"
 #endif
Index: test/Misc/amdgcn.languageOptsOpenCL.cl
===
--- test/Misc/amdgcn.languageOptsOpenCL.cl
+++ test/Misc/amdgcn.languageOptsOpenCL.cl
@@ -181,6 +181,14 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 // expected-warning@-1{{unsupported OpenCL extension 'cl_khr_egl_image' - 
ignoring}}
 
+#if (__OPENCL_C_VERSION__ < 200)
+#ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+// expected-warning@-1{{unsupported OpenCL extension 'cl_khr_mipmap_image' - 
ignoring}}
+#endif
+
 #ifdef cl_khr_srgb_image_writes
 #error "Incorrect cl_khr_srgb_image_writes define"
 #endif
Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2115,6 +2115,7 @@
   Opts.cl_khr_fp16 = 1;
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
+  Opts.cl_khr_mipmap_image = 1;
   Opts.cl_khr_3d_image_writes = 1;
 }
   }
Index: include/clang/Basic/OpenCLExtensions.def
===
--- include/clang/Basic/OpenCLExtensions.def
+++ include/clang/Basic/OpenCLExtensions.def
@@ -67,6 +67,7 @@
 // OpenCL 2.0.
 OPENCLEXT_INTERNAL(cl_khr_egl_event, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_egl_image, 200, ~0U)
+OPENCLEXT_INTERNAL(cl_khr_mipmap_image, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_srgb_image_writes, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_subgroups, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_terminate_context, 200, ~0U)


Index: test/SemaOpenCL/extension-version.cl
===
--- test/SemaOpenCL/extension-version.cl
+++ test/SemaOpenCL/extension-version.cl
@@ -222,6 +222,15 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 
 #if (__OPENCL_C_VERSION__ >= 200)
+#ifndef cl_khr_mipmap_image
+#error "Missing cl_khr_mipmap_image define"
+#endif
+#else
+// expected-warning@+2{{unsupported OpenCL extension 'cl_khr_mipmap_image' - ignoring}}
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+
+#if (__OPENCL_C_VERSION__ >= 200)
 #ifndef cl_khr_srgb_image_writes
 #error "Missing cl_khr_srgb_image_writes define"
 #endif
Index: test/Misc/amdgcn.languageOptsOpenCL.cl
===
--- test/Misc/amdgcn.languageOptsOpenCL.cl
+++ test/Misc/amdgcn.languageOptsOpenCL.cl
@@ -181,6 +181,14 @@
 #pragma OPENCL EXTENSION cl_khr_egl_image: enable
 // expected-warning@-1{{unsupported OpenCL extension 'cl_khr_egl_image' - ignoring}}
 
+#if (__OPENCL_C_VERSION__ < 200)
+#ifdef cl_khr_mipmap_image
+#error "Incorrect cl_khr_mipmap_image define"
+#endif
+#pragma OPENCL EXTENSION cl_khr_mipmap_image: enable
+// expected-warning@-1{{unsupported OpenCL extension 'cl_khr_mipmap_image' - ignoring}}
+#endif
+
 #ifdef cl_khr_srgb_image_writes
 #error "Incorrect cl_khr_srgb_image_writes define"
 #endif
Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2115,6 +2115,7 @@
   Opts.cl_khr_fp16 = 1;
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
+  Opts.cl_khr_mipmap_image = 1;
   Opts.cl_khr_3d_image_writes = 1;
 }
   }
Index: include/clang/Basic/OpenCLExtensions.def
===
--- include/clang/Basic/OpenCLExtensions.def
+++ include/clang/Basic/OpenCLExtensions.def
@@ -67,6 +67,7 @@
 // OpenCL 2.0.
 OPENCLEXT_INTERNAL(cl_khr_egl_event, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_egl_image, 200, ~0U)
+OPENCLEXT_INTERNAL(cl_khr_mipmap_image, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_srgb_image_writes, 200, ~0U)

[PATCH] D22637: [OpenCL] Add extension cl_khr_mipmap_image to clang

2016-07-21 Thread Aaron En Ye Shi via cfe-commits 
ashi1 created this revision.
ashi1 added reviewers: yaxunl, Anastasia.
ashi1 added a subscriber: cfe-commits.
ashi1 set the repository for this revision to rL LLVM.

Adding extension cl_khr_mipmap_image to clang's OpenCL Extensions and initiated 
inside AMDGPU Target.

Repository:
  rL LLVM

https://reviews.llvm.org/D22637

Files:
  include/clang/Basic/OpenCLExtensions.def
  lib/Basic/Targets.cpp

Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2116,6 +2116,7 @@
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
   Opts.cl_khr_3d_image_writes = 1;
+  Opts.cl_khr_mipmap_image = 1;
 }
   }
 
Index: include/clang/Basic/OpenCLExtensions.def
===
--- include/clang/Basic/OpenCLExtensions.def
+++ include/clang/Basic/OpenCLExtensions.def
@@ -70,6 +70,7 @@
 OPENCLEXT_INTERNAL(cl_khr_srgb_image_writes, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_subgroups, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_terminate_context, 200, ~0U)
+OPENCLEXT_INTERNAL(cl_khr_mipmap_image, 200, ~0U)
 
 // Clang Extensions.
 OPENCLEXT_INTERNAL(cl_clang_storage_class_specifiers, 100, ~0U)


Index: lib/Basic/Targets.cpp
===
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2116,6 +2116,7 @@
   Opts.cl_khr_int64_base_atomics = 1;
   Opts.cl_khr_int64_extended_atomics = 1;
   Opts.cl_khr_3d_image_writes = 1;
+  Opts.cl_khr_mipmap_image = 1;
 }
   }
 
Index: include/clang/Basic/OpenCLExtensions.def
===
--- include/clang/Basic/OpenCLExtensions.def
+++ include/clang/Basic/OpenCLExtensions.def
@@ -70,6 +70,7 @@
 OPENCLEXT_INTERNAL(cl_khr_srgb_image_writes, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_subgroups, 200, ~0U)
 OPENCLEXT_INTERNAL(cl_khr_terminate_context, 200, ~0U)
+OPENCLEXT_INTERNAL(cl_khr_mipmap_image, 200, ~0U)
 
 // Clang Extensions.
 OPENCLEXT_INTERNAL(cl_clang_storage_class_specifiers, 100, ~0U)
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Re: [PATCH] D22523: [OpenCL] AMDGCN target will generate images in constant address space

2016-07-20 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 64706.
ashi1 marked an inline comment as done.
ashi1 added a comment.

Removed excess semicolon by Anastasia's comments


Repository:
  rL LLVM

https://reviews.llvm.org/D22523

Files:
  lib/CodeGen/CGOpenCLRuntime.cpp
  lib/CodeGen/TargetInfo.cpp
  lib/CodeGen/TargetInfo.h
  test/CodeGenOpenCL/opencl_types.cl

Index: test/CodeGenOpenCL/opencl_types.cl
===
--- test/CodeGenOpenCL/opencl_types.cl
+++ test/CodeGenOpenCL/opencl_types.cl
@@ -1,40 +1,49 @@
-// RUN: %clang_cc1 %s -emit-llvm -o - -O0 | FileCheck %s
+// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - -O0 | FileCheck %s --check-prefix=CHECK-SPIR
+// RUN: %clang_cc1 %s -triple "amdgcn--amdhsa" -emit-llvm -o - -O0 | FileCheck %s --check-prefix=CHECK-AMDGCN
 
 constant sampler_t glb_smp = 7;
-// CHECK: constant i32 7
+// CHECK-SPIR: constant i32 7
+// CHECK-AMDGCN: addrspace(2) constant i32 7
 
 void fnc1(image1d_t img) {}
-// CHECK: @fnc1(%opencl.image1d_ro_t*
+// CHECK-SPIR: @fnc1(%opencl.image1d_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc1(%opencl.image1d_ro_t addrspace(2)*
 
 void fnc1arr(image1d_array_t img) {}
-// CHECK: @fnc1arr(%opencl.image1d_array_ro_t*
+// CHECK-SPIR: @fnc1arr(%opencl.image1d_array_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc1arr(%opencl.image1d_array_ro_t addrspace(2)*
 
 void fnc1buff(image1d_buffer_t img) {}
-// CHECK: @fnc1buff(%opencl.image1d_buffer_ro_t*
+// CHECK-SPIR: @fnc1buff(%opencl.image1d_buffer_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc1buff(%opencl.image1d_buffer_ro_t addrspace(2)*
 
 void fnc2(image2d_t img) {}
-// CHECK: @fnc2(%opencl.image2d_ro_t*
+// CHECK-SPIR: @fnc2(%opencl.image2d_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc2(%opencl.image2d_ro_t addrspace(2)*
 
 void fnc2arr(image2d_array_t img) {}
-// CHECK: @fnc2arr(%opencl.image2d_array_ro_t*
+// CHECK-SPIR: @fnc2arr(%opencl.image2d_array_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc2arr(%opencl.image2d_array_ro_t addrspace(2)*
 
 void fnc3(image3d_t img) {}
-// CHECK: @fnc3(%opencl.image3d_ro_t*
+// CHECK-SPIR: @fnc3(%opencl.image3d_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc3(%opencl.image3d_ro_t addrspace(2)*
 
 void fnc4smp(sampler_t s) {}
-// CHECK-LABEL: define {{.*}}void @fnc4smp(i32
+// CHECK-SPIR-LABEL: define {{.*}}void @fnc4smp(i32
 
 kernel void foo(image1d_t img) {
   sampler_t smp = 5;
-  // CHECK: alloca i32
+  // CHECK-SPIR: alloca i32
   event_t evt;
-  // CHECK: alloca %opencl.event_t*
-  // CHECK: store i32 5,
+  // CHECK-SPIR: alloca %opencl.event_t*
+  // CHECK-SPIR: store i32 5,
   fnc4smp(smp);
-  // CHECK: call {{.*}}void @fnc4smp(i32
+  // CHECK-SPIR: call {{.*}}void @fnc4smp(i32
   fnc4smp(glb_smp);
-  // CHECK: call {{.*}}void @fnc4smp(i32
+  // CHECK-SPIR: call {{.*}}void @fnc4smp(i32
 }
 
 void __attribute__((overloadable)) bad1(image1d_t b, image2d_t c, image2d_t d) {}
-// CHECK-LABEL: @{{_Z4bad114ocl_image1d_ro14ocl_image2d_roS0_|"\\01\?bad1@@\$\$J0YAXPAUocl_image1d_ro@@PAUocl_image2d_ro@@1@Z"}}
+// CHECK-SPIR-LABEL: @{{_Z4bad114ocl_image1d_ro14ocl_image2d_roS0_|"\\01\?bad1@@\$\$J0YAXPAUocl_image1d_ro@@PAUocl_image2d_ro@@1@Z"}}
+// CHECK-AMDGCN-LABEL: @{{_Z4bad114ocl_image1d_ro14ocl_image2d_roS0_|"\\01\?bad1@@\$\$J0YAXPAUocl_image1d_ro@@PAUocl_image2d_ro@@1@Z"}}(%opencl.image1d_ro_t addrspace(2)*{{.*}}%opencl.image2d_ro_t addrspace(2)*{{.*}}%opencl.image2d_ro_t addrspace(2)*{{.*}})
Index: lib/CodeGen/TargetInfo.h
===
--- lib/CodeGen/TargetInfo.h
+++ lib/CodeGen/TargetInfo.h
@@ -220,6 +220,9 @@
 
   /// Get LLVM calling convention for OpenCL kernel.
   virtual unsigned getOpenCLKernelCallingConv() const;
+
+  /// Get LLVM Image Address Space for OpenCL kernel.
+  virtual unsigned getOpenCLImageAddrSpace(CodeGen::CodeGenModule ) const;
 };
 
 } // namespace CodeGen
Index: lib/CodeGen/TargetInfo.cpp
===
--- lib/CodeGen/TargetInfo.cpp
+++ lib/CodeGen/TargetInfo.cpp
@@ -375,6 +375,11 @@
 unsigned TargetCodeGenInfo::getOpenCLKernelCallingConv() const {
   return llvm::CallingConv::C;
 }
+
+unsigned TargetCodeGenInfo::getOpenCLImageAddrSpace(CodeGen::CodeGenModule ) const {
+  return CGM.getContext().getTargetAddressSpace(LangAS::opencl_global);
+}
+
 static bool isEmptyRecord(ASTContext , QualType T, bool AllowArrays);
 
 /// isEmptyField - Return true iff a the field is "empty", that is it
@@ -6832,6 +6832,7 @@
   void setTargetAttributes(const Decl *D, llvm::GlobalValue *GV,
CodeGen::CodeGenModule ) const override;
   unsigned getOpenCLKernelCallingConv() const override;
+  unsigned getOpenCLImageAddrSpace(CodeGen::CodeGenModule ) const override;
 };
 
 }
@@ -6864,6 +6864,10 @@
   return llvm::CallingConv::AMDGPU_KERNEL;
 }
 
+unsigned AMDGPUTargetCodeGenInfo::getOpenCLImageAddrSpace(CodeGen::CodeGenModule ) const {
+  return

Re: [PATCH] D22523: [OpenCL] AMDGCN target will generate images in constant address space

2016-07-19 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 64538.
ashi1 marked an inline comment as done.
ashi1 added a comment.

Revised based on Sam's comments. Also updated test file to changes with using 
triple spir-unknown-unknown.


Repository:
  rL LLVM

https://reviews.llvm.org/D22523

Files:
  lib/CodeGen/CGOpenCLRuntime.cpp
  lib/CodeGen/TargetInfo.cpp
  lib/CodeGen/TargetInfo.h
  test/CodeGenOpenCL/opencl_types.cl

Index: test/CodeGenOpenCL/opencl_types.cl
===
--- test/CodeGenOpenCL/opencl_types.cl
+++ test/CodeGenOpenCL/opencl_types.cl
@@ -1,40 +1,49 @@
-// RUN: %clang_cc1 %s -emit-llvm -o - -O0 | FileCheck %s
+// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - -O0 | FileCheck %s --check-prefix=CHECK-SPIR
+// RUN: %clang_cc1 %s -triple "amdgcn--amdhsa" -emit-llvm -o - -O0 | FileCheck %s --check-prefix=CHECK-AMDGCN
 
 constant sampler_t glb_smp = 7;
-// CHECK: constant i32 7
+// CHECK-SPIR: constant i32 7
+// CHECK-AMDGCN: addrspace(2) constant i32 7
 
 void fnc1(image1d_t img) {}
-// CHECK: @fnc1(%opencl.image1d_ro_t*
+// CHECK-SPIR: @fnc1(%opencl.image1d_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc1(%opencl.image1d_ro_t addrspace(2)*
 
 void fnc1arr(image1d_array_t img) {}
-// CHECK: @fnc1arr(%opencl.image1d_array_ro_t*
+// CHECK-SPIR: @fnc1arr(%opencl.image1d_array_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc1arr(%opencl.image1d_array_ro_t addrspace(2)*
 
 void fnc1buff(image1d_buffer_t img) {}
-// CHECK: @fnc1buff(%opencl.image1d_buffer_ro_t*
+// CHECK-SPIR: @fnc1buff(%opencl.image1d_buffer_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc1buff(%opencl.image1d_buffer_ro_t addrspace(2)*
 
 void fnc2(image2d_t img) {}
-// CHECK: @fnc2(%opencl.image2d_ro_t*
+// CHECK-SPIR: @fnc2(%opencl.image2d_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc2(%opencl.image2d_ro_t addrspace(2)*
 
 void fnc2arr(image2d_array_t img) {}
-// CHECK: @fnc2arr(%opencl.image2d_array_ro_t*
+// CHECK-SPIR: @fnc2arr(%opencl.image2d_array_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc2arr(%opencl.image2d_array_ro_t addrspace(2)*
 
 void fnc3(image3d_t img) {}
-// CHECK: @fnc3(%opencl.image3d_ro_t*
+// CHECK-SPIR: @fnc3(%opencl.image3d_ro_t addrspace(1)*
+// CHECK-AMDGCN: @fnc3(%opencl.image3d_ro_t addrspace(2)*
 
 void fnc4smp(sampler_t s) {}
-// CHECK-LABEL: define {{.*}}void @fnc4smp(i32
+// CHECK-SPIR-LABEL: define {{.*}}void @fnc4smp(i32
 
 kernel void foo(image1d_t img) {
   sampler_t smp = 5;
-  // CHECK: alloca i32
+  // CHECK-SPIR: alloca i32
   event_t evt;
-  // CHECK: alloca %opencl.event_t*
-  // CHECK: store i32 5,
+  // CHECK-SPIR: alloca %opencl.event_t*
+  // CHECK-SPIR: store i32 5,
   fnc4smp(smp);
-  // CHECK: call {{.*}}void @fnc4smp(i32
+  // CHECK-SPIR: call {{.*}}void @fnc4smp(i32
   fnc4smp(glb_smp);
-  // CHECK: call {{.*}}void @fnc4smp(i32
+  // CHECK-SPIR: call {{.*}}void @fnc4smp(i32
 }
 
 void __attribute__((overloadable)) bad1(image1d_t b, image2d_t c, image2d_t d) {}
-// CHECK-LABEL: @{{_Z4bad114ocl_image1d_ro14ocl_image2d_roS0_|"\\01\?bad1@@\$\$J0YAXPAUocl_image1d_ro@@PAUocl_image2d_ro@@1@Z"}}
+// CHECK-SPIR-LABEL: @{{_Z4bad114ocl_image1d_ro14ocl_image2d_roS0_|"\\01\?bad1@@\$\$J0YAXPAUocl_image1d_ro@@PAUocl_image2d_ro@@1@Z"}}
+// CHECK-AMDGCN-LABEL: @{{_Z4bad114ocl_image1d_ro14ocl_image2d_roS0_|"\\01\?bad1@@\$\$J0YAXPAUocl_image1d_ro@@PAUocl_image2d_ro@@1@Z"}}(%opencl.image1d_ro_t addrspace(2)*{{.*}}%opencl.image2d_ro_t addrspace(2)*{{.*}}%opencl.image2d_ro_t addrspace(2)*{{.*}})
Index: lib/CodeGen/TargetInfo.h
===
--- lib/CodeGen/TargetInfo.h
+++ lib/CodeGen/TargetInfo.h
@@ -220,6 +220,9 @@
 
   /// Get LLVM calling convention for OpenCL kernel.
   virtual unsigned getOpenCLKernelCallingConv() const;
+
+  /// Get LLVM Image Address Space for OpenCL kernel.
+  virtual unsigned getOpenCLImageAddrSpace(CodeGen::CodeGenModule ) const;
 };
 
 } // namespace CodeGen
Index: lib/CodeGen/TargetInfo.cpp
===
--- lib/CodeGen/TargetInfo.cpp
+++ lib/CodeGen/TargetInfo.cpp
@@ -375,6 +375,11 @@
 unsigned TargetCodeGenInfo::getOpenCLKernelCallingConv() const {
   return llvm::CallingConv::C;
 }
+
+unsigned TargetCodeGenInfo::getOpenCLImageAddrSpace(CodeGen::CodeGenModule ) const {
+  return CGM.getContext().getTargetAddressSpace(LangAS::opencl_global);
+}
+
 static bool isEmptyRecord(ASTContext , QualType T, bool AllowArrays);
 
 /// isEmptyField - Return true iff a the field is "empty", that is it
@@ -6832,6 +6832,7 @@
   void setTargetAttributes(const Decl *D, llvm::GlobalValue *GV,
CodeGen::CodeGenModule ) const override;
   unsigned getOpenCLKernelCallingConv() const override;
+  unsigned getOpenCLImageAddrSpace(CodeGen::CodeGenModule ) const override;
 };
 
 }
@@ -6864,6 +6864,10 @@
   return llvm::CallingConv::AMDGPU_KERNEL;
 }
 
+unsigned AMDGPUTargetCodeGenInfo::getOpenCLImageAddrSpace(CodeGen::CodeGenModule )

[PATCH] D22523: [OpenCL] AMDGCN target will generate images in constant address space

2016-07-19 Thread Aaron En Ye Shi via cfe-commits 
ashi1 created this revision.
ashi1 added reviewers: yaxunl, Anastasia.
ashi1 added a subscriber: cfe-commits.
ashi1 set the repository for this revision to rL LLVM.

Allows AMDGCN target to generate images (such as %opencl.image2d_t) in constant 
address space.
Images will still be generated in global address space by default. 

Added tests to existing opencl-types.cl in test\CodeGenOpenCL

Repository:
  rL LLVM

https://reviews.llvm.org/D22523

Files:
  lib/CodeGen/CGOpenCLRuntime.cpp
  lib/CodeGen/TargetInfo.cpp
  lib/CodeGen/TargetInfo.h
  test/CodeGenOpenCL/opencl_types.cl

Index: test/CodeGenOpenCL/opencl_types.cl
===
--- test/CodeGenOpenCL/opencl_types.cl
+++ test/CodeGenOpenCL/opencl_types.cl
@@ -1,40 +1,49 @@
-// RUN: %clang_cc1 %s -emit-llvm -o - -O0 | FileCheck %s
+// RUN: %clang_cc1 %s -emit-llvm -o - -O0 | FileCheck %s --check-prefix=CHECK-NORMAL
+// RUN: %clang_cc1 %s -triple "amdgcn--amdhsa" -emit-llvm -o - -O0 | FileCheck %s --check-prefix=CHECK-AMDGCN
 
 constant sampler_t glb_smp = 7;
-// CHECK: constant i32 7
+// CHECK-NORMAL: constant i32 7
+// CHECK-AMDGCN: addrspace(2) constant i32 7
 
 void fnc1(image1d_t img) {}
-// CHECK: @fnc1(%opencl.image1d_ro_t*
+// CHECK-NORMAL: @fnc1(%opencl.image1d_ro_t*
+// CHECK-AMDGCN: @fnc1(%opencl.image1d_ro_t addrspace(2)*
 
 void fnc1arr(image1d_array_t img) {}
-// CHECK: @fnc1arr(%opencl.image1d_array_ro_t*
+// CHECK-NORMAL: @fnc1arr(%opencl.image1d_array_ro_t*
+// CHECK-AMDGCN: @fnc1arr(%opencl.image1d_array_ro_t addrspace(2)*
 
 void fnc1buff(image1d_buffer_t img) {}
-// CHECK: @fnc1buff(%opencl.image1d_buffer_ro_t*
+// CHECK-NORMAL: @fnc1buff(%opencl.image1d_buffer_ro_t*
+// CHECK-AMDGCN: @fnc1buff(%opencl.image1d_buffer_ro_t addrspace(2)*
 
 void fnc2(image2d_t img) {}
-// CHECK: @fnc2(%opencl.image2d_ro_t*
+// CHECK-NORMAL: @fnc2(%opencl.image2d_ro_t*
+// CHECK-AMDGCN: @fnc2(%opencl.image2d_ro_t addrspace(2)*
 
 void fnc2arr(image2d_array_t img) {}
-// CHECK: @fnc2arr(%opencl.image2d_array_ro_t*
+// CHECK-NORMAL: @fnc2arr(%opencl.image2d_array_ro_t*
+// CHECK-AMDGCN: @fnc2arr(%opencl.image2d_array_ro_t addrspace(2)*
 
 void fnc3(image3d_t img) {}
-// CHECK: @fnc3(%opencl.image3d_ro_t*
+// CHECK-NORMAL: @fnc3(%opencl.image3d_ro_t*
+// CHECK-AMDGCN: @fnc3(%opencl.image3d_ro_t addrspace(2)*
 
 void fnc4smp(sampler_t s) {}
-// CHECK-LABEL: define {{.*}}void @fnc4smp(i32
+// CHECK-NORMAL-LABEL: define {{.*}}void @fnc4smp(i32
 
 kernel void foo(image1d_t img) {
   sampler_t smp = 5;
-  // CHECK: alloca i32
+  // CHECK-NORMAL: alloca i32
   event_t evt;
-  // CHECK: alloca %opencl.event_t*
-  // CHECK: store i32 5,
+  // CHECK-NORMAL: alloca %opencl.event_t*
+  // CHECK-NORMAL: store i32 5,
   fnc4smp(smp);
-  // CHECK: call {{.*}}void @fnc4smp(i32
+  // CHECK-NORMAL: call {{.*}}void @fnc4smp(i32
   fnc4smp(glb_smp);
-  // CHECK: call {{.*}}void @fnc4smp(i32
+  // CHECK-NORMAL: call {{.*}}void @fnc4smp(i32
 }
 
 void __attribute__((overloadable)) bad1(image1d_t b, image2d_t c, image2d_t d) {}
-// CHECK-LABEL: @{{_Z4bad114ocl_image1d_ro14ocl_image2d_roS0_|"\\01\?bad1@@\$\$J0YAXPAUocl_image1d_ro@@PAUocl_image2d_ro@@1@Z"}}
+// CHECK-NORMAL-LABEL: @{{_Z4bad114ocl_image1d_ro14ocl_image2d_roS0_|"\\01\?bad1@@\$\$J0YAXPAUocl_image1d_ro@@PAUocl_image2d_ro@@1@Z"}}
+// CHECK-AMDGCN-LABEL: @{{_Z4bad114ocl_image1d_ro14ocl_image2d_roS0_|"\\01\?bad1@@\$\$J0YAXPAUocl_image1d_ro@@PAUocl_image2d_ro@@1@Z"}}(%opencl.image1d_ro_t addrspace(2)*{{.*}}%opencl.image2d_ro_t addrspace(2)*{{.*}}%opencl.image2d_ro_t addrspace(2)*{{.*}})
Index: lib/CodeGen/TargetInfo.h
===
--- lib/CodeGen/TargetInfo.h
+++ lib/CodeGen/TargetInfo.h
@@ -220,6 +220,9 @@
 
   /// Get LLVM calling convention for OpenCL kernel.
   virtual unsigned getOpenCLKernelCallingConv() const;
+
+  /// Get LLVM Image Address Space for OpenCL kernel.
+  virtual unsigned getOpenCLImageAddrSpace(CodeGen::CodeGenModule ) const;
 };
 
 } // namespace CodeGen
Index: lib/CodeGen/TargetInfo.cpp
===
--- lib/CodeGen/TargetInfo.cpp
+++ lib/CodeGen/TargetInfo.cpp
@@ -375,6 +375,11 @@
 unsigned TargetCodeGenInfo::getOpenCLKernelCallingConv() const {
   return llvm::CallingConv::C;
 }
+
+unsigned TargetCodeGenInfo::getOpenCLImageAddrSpace(CodeGen::CodeGenModule ) const {
+  return CGM.getContext().getTargetAddressSpace(LangAS::opencl_global);
+}
+
 static bool isEmptyRecord(ASTContext , QualType T, bool AllowArrays);
 
 /// isEmptyField - Return true iff a the field is "empty", that is it
@@ -6832,6 +6832,7 @@
   void setTargetAttributes(const Decl *D, llvm::GlobalValue *GV,
CodeGen::CodeGenModule ) const override;
   unsigned getOpenCLKernelCallingConv() const override;
+  unsigned getOpenCLImageAddrSpace(CodeGen::CodeGenModule ) const override;
 };
 
 }
@@ -6864,6 +6864,10 @@
   return

Re: [PATCH] D22424: [OpenCL] Fixes bug of missing OCL related metadata on the AMDGCN target

2016-07-19 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 64513.
ashi1 marked an inline comment as done.
ashi1 added a comment.

Revised based on Anastasia's comments. Now using new function name 
appendOpenCLVersionMD(


Repository:
  rL LLVM

https://reviews.llvm.org/D22424

Files:
  lib/CodeGen/TargetInfo.cpp
  test/CodeGenOpenCL/spir_version.cl

Index: test/CodeGenOpenCL/spir_version.cl
===
--- test/CodeGenOpenCL/spir_version.cl
+++ test/CodeGenOpenCL/spir_version.cl
@@ -1,18 +1,31 @@
-// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - | 
FileCheck %s --check-prefix=CL10
-// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - 
-cl-std=CL1.2 | FileCheck %s --check-prefix=CL12
-// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - 
-cl-std=CL2.0 | FileCheck %s --check-prefix=CL20
-// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - | 
FileCheck %s --check-prefix=CL10
-// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - 
-cl-std=CL1.2 | FileCheck %s --check-prefix=CL12
-// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - 
-cl-std=CL2.0 | FileCheck %s --check-prefix=CL20
+// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - | 
FileCheck %s --check-prefix=CHECK-SPIR-CL10
+// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - 
-cl-std=CL1.2 | FileCheck %s --check-prefix=CHECK-SPIR-CL12
+// RUN: %clang_cc1 %s -triple "spir-unknown-unknown" -emit-llvm -o - 
-cl-std=CL2.0 | FileCheck %s --check-prefix=CHECK-SPIR-CL20
+// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - | 
FileCheck %s --check-prefix=CHECK-SPIR-CL10
+// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - 
-cl-std=CL1.2 | FileCheck %s --check-prefix=CHECK-SPIR-CL12
+// RUN: %clang_cc1 %s -triple "spir64-unknown-unknown" -emit-llvm -o - 
-cl-std=CL2.0 | FileCheck %s --check-prefix=CHECK-SPIR-CL20
+
+// RUN: %clang_cc1 %s -triple "amdgcn--amdhsa" -emit-llvm -o - | FileCheck %s 
--check-prefix=CHECK-AMDGCN-CL10
+// RUN: %clang_cc1 %s -triple "amdgcn--amdhsa" -emit-llvm -o - -cl-std=CL1.2 | 
FileCheck %s --check-prefix=CHECK-AMDGCN-CL12
+// RUN: %clang_cc1 %s -triple "amdgcn--amdhsa" -emit-llvm -o - -cl-std=CL2.0 | 
FileCheck %s --check-prefix=CHECK-AMDGCN-CL20
+
 kernel void foo() {}
-// CL10: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
-// CL10: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
-// CL10: [[SPIR]] = !{i32 2, i32 0}
-// CL10: [[OCL]] = !{i32 1, i32 0}
-// CL12: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
-// CL12: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
-// CL12: [[SPIR]] = !{i32 2, i32 0}
-// CL12: [[OCL]] = !{i32 1, i32 2}
-// CL20: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
-// CL20: !opencl.ocl.version = !{[[SPIR:![0-9]+]]}
-// CL20: [[SPIR]] = !{i32 2, i32 0}
+
+// CHECK-SPIR-CL10: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
+// CHECK-SPIR-CL10: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
+// CHECK-SPIR-CL10: [[SPIR]] = !{i32 2, i32 0}
+// CHECK-SPIR-CL10: [[OCL]] = !{i32 1, i32 0}
+// CHECK-SPIR-CL12: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
+// CHECK-SPIR-CL12: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
+// CHECK-SPIR-CL12: [[SPIR]] = !{i32 2, i32 0}
+// CHECK-SPIR-CL12: [[OCL]] = !{i32 1, i32 2}
+// CHECK-SPIR-CL20: !opencl.spir.version = !{[[SPIR:![0-9]+]]}
+// CHECK-SPIR-CL20: !opencl.ocl.version = !{[[SPIR:![0-9]+]]}
+// CHECK-SPIR-CL20: [[SPIR]] = !{i32 2, i32 0}
+
+// CHECK-AMDGCN-CL10: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
+// CHECK-AMDGCN-CL10: [[OCL]] = !{i32 1, i32 0}
+// CHECK-AMDGCN-CL12: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
+// CHECK-AMDGCN-CL12: [[OCL]] = !{i32 1, i32 2}
+// CHECK-AMDGCN-CL20: !opencl.ocl.version = !{[[OCL:![0-9]+]]}
+// CHECK-AMDGCN-CL20: [[OCL]] = !{i32 2, i32 0}
\ No newline at end of file
Index: lib/CodeGen/TargetInfo.cpp
===
--- lib/CodeGen/TargetInfo.cpp
+++ lib/CodeGen/TargetInfo.cpp
@@ -6836,6 +6836,8 @@
 
 }
 
+static void appendOpenCLVersionMD (CodeGen::CodeGenModule );
+
 void AMDGPUTargetCodeGenInfo::setTargetAttributes(
   const Decl *D,
   llvm::GlobalValue *GV,
@@ -6857,6 +6859,8 @@
 if (NumSGPR != 0)
   F->addFnAttr("amdgpu_num_sgpr", llvm::utostr(NumSGPR));
   }
+
+  appendOpenCLVersionMD(M);
 }
 
 
@@ -7530,6 +7534,13 @@
   llvm::NamedMDNode *SPIRVerMD =
   M.getOrInsertNamedMetadata("opencl.spir.version");
   SPIRVerMD->addOperand(llvm::MDNode::get(Ctx, SPIRVerElts));
+  appendOpenCLVersionMD(CGM);
+}
+
+static void appendOpenCLVersionMD (CodeGen::CodeGenModule ) {
+  llvm::LLVMContext  = CGM.getModule().getContext();
+  llvm::Type *Int32Ty = llvm::Type::getInt32Ty(Ctx);
+  llvm::Module  = CGM.getModule();
   // SPIR v2.0 s2.13 - The OpenCL version used by the module is stored in the
   // opencl.ocl.version named metadata node.
   llvm::Metadata *OCLVerElts[] = {


Index:

Re: [PATCH] D22170: [OpenCL] Fixes opencl.cl testcase issues and cl-strict-aliasing only allowed with cl-std=CL

2016-07-12 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 63722.
ashi1 marked 4 inline comments as done.
ashi1 added a comment.

Revised to Anastasia's comments. Removed opencl-blocks.cl, and created a 
generic opencl.cl inside test/Frontend folder.

This change passes clang-test.


Repository:
  rL LLVM

http://reviews.llvm.org/D22170

Files:
  lib/Frontend/CompilerInvocation.cpp
  test/Driver/opencl.cl
  test/Frontend/opencl-blocks.cl
  test/Frontend/opencl.cl

Index: test/Frontend/opencl.cl
===
--- test/Frontend/opencl.cl
+++ test/Frontend/opencl.cl
@@ -0,0 +1,27 @@
+// RUN: %clang_cc1 %s -verify -fsyntax-only
+// RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL1.1
+// RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL1.2
+// RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL2.0
+// RUN: %clang_cc1 %s -verify -fsyntax-only -fblocks -DBLOCKS
+// RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL1.1 -fblocks -DBLOCKS
+// RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL1.2 -fblocks -DBLOCKS
+// RUN: %clang_cc1 %s -triple amdgcn--amdhsa -x c -std=c99 -verify -fsyntax-only
+// RUN: %clang_cc1 -cl-std=CL1.1 -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION11 %s
+// RUN: %clang_cc1 -cl-std=CL1.2 -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION12 %s
+// RUN: %clang_cc1 -cl-std=CL2.0 -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION20 %s
+
+void f(void (^g)(void)) {
+#ifdef __OPENCL_C_VERSION__
+#if __OPENCL_C_VERSION__ < CL_VERSION_2_0 && !defined(BLOCKS)
+  // expected-error@-3{{blocks support disabled - compile with -fblocks or for OpenCL 2.0 or above}}
+#else
+  // expected-no-diagnostics
+#endif
+#else
+  // expected-error@-8{{blocks support disabled - compile with -fblocks or pick a deployment target that supports them}}
+#endif
+}
+
+// CHECK-INVALID-OPENCL-VERSION11: warning: OpenCL version 1.1 does not support the option '-cl-strict-aliasing'
+// CHECK-INVALID-OPENCL-VERSION12: warning: OpenCL version 1.2 does not support the option '-cl-strict-aliasing'
+// CHECK-INVALID-OPENCL-VERSION20: warning: OpenCL version 2.0 does not support the option '-cl-strict-aliasing'
\ No newline at end of file
Index: test/Frontend/opencl-blocks.cl
===
--- test/Frontend/opencl-blocks.cl
+++ test/Frontend/opencl-blocks.cl
@@ -1,20 +0,0 @@
-// RUN: %clang_cc1 %s -verify -fsyntax-only
-// RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL1.1
-// RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL1.2
-// RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL2.0
-// RUN: %clang_cc1 %s -verify -fsyntax-only -fblocks -DBLOCKS
-// RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL1.1 -fblocks -DBLOCKS
-// RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL1.2 -fblocks -DBLOCKS
-// RUN: %clang_cc1 %s -triple amdgcn--amdhsa -x c -std=c99 -verify -fsyntax-only
-
-void f(void (^g)(void)) {
-#ifdef __OPENCL_C_VERSION__
-#if __OPENCL_C_VERSION__ < CL_VERSION_2_0 && !defined(BLOCKS)
-  // expected-error@-3{{blocks support disabled - compile with -fblocks or for OpenCL 2.0 or above}}
-#else
-  // expected-no-diagnostics
-#endif
-#else
-  // expected-error@-8{{blocks support disabled - compile with -fblocks or pick a deployment target that supports them}}
-#endif
-}
Index: test/Driver/opencl.cl
===
--- test/Driver/opencl.cl
+++ test/Driver/opencl.cl
@@ -1,42 +1,35 @@
-// XFAIL: *
-// RUN: %clang -S -### -cl-std=CL %s | FileCheck --check-prefix=CHECK-CL %s
-// RUN: %clang -S -### -cl-std=CL1.1 %s | FileCheck --check-prefix=CHECK-CL11 %s
-// RUN: %clang -S -### -cl-std=CL1.2 %s | FileCheck --check-prefix=CHECK-CL12 %s
-// RUN: %clang -S -### -cl-std=CL2.0 %s | FileCheck --check-prefix=CHECK-CL20 %s
-// RUN: %clang -S -### -cl-opt-disable %s | FileCheck --check-prefix=CHECK-OPT-DISABLE %s
-// RUN: %clang -S -### -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-STRICT-ALIASING %s
-// RUN: %clang -S -### -cl-std=CL1.1 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION11 %s
-// RUN: %clang -S -### -cl-std=CL1.2 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION12 %s
-// RUN: %clang -S -### -cl-std=CL2.0 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION20 %s
-// RUN: %clang -S -### -cl-single-precision-constant %s | FileCheck --check-prefix=CHECK-SINGLE-PRECISION-CONST %s
-// RUN: %clang -S -### -cl-finite-math-only %s | FileCheck --check-prefix=CHECK-FINITE-MATH-ONLY %s
-// RUN: %clang -S -### -cl-kernel-arg-info %s | FileCheck --check-prefix=CHECK-KERNEL-ARG-INFO %s
-// RUN: %clang -S -### -cl-unsafe-math-optimizations %s | FileCheck --check-prefix=CHECK-UNSAFE-MATH-OPT %s
-// RUN: %clang -S -### -cl-fast-relaxed-math %s | FileCheck --check-prefix=CHECK-FAST-RELAXED-MATH %s

Re: [PATCH] D22170: [OpenCL] Fixes opencl.cl testcase issues and cl-strict-aliasing only allowed with cl-std=CL

2016-07-11 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 63539.
ashi1 marked 2 inline comments as done.
ashi1 added a comment.

Moved cl-strict-aliasing testing to a new file cl-strict-aliasing.cl


Repository:
  rL LLVM

http://reviews.llvm.org/D22170

Files:
  lib/Frontend/CompilerInvocation.cpp
  test/Driver/opencl.cl
  test/Frontend/cl-strict-aliasing.cl

Index: test/Frontend/cl-strict-aliasing.cl
===
--- test/Frontend/cl-strict-aliasing.cl
+++ test/Frontend/cl-strict-aliasing.cl
@@ -0,0 +1,9 @@
+// RUN: %clang_cc1 -cl-std=CL1.1 -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION11 %s
+// RUN: %clang_cc1 -cl-std=CL1.2 -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION12 %s
+// RUN: %clang_cc1 -cl-std=CL2.0 -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION20 %s
+
+// CHECK-INVALID-OPENCL-VERSION11: warning: OpenCL version 1.1 does not support the option '-cl-strict-aliasing'
+// CHECK-INVALID-OPENCL-VERSION12: warning: OpenCL version 1.2 does not support the option '-cl-strict-aliasing'
+// CHECK-INVALID-OPENCL-VERSION20: warning: OpenCL version 2.0 does not support the option '-cl-strict-aliasing'
+
+kernel void func(void);
\ No newline at end of file
Index: test/Driver/opencl.cl
===
--- test/Driver/opencl.cl
+++ test/Driver/opencl.cl
@@ -1,42 +1,35 @@
-// XFAIL: *
-// RUN: %clang -S -### -cl-std=CL %s | FileCheck --check-prefix=CHECK-CL %s
-// RUN: %clang -S -### -cl-std=CL1.1 %s | FileCheck --check-prefix=CHECK-CL11 %s
-// RUN: %clang -S -### -cl-std=CL1.2 %s | FileCheck --check-prefix=CHECK-CL12 %s
-// RUN: %clang -S -### -cl-std=CL2.0 %s | FileCheck --check-prefix=CHECK-CL20 %s
-// RUN: %clang -S -### -cl-opt-disable %s | FileCheck --check-prefix=CHECK-OPT-DISABLE %s
-// RUN: %clang -S -### -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-STRICT-ALIASING %s
-// RUN: %clang -S -### -cl-std=CL1.1 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION11 %s
-// RUN: %clang -S -### -cl-std=CL1.2 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION12 %s
-// RUN: %clang -S -### -cl-std=CL2.0 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION20 %s
-// RUN: %clang -S -### -cl-single-precision-constant %s | FileCheck --check-prefix=CHECK-SINGLE-PRECISION-CONST %s
-// RUN: %clang -S -### -cl-finite-math-only %s | FileCheck --check-prefix=CHECK-FINITE-MATH-ONLY %s
-// RUN: %clang -S -### -cl-kernel-arg-info %s | FileCheck --check-prefix=CHECK-KERNEL-ARG-INFO %s
-// RUN: %clang -S -### -cl-unsafe-math-optimizations %s | FileCheck --check-prefix=CHECK-UNSAFE-MATH-OPT %s
-// RUN: %clang -S -### -cl-fast-relaxed-math %s | FileCheck --check-prefix=CHECK-FAST-RELAXED-MATH %s
-// RUN: %clang -S -### -cl-mad-enable %s | FileCheck --check-prefix=CHECK-MAD-ENABLE %s
-// RUN: %clang -S -### -cl-no-signed-zeros %s | FileCheck --check-prefix=CHECK-NO-SIGNED-ZEROS %s
-// RUN: %clang -S -### -cl-denorms-are-zero %s | FileCheck --check-prefix=CHECK-DENORMS-ARE-ZERO %s
-// RUN: not %clang_cc1 -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
-// RUN: not %clang_cc1 -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
+// RUN: %clang -S -### -cl-std=CL %s 2>&1 | FileCheck --check-prefix=CHECK-CL %s
+// RUN: %clang -S -### -cl-std=CL1.1 %s 2>&1 | FileCheck --check-prefix=CHECK-CL11 %s
+// RUN: %clang -S -### -cl-std=CL1.2 %s 2>&1 | FileCheck --check-prefix=CHECK-CL12 %s
+// RUN: %clang -S -### -cl-std=CL2.0 %s 2>&1 | FileCheck --check-prefix=CHECK-CL20 %s
+// RUN: %clang -S -### -cl-opt-disable %s 2>&1 | FileCheck --check-prefix=CHECK-OPT-DISABLE %s
+// RUN: %clang -S -### -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-STRICT-ALIASING %s
+// RUN: %clang -S -### -cl-single-precision-constant %s 2>&1 | FileCheck --check-prefix=CHECK-SINGLE-PRECISION-CONST %s
+// RUN: %clang -S -### -cl-finite-math-only %s 2>&1 | FileCheck --check-prefix=CHECK-FINITE-MATH-ONLY %s
+// RUN: %clang -S -### -cl-kernel-arg-info %s 2>&1 | FileCheck --check-prefix=CHECK-KERNEL-ARG-INFO %s
+// RUN: %clang -S -### -cl-unsafe-math-optimizations %s 2>&1 | FileCheck --check-prefix=CHECK-UNSAFE-MATH-OPT %s
+// RUN: %clang -S -### -cl-fast-relaxed-math %s 2>&1 | FileCheck --check-prefix=CHECK-FAST-RELAXED-MATH %s
+// RUN: %clang -S -### -cl-mad-enable %s 2>&1 | FileCheck --check-prefix=CHECK-MAD-ENABLE %s
+// RUN: %clang -S -### -cl-no-signed-zeros %s 2>&1 | FileCheck --check-prefix=CHECK-NO-SIGNED-ZEROS %s
+// RUN: %clang -S -### -cl-denorms-are-zero %s 2>&1 | FileCheck --check-prefix=CHECK-DENORMS-ARE-ZERO %s
+// RUN: not %clang_cc1 -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
+// RUN: not %clang_cc1 -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
 
-// CHECK-CL:

Re: [PATCH] D22170: [OpenCL] Fixes opencl.cl testcase issues and cl-strict-aliasing only allowed with cl-std=CL

2016-07-11 Thread Aaron En Ye Shi via cfe-commits 
ashi1 marked 4 inline comments as done.


Comment at: lib/Frontend/CompilerInvocation.cpp:1681
@@ -1692,1 +1680,3 @@
 
+  // -cl-strict-aliasing needs to emit diagnostic in the case where CL > 1.0.
+  // This option should be deprecated for CL > 1.0 because

Anastasia wrote:
> Was this code moved intensionally?
Yes this had to be moved intentionally, due to Opts.OpenCLVersion not being 
correctly set up until after the above function call to 
CompilerInvocation::setLangDefaults(


Comment at: test/Frontend/opencl-blocks.cl:9
@@ -8,1 +8,3 @@
 // RUN: %clang_cc1 %s -triple amdgcn--amdhsa -x c -std=c99 -verify 
-fsyntax-only
+// RUN: %clang_cc1 -cl-std=CL1.1 -cl-strict-aliasing %s 2>&1 | FileCheck 
--check-prefix=CHECK-INVALID-OPENCL-VERSION11 %s
+// RUN: %clang_cc1 -cl-std=CL1.2 -cl-strict-aliasing %s 2>&1 | FileCheck 
--check-prefix=CHECK-INVALID-OPENCL-VERSION12 %s

yaxunl wrote:
> Anastasia wrote:
> > yaxunl wrote:
> > > Better separate these tests to another file, e.g. cl-strict-aliasing.cl
> > I think it was right to have this in test/Driver/opencl.cl. Why was it 
> > moved in here?
> This is a frontend option and the warning is emitted by frontend, not the 
> driver. The driver does not consume the option. It just passes it to the 
> frontend.
> 
> The driver test is mostly testing whether the option is correctly passed to 
> the compiler invocation by using -###.
should it be called opencl-strict-aliasing.cl or cl-strict-aliasing.cl


Repository:
  rL LLVM

http://reviews.llvm.org/D22170



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D22170: [OpenCL] Fixes opencl.cl testcase issues and cl-strict-aliasing only allowed with cl-std=CL

2016-07-08 Thread Aaron En Ye Shi via cfe-commits 
ashi1 created this revision.
ashi1 added reviewers: Anastasia, bkramer.
ashi1 added subscribers: nhaustov, rsmith, bader, pxli168, cfe-commits, yaxunl.
ashi1 set the repository for this revision to rL LLVM.

Fixes failures in test/Driver/opencl.cl.

Also fixes strict-aliasing option to only be allowed when OpenCL Version 1.0. 
Added testcase in test/Frontend/opencl-blocks.cl . 

Repository:
  rL LLVM

http://reviews.llvm.org/D22170

Files:
  lib/Frontend/CompilerInvocation.cpp
  test/Driver/opencl.cl
  test/Frontend/opencl-blocks.cl

Index: test/Frontend/opencl-blocks.cl
===
--- test/Frontend/opencl-blocks.cl
+++ test/Frontend/opencl-blocks.cl
@@ -6,6 +6,9 @@
 // RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL1.1 -fblocks -DBLOCKS
 // RUN: %clang_cc1 %s -verify -fsyntax-only -cl-std=CL1.2 -fblocks -DBLOCKS
 // RUN: %clang_cc1 %s -triple amdgcn--amdhsa -x c -std=c99 -verify -fsyntax-only
+// RUN: %clang_cc1 -cl-std=CL1.1 -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION11 %s
+// RUN: %clang_cc1 -cl-std=CL1.2 -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION12 %s
+// RUN: %clang_cc1 -cl-std=CL2.0 -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION20 %s
 
 void f(void (^g)(void)) {
 #ifdef __OPENCL_C_VERSION__
@@ -18,3 +21,7 @@
   // expected-error@-8{{blocks support disabled - compile with -fblocks or pick a deployment target that supports them}}
 #endif
 }
+
+// CHECK-INVALID-OPENCL-VERSION11: warning: OpenCL version 1.1 does not support the option '-cl-strict-aliasing'
+// CHECK-INVALID-OPENCL-VERSION12: warning: OpenCL version 1.2 does not support the option '-cl-strict-aliasing'
+// CHECK-INVALID-OPENCL-VERSION20: warning: OpenCL version 2.0 does not support the option '-cl-strict-aliasing'
\ No newline at end of file
Index: test/Driver/opencl.cl
===
--- test/Driver/opencl.cl
+++ test/Driver/opencl.cl
@@ -1,42 +1,35 @@
-// XFAIL: *
-// RUN: %clang -S -### -cl-std=CL %s | FileCheck --check-prefix=CHECK-CL %s
-// RUN: %clang -S -### -cl-std=CL1.1 %s | FileCheck --check-prefix=CHECK-CL11 %s
-// RUN: %clang -S -### -cl-std=CL1.2 %s | FileCheck --check-prefix=CHECK-CL12 %s
-// RUN: %clang -S -### -cl-std=CL2.0 %s | FileCheck --check-prefix=CHECK-CL20 %s
-// RUN: %clang -S -### -cl-opt-disable %s | FileCheck --check-prefix=CHECK-OPT-DISABLE %s
-// RUN: %clang -S -### -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-STRICT-ALIASING %s
-// RUN: %clang -S -### -cl-std=CL1.1 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION11 %s
-// RUN: %clang -S -### -cl-std=CL1.2 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION12 %s
-// RUN: %clang -S -### -cl-std=CL2.0 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION20 %s
-// RUN: %clang -S -### -cl-single-precision-constant %s | FileCheck --check-prefix=CHECK-SINGLE-PRECISION-CONST %s
-// RUN: %clang -S -### -cl-finite-math-only %s | FileCheck --check-prefix=CHECK-FINITE-MATH-ONLY %s
-// RUN: %clang -S -### -cl-kernel-arg-info %s | FileCheck --check-prefix=CHECK-KERNEL-ARG-INFO %s
-// RUN: %clang -S -### -cl-unsafe-math-optimizations %s | FileCheck --check-prefix=CHECK-UNSAFE-MATH-OPT %s
-// RUN: %clang -S -### -cl-fast-relaxed-math %s | FileCheck --check-prefix=CHECK-FAST-RELAXED-MATH %s
-// RUN: %clang -S -### -cl-mad-enable %s | FileCheck --check-prefix=CHECK-MAD-ENABLE %s
-// RUN: %clang -S -### -cl-no-signed-zeros %s | FileCheck --check-prefix=CHECK-NO-SIGNED-ZEROS %s
-// RUN: %clang -S -### -cl-denorms-are-zero %s | FileCheck --check-prefix=CHECK-DENORMS-ARE-ZERO %s
-// RUN: not %clang_cc1 -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
-// RUN: not %clang_cc1 -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
+// RUN: %clang -S -### -cl-std=CL %s 2>&1 | FileCheck --check-prefix=CHECK-CL %s
+// RUN: %clang -S -### -cl-std=CL1.1 %s 2>&1 | FileCheck --check-prefix=CHECK-CL11 %s
+// RUN: %clang -S -### -cl-std=CL1.2 %s 2>&1 | FileCheck --check-prefix=CHECK-CL12 %s
+// RUN: %clang -S -### -cl-std=CL2.0 %s 2>&1 | FileCheck --check-prefix=CHECK-CL20 %s
+// RUN: %clang -S -### -cl-opt-disable %s 2>&1 | FileCheck --check-prefix=CHECK-OPT-DISABLE %s
+// RUN: %clang -S -### -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-STRICT-ALIASING %s
+// RUN: %clang -S -### -cl-single-precision-constant %s 2>&1 | FileCheck --check-prefix=CHECK-SINGLE-PRECISION-CONST %s
+// RUN: %clang -S -### -cl-finite-math-only %s 2>&1 | FileCheck --check-prefix=CHECK-FINITE-MATH-ONLY %s
+// RUN: %clang -S -### -cl-kernel-arg-info %s 2>&1 | FileCheck --check-prefix=CHECK-KERNEL-ARG-INFO %s
+// RUN: %clang -S -### -cl-unsafe-math-optimizations %s 2>&1 | FileCheck --check-prefix=CHECK-UNSAFE-MATH-OPT %s
+// RUN: %clang -S

Re: [PATCH] D21031: [OpenCL] Allow -cl-std and other standard -cl- options in driver

2016-07-07 Thread Aaron En Ye Shi via cfe-commits 
ashi1 marked an inline comment as done.


Comment at: cfe/trunk/include/clang/Driver/Options.td:381
@@ +380,3 @@
+def cl_unsafe_math_optimizations : Flag<["-"], 
"cl-unsafe-math-optimizations">, Group, Flags<[CC1Option]>,
+  HelpText<"OpenCL only. Allow unsafe floating-point optimizations.  Also 
implies -cl-no-signed-zeros and -cl-mad-enable.">;
+def cl_fast_relaxed_math : Flag<["-"], "cl-fast-relaxed-math">, 
Group, Flags<[CC1Option]>,

jvesely wrote:
> It'd be nice if you added cl-no-signed-zeros since it's mentioned here
Can you review http://reviews.llvm.org/D22067 ? Thanks


Repository:
  rL LLVM

http://reviews.llvm.org/D21031



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Re: [PATCH] D22067: [OpenCL] Add missing -cl-no-signed-zeros option into driver

2016-07-07 Thread Aaron En Ye Shi via cfe-commits 
ashi1 added a reviewer: yaxunl.
ashi1 removed rL LLVM as the repository for this revision.
ashi1 updated this revision to Diff 63143.
ashi1 added a comment.

Revised base on Sam's comments.

Added no-signed-zeros as an attribute no-signed-zeros-fp-math. 
Added a test for no-signed-zeros-fp-math.


http://reviews.llvm.org/D22067

Files:
  include/clang/Driver/Options.td
  lib/CodeGen/CGCall.cpp
  lib/Driver/Tools.cpp
  lib/Frontend/CompilerInvocation.cpp
  test/CodeGenOpenCL/no-signed-zeros.cl
  test/Driver/opencl.cl

Index: test/Driver/opencl.cl
===
--- test/Driver/opencl.cl
+++ test/Driver/opencl.cl
@@ -14,6 +14,7 @@
 // RUN: %clang -S -### -cl-unsafe-math-optimizations %s | FileCheck 
--check-prefix=CHECK-UNSAFE-MATH-OPT %s
 // RUN: %clang -S -### -cl-fast-relaxed-math %s | FileCheck 
--check-prefix=CHECK-FAST-RELAXED-MATH %s
 // RUN: %clang -S -### -cl-mad-enable %s | FileCheck 
--check-prefix=CHECK-MAD-ENABLE %s
+// RUN: %clang -S -### -cl-no-signed-zeros %s | FileCheck 
--check-prefix=CHECK-NO-SIGNED-ZEROS %s
 // RUN: %clang -S -### -cl-denorms-are-zero %s | FileCheck 
--check-prefix=CHECK-DENORMS-ARE-ZERO %s
 // RUN: not %clang_cc1 -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck 
--check-prefix=CHECK-C99 %s
 // RUN: not %clang_cc1 -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck 
--check-prefix=CHECK-INVALID %s
@@ -33,6 +34,7 @@
 // CHECK-UNSAFE-MATH-OPT: .*clang.* "-cc1" .* "-cl-unsafe-math-optimizations"
 // CHECK-FAST-RELAXED-MATH: .*clang.* "-cc1" .* "-cl-fast-relaxed-math"
 // CHECK-MAD-ENABLE: .*clang.* "-cc1" .* "-cl-mad-enable"
+// CHECK-NO-SIGNED-ZEROS: .*clang.* "-cc1" .* "-cl-no-signed-zeros"
 // CHECK-DENORMS-ARE-ZERO: .*clang.* "-cc1" .* "-cl-denorms-are-zero"
 // CHECK-C99: error: invalid argument '-cl-std=c99' not allowed with 'OpenCL'
 // CHECK-INVALID: error: invalid value 'invalid' in '-cl-std=invalid'
Index: test/CodeGenOpenCL/no-signed-zeros.cl
===
--- test/CodeGenOpenCL/no-signed-zeros.cl
+++ test/CodeGenOpenCL/no-signed-zeros.cl
@@ -0,0 +1,10 @@
+// RUN: %clang_cc1 %s -emit-llvm -o - | FileCheck %s -check-prefix=NORMAL
+// RUN: %clang_cc1 %s -emit-llvm -cl-no-signed-zeros -o - | FileCheck %s 
-check-prefix=NO-SIGNED-ZEROS
+
+float signedzeros(float a) {
+  return a;
+}
+
+// CHECK: attributes
+// NORMAL: "no-signed-zeros-fp-math"="false"
+// NO-SIGNED-ZEROS: "no-signed-zeros-fp-math"="true"
Index: lib/Frontend/CompilerInvocation.cpp
===
--- lib/Frontend/CompilerInvocation.cpp
+++ lib/Frontend/CompilerInvocation.cpp
@@ -564,7 +564,8 @@
Args.hasArg(OPT_cl_unsafe_math_optimizations) ||
Args.hasArg(OPT_cl_finite_math_only) ||
Args.hasArg(OPT_cl_fast_relaxed_math));
-  Opts.NoSignedZeros = Args.hasArg(OPT_fno_signed_zeros);
+  Opts.NoSignedZeros = (Args.hasArg(OPT_fno_signed_zeros) ||
+Args.hasArg(OPT_cl_no_signed_zeros));
   Opts.ReciprocalMath = Args.hasArg(OPT_freciprocal_math);
   Opts.NoZeroInitializedInBSS = Args.hasArg(OPT_mno_zero_initialized_in_bss);
   Opts.BackendOptions = Args.getAllArgValues(OPT_backend_option);
Index: lib/Driver/Tools.cpp
===
--- lib/Driver/Tools.cpp
+++ lib/Driver/Tools.cpp
@@ -5139,6 +5139,9 @@
   if (Args.getLastArg(options::OPT_cl_mad_enable)) {
 CmdArgs.push_back("-cl-mad-enable");
   }
+  if (Args.getLastArg(options::OPT_cl_no_signed_zeros)) {
+CmdArgs.push_back("-cl-no-signed-zeros");
+  }
   if (Arg *A = Args.getLastArg(options::OPT_cl_std_EQ)) {
 std::string CLStdStr = "-cl-std=";
 CLStdStr += A->getValue();
Index: lib/CodeGen/CGCall.cpp
===
--- lib/CodeGen/CGCall.cpp
+++ lib/CodeGen/CGCall.cpp
@@ -1732,6 +1732,8 @@
llvm::toStringRef(CodeGenOpts.SoftFloat));
 FuncAttrs.addAttribute("stack-protector-buffer-size",
llvm::utostr(CodeGenOpts.SSPBufferSize));
+FuncAttrs.addAttribute("no-signed-zeros-fp-math",
+   llvm::toStringRef(CodeGenOpts.NoSignedZeros));
 
 if (CodeGenOpts.StackRealignment)
   FuncAttrs.addAttribute("stackrealign");
Index: include/clang/Driver/Options.td
===
--- include/clang/Driver/Options.td
+++ include/clang/Driver/Options.td
@@ -383,6 +383,8 @@
   HelpText<"OpenCL only. Sets -cl-finite-math-only and 
-cl-unsafe-math-optimizations, and defines __FAST_RELAXED_MATH__.">;
 def cl_mad_enable : Flag<["-"], "cl-mad-enable">, Group, 
Flags<[CC1Option]>,
   HelpText<"OpenCL only. Allow use of less precise MAD computations in the 
generated binary.">;
+def cl_no_signed_zeros : Flag<["-"], "cl-no-signed-zeros">, 
Group, Flags<[CC1Option]>,
+  HelpText<"OpenCL only.

[PATCH] D22067: [OpenCL] Add missing -cl-no-signed-zeros option into driver

2016-07-06 Thread Aaron En Ye Shi via cfe-commits 
ashi1 created this revision.
ashi1 added reviewers: Anastasia, jvesely.
ashi1 added subscribers: yaxunl, nhaustov, rsmith, bader, pxli168, cfe-commits.
ashi1 set the repository for this revision to rL LLVM.

Add OCL option -cl-no-signed-zeros to driver options.

Also added to opencl.cl testcases.

Repository:
  rL LLVM

http://reviews.llvm.org/D22067

Files:
  include/clang/Driver/Options.td
  lib/Driver/Tools.cpp
  test/Driver/opencl.cl

Index: test/Driver/opencl.cl
===
--- test/Driver/opencl.cl
+++ test/Driver/opencl.cl
@@ -14,6 +14,7 @@
 // RUN: %clang -S -### -cl-unsafe-math-optimizations %s | FileCheck 
--check-prefix=CHECK-UNSAFE-MATH-OPT %s
 // RUN: %clang -S -### -cl-fast-relaxed-math %s | FileCheck 
--check-prefix=CHECK-FAST-RELAXED-MATH %s
 // RUN: %clang -S -### -cl-mad-enable %s | FileCheck 
--check-prefix=CHECK-MAD-ENABLE %s
+// RUN: %clang -S -### -cl-no-signed-zeros %s | FileCheck 
--check-prefix=CHECK-NO-SIGNED-ZEROS %s
 // RUN: %clang -S -### -cl-denorms-are-zero %s | FileCheck 
--check-prefix=CHECK-DENORMS-ARE-ZERO %s
 // RUN: not %clang_cc1 -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck 
--check-prefix=CHECK-C99 %s
 // RUN: not %clang_cc1 -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck 
--check-prefix=CHECK-INVALID %s
@@ -33,6 +34,7 @@
 // CHECK-UNSAFE-MATH-OPT: .*clang.* "-cc1" .* "-cl-unsafe-math-optimizations"
 // CHECK-FAST-RELAXED-MATH: .*clang.* "-cc1" .* "-cl-fast-relaxed-math"
 // CHECK-MAD-ENABLE: .*clang.* "-cc1" .* "-cl-mad-enable"
+// CHECK-NO-SIGNED-ZEROS: .*clang.* "-cc1" .* "-cl-no-signed-zeros"
 // CHECK-DENORMS-ARE-ZERO: .*clang.* "-cc1" .* "-cl-denorms-are-zero"
 // CHECK-C99: error: invalid argument '-cl-std=c99' not allowed with 'OpenCL'
 // CHECK-INVALID: error: invalid value 'invalid' in '-cl-std=invalid'
Index: lib/Driver/Tools.cpp
===
--- lib/Driver/Tools.cpp
+++ lib/Driver/Tools.cpp
@@ -5139,6 +5139,9 @@
   if (Args.getLastArg(options::OPT_cl_mad_enable)) {
 CmdArgs.push_back("-cl-mad-enable");
   }
+  if (Args.getLastArg(options::OPT_cl_no_signed_zeros)) {
+CmdArgs.push_back("-cl-no-signed-zeros");
+  }
   if (Arg *A = Args.getLastArg(options::OPT_cl_std_EQ)) {
 std::string CLStdStr = "-cl-std=";
 CLStdStr += A->getValue();
Index: include/clang/Driver/Options.td
===
--- include/clang/Driver/Options.td
+++ include/clang/Driver/Options.td
@@ -383,6 +383,8 @@
   HelpText<"OpenCL only. Sets -cl-finite-math-only and 
-cl-unsafe-math-optimizations, and defines __FAST_RELAXED_MATH__.">;
 def cl_mad_enable : Flag<["-"], "cl-mad-enable">, Group, 
Flags<[CC1Option]>,
   HelpText<"OpenCL only. Allow use of less precise MAD computations in the 
generated binary.">;
+def cl_no_signed_zeros : Flag<["-"], "cl-no-signed-zeros">, 
Group, Flags<[CC1Option]>,
+  HelpText<"OpenCL only. Allow use of less precise no signed zeros 
computations in the generated binary.">;
 def cl_std_EQ : Joined<["-"], "cl-std=">, Group, 
Flags<[CC1Option]>,
   HelpText<"OpenCL language standard to compile for.">;
 def cl_denorms_are_zero : Flag<["-"], "cl-denorms-are-zero">, 
Group, Flags<[CC1Option]>,


Index: test/Driver/opencl.cl
===
--- test/Driver/opencl.cl
+++ test/Driver/opencl.cl
@@ -14,6 +14,7 @@
 // RUN: %clang -S -### -cl-unsafe-math-optimizations %s | FileCheck --check-prefix=CHECK-UNSAFE-MATH-OPT %s
 // RUN: %clang -S -### -cl-fast-relaxed-math %s | FileCheck --check-prefix=CHECK-FAST-RELAXED-MATH %s
 // RUN: %clang -S -### -cl-mad-enable %s | FileCheck --check-prefix=CHECK-MAD-ENABLE %s
+// RUN: %clang -S -### -cl-no-signed-zeros %s | FileCheck --check-prefix=CHECK-NO-SIGNED-ZEROS %s
 // RUN: %clang -S -### -cl-denorms-are-zero %s | FileCheck --check-prefix=CHECK-DENORMS-ARE-ZERO %s
 // RUN: not %clang_cc1 -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
 // RUN: not %clang_cc1 -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
@@ -33,6 +34,7 @@
 // CHECK-UNSAFE-MATH-OPT: .*clang.* "-cc1" .* "-cl-unsafe-math-optimizations"
 // CHECK-FAST-RELAXED-MATH: .*clang.* "-cc1" .* "-cl-fast-relaxed-math"
 // CHECK-MAD-ENABLE: .*clang.* "-cc1" .* "-cl-mad-enable"
+// CHECK-NO-SIGNED-ZEROS: .*clang.* "-cc1" .* "-cl-no-signed-zeros"
 // CHECK-DENORMS-ARE-ZERO: .*clang.* "-cc1" .* "-cl-denorms-are-zero"
 // CHECK-C99: error: invalid argument '-cl-std=c99' not allowed with 'OpenCL'
 // CHECK-INVALID: error: invalid value 'invalid' in '-cl-std=invalid'
Index: lib/Driver/Tools.cpp
===
--- lib/Driver/Tools.cpp
+++ lib/Driver/Tools.cpp
@@ -5139,6 +5139,9 @@
   if (Args.getLastArg(options::OPT_cl_mad_enable)) {
 CmdArgs.push_back("-cl-mad-enable");
   }
+  if (Args.getLastArg(options::OPT_cl_no_signed_zeros)) {
+

Re: [PATCH] D21031: [OpenCL] Allow -cl-std and other standard -cl- options in driver

2016-06-22 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 61574.
ashi1 marked 4 inline comments as done.
ashi1 added a comment.

Revised to Anastasia's comments.


http://reviews.llvm.org/D21031

Files:
  include/clang/Basic/DiagnosticFrontendKinds.td
  include/clang/Driver/CC1Options.td
  include/clang/Driver/Options.td
  lib/Driver/Tools.cpp
  lib/Frontend/CompilerInvocation.cpp
  test/Driver/opencl.cl

Index: test/Driver/opencl.cl
===
--- test/Driver/opencl.cl
+++ test/Driver/opencl.cl
@@ -1,15 +1,39 @@
-// RUN: %clang -fsyntax-only %s
-// RUN: %clang -fsyntax-only -std=cl %s
-// RUN: %clang -fsyntax-only -std=cl1.1 %s
-// RUN: %clang -fsyntax-only -std=cl1.2 %s
-// RUN: %clang -fsyntax-only -std=cl2.0 %s
-// RUN: %clang -fsyntax-only -std=CL %s
-// RUN: %clang -fsyntax-only -std=CL1.1 %s
-// RUN: %clang -fsyntax-only -std=CL1.2 %s
-// RUN: %clang -fsyntax-only -std=CL2.0 %s
-// RUN: not %clang_cc1 -std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
-// RUN: not %clang_cc1 -std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
-// CHECK-C99: error: invalid argument '-std=c99' not allowed with 'OpenCL'
-// CHECK-INVALID: error: invalid value 'invalid' in '-std=invalid'
+// RUN: %clang -S -### -cl-std=CL %s | FileCheck --check-prefix=CHECK-CL %s
+// RUN: %clang -S -### -cl-std=CL1.1 %s | FileCheck --check-prefix=CHECK-CL11 %s
+// RUN: %clang -S -### -cl-std=CL1.2 %s | FileCheck --check-prefix=CHECK-CL12 %s
+// RUN: %clang -S -### -cl-std=CL2.0 %s | FileCheck --check-prefix=CHECK-CL20 %s
+// RUN: %clang -S -### -cl-opt-disable %s | FileCheck --check-prefix=CHECK-OPT-DISABLE %s
+// RUN: %clang -S -### -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-STRICT-ALIASING %s
+// RUN: %clang -S -### -cl-std=CL1.1 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION11 %s
+// RUN: %clang -S -### -cl-std=CL1.2 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION12 %s
+// RUN: %clang -S -### -cl-std=CL2.0 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION20 %s
+// RUN: %clang -S -### -cl-single-precision-constant %s | FileCheck --check-prefix=CHECK-SINGLE-PRECISION-CONST %s
+// RUN: %clang -S -### -cl-finite-math-only %s | FileCheck --check-prefix=CHECK-FINITE-MATH-ONLY %s
+// RUN: %clang -S -### -cl-kernel-arg-info %s | FileCheck --check-prefix=CHECK-KERNEL-ARG-INFO %s
+// RUN: %clang -S -### -cl-unsafe-math-optimizations %s | FileCheck --check-prefix=CHECK-UNSAFE-MATH-OPT %s
+// RUN: %clang -S -### -cl-fast-relaxed-math %s | FileCheck --check-prefix=CHECK-FAST-RELAXED-MATH %s
+// RUN: %clang -S -### -cl-mad-enable %s | FileCheck --check-prefix=CHECK-MAD-ENABLE %s
+// RUN: %clang -S -### -cl-denorms-are-zero %s | FileCheck --check-prefix=CHECK-DENORMS-ARE-ZERO %s
+// RUN: not %clang_cc1 -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
+// RUN: not %clang_cc1 -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
 
+// CHECK-CL: .*clang.* "-cc1" .* "-cl-std=CL"
+// CHECK-CL11: .*clang.* "-cc1" .* "-cl-std=CL1.1"
+// CHECK-CL12: .*clang.* "-cc1" .* "-cl-std=CL1.2"
+// CHECK-CL20: .*clang.* "-cc1" .* "-cl-std=CL2.0"
+// CHECK-OPT-DISABLE: .*clang.* "-cc1" .* "-cl-opt-disable"
+// CHECK-STRICT-ALIASING: .*clang.* "-cc1" .* "-cl-strict-aliasing"
+// CHECK-INVALID-OPENCL-VERSION11: OpenCL version 1.1 does not support the option 'cl-strict-aliasing'
+// CHECK-INVALID-OPENCL-VERSION12: OpenCL version 1.2 does not support the option 'cl-strict-aliasing'
+// CHECK-INVALID-OPENCL-VERSION20: OpenCL version 2.0 does not support the option 'cl-strict-aliasing'
+// CHECK-SINGLE-PRECISION-CONST: .*clang.* "-cc1" .* "-cl-single-precision-constant"
+// CHECK-FINITE-MATH-ONLY: .*clang.* "-cc1" .* "-cl-finite-math-only"
+// CHECK-KERNEL-ARG-INFO: .*clang.* "-cc1" .* "-cl-kernel-arg-info"
+// CHECK-UNSAFE-MATH-OPT: .*clang.* "-cc1" .* "-cl-unsafe-math-optimizations"
+// CHECK-FAST-RELAXED-MATH: .*clang.* "-cc1" .* "-cl-fast-relaxed-math"
+// CHECK-MAD-ENABLE: .*clang.* "-cc1" .* "-cl-mad-enable"
+// CHECK-DENORMS-ARE-ZERO: .*clang.* "-cc1" .* "-cl-denorms-are-zero"
+// CHECK-C99: error: invalid argument '-cl-std=c99' not allowed with 'OpenCL'
+// CHECK-INVALID: error: invalid value 'invalid' in '-cl-std=invalid'
+
 kernel void func(void);
Index: lib/Frontend/CompilerInvocation.cpp
===
--- lib/Frontend/CompilerInvocation.cpp
+++ lib/Frontend/CompilerInvocation.cpp
@@ -41,6 +41,7 @@
 #include "llvm/Support/Path.h"
 #include "llvm/Support/Process.h"
 #include "llvm/Target/TargetOptions.h"
+#include "llvm/Support/ScopedPrinter.h"
 #include 
 #include 
 #include 
@@ -1666,6 +1667,18 @@
   LangStd = OpenCLLangStd;
   }
 
+  // -cl-strict-aliasing needs to emit diagnostic in the case where CL > 1.0.
+  // This option should be deprecated for CL > 1.0 because
+  // this option

Re: [PATCH] D21031: [OpenCL] Allow -cl-std and other standard -cl- options in driver

2016-06-21 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 61423.
ashi1 marked 2 inline comments as done.
ashi1 added a comment.

Revised based on Anastasia's comments. Also clang-test run passes, the 
testcases should be working correctly.


http://reviews.llvm.org/D21031

Files:
  include/clang/Basic/DiagnosticFrontendKinds.td
  include/clang/Driver/CC1Options.td
  include/clang/Driver/Options.td
  lib/Driver/Tools.cpp
  lib/Frontend/CompilerInvocation.cpp
  test/Driver/opencl.cl

Index: test/Driver/opencl.cl
===
--- test/Driver/opencl.cl
+++ test/Driver/opencl.cl
@@ -1,15 +1,39 @@
-// RUN: %clang -fsyntax-only %s
-// RUN: %clang -fsyntax-only -std=cl %s
-// RUN: %clang -fsyntax-only -std=cl1.1 %s
-// RUN: %clang -fsyntax-only -std=cl1.2 %s
-// RUN: %clang -fsyntax-only -std=cl2.0 %s
-// RUN: %clang -fsyntax-only -std=CL %s
-// RUN: %clang -fsyntax-only -std=CL1.1 %s
-// RUN: %clang -fsyntax-only -std=CL1.2 %s
-// RUN: %clang -fsyntax-only -std=CL2.0 %s
-// RUN: not %clang_cc1 -std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
-// RUN: not %clang_cc1 -std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
-// CHECK-C99: error: invalid argument '-std=c99' not allowed with 'OpenCL'
-// CHECK-INVALID: error: invalid value 'invalid' in '-std=invalid'
+// RUN: %clang -S -### %s
+// RUN: %clang -S -### -cl-std=CL %s | FileCheck --check-prefix=CHECK-CL %s
+// RUN: %clang -S -### -cl-std=CL1.1 %s | FileCheck --check-prefix=CHECK-CL11 %s
+// RUN: %clang -S -### -cl-std=CL1.2 %s | FileCheck --check-prefix=CHECK-CL12 %s
+// RUN: %clang -S -### -cl-std=CL2.0 %s | FileCheck --check-prefix=CHECK-CL20 %s
+// RUN: %clang -S -### -cl-opt-disable %s | FileCheck --check-prefix=CHECK-OPT-DISABLE %s
+// RUN: %clang -S -### -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-STRICT-ALIASING %s
+// RUN: %clang -S -### -cl-std=CL1.1 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION11 %s
+// RUN: %clang -S -### -cl-std=CL1.2 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION12 %s
+// RUN: %clang -S -### -cl-std=CL2.0 -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-INVALID-OPENCL-VERSION20 %s
+// RUN: %clang -S -### -cl-single-precision-constant %s | FileCheck --check-prefix=CHECK-SINGLE-PRECISION-CONST %s
+// RUN: %clang -S -### -cl-finite-math-only %s | FileCheck --check-prefix=CHECK-FINITE-MATH-ONLY %s
+// RUN: %clang -S -### -cl-kernel-arg-info %s | FileCheck --check-prefix=CHECK-KERNEL-ARG-INFO %s
+// RUN: %clang -S -### -cl-unsafe-math-optimizations %s | FileCheck --check-prefix=CHECK-UNSAFE-MATH-OPT %s
+// RUN: %clang -S -### -cl-fast-relaxed-math %s | FileCheck --check-prefix=CHECK-FAST-RELAXED-MATH %s
+// RUN: %clang -S -### -cl-mad-enable %s | FileCheck --check-prefix=CHECK-MAD-ENABLE %s
+// RUN: %clang -S -### -cl-denorms-are-zero %s | FileCheck --check-prefix=CHECK-DENORMS-ARE-ZERO %s
+// RUN: not %clang_cc1 -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
+// RUN: not %clang_cc1 -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
+// CHECK-C99: error: invalid argument '-cl-std=c99' not allowed with 'OpenCL'
+// CHECK-INVALID: error: invalid value 'invalid' in '-cl-std=invalid'
+// CHECK-INVALID-OPENCL-VERSION11: OpenCL version 1.1 does not support the option 'cl-strict-aliasing'
+// CHECK-INVALID-OPENCL-VERSION12: OpenCL version 1.2 does not support the option 'cl-strict-aliasing'
+// CHECK-INVALID-OPENCL-VERSION20: OpenCL version 2.0 does not support the option 'cl-strict-aliasing'
+// CHECK-CL: .*clang.* "-cc1" .* "-cl-std=CL"
+// CHECK-CL11: .*clang.* "-cc1" .* "-cl-std=CL1.1"
+// CHECK-CL12: .*clang.* "-cc1" .* "-cl-std=CL1.2"
+// CHECK-CL20: .*clang.* "-cc1" .* "-cl-std=CL2.0"
+// CHECK-OPT-DISABLE: .*clang.* "-cc1" .* "-cl-opt-disable"
+// CHECK-STRICT-ALIASING: .*clang.* "-cc1" .* "-cl-strict-aliasing"
+// CHECK-SINGLE-PRECISION-CONST: .*clang.* "-cc1" .* "-cl-single-precision-constant"
+// CHECK-FINITE-MATH-ONLY: .*clang.* "-cc1" .* "-cl-finite-math-only"
+// CHECK-KERNEL-ARG-INFO: .*clang.* "-cc1" .* "-cl-kernel-arg-info"
+// CHECK-UNSAFE-MATH-OPT: .*clang.* "-cc1" .* "-cl-unsafe-math-optimizations"
+// CHECK-FAST-RELAXED-MATH: .*clang.* "-cc1" .* "-cl-fast-relaxed-math"
+// CHECK-MAD-ENABLE: .*clang.* "-cc1" .* "-cl-mad-enable"
+// CHECK-DENORMS-ARE-ZERO: .*clang.* "-cc1" .* "-cl-denorms-are-zero"
 
 kernel void func(void);
Index: lib/Frontend/CompilerInvocation.cpp
===
--- lib/Frontend/CompilerInvocation.cpp
+++ lib/Frontend/CompilerInvocation.cpp
@@ -41,6 +41,7 @@
 #include "llvm/Support/Path.h"
 #include "llvm/Support/Process.h"
 #include "llvm/Target/TargetOptions.h"
+#include "llvm/Support/ScopedPrinter.h"
 #include 
 #include 
 #include 
@@ -1666,6 +1667,19 @@
   LangStd = OpenCLLangStd;
   }
 
+  // -cl-strict-aliasing needs to emit diagnostic in

Re: [PATCH] D21031: [OpenCL] Allow -cl-std and other standard -cl- options in driver

2016-06-20 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 61275.
ashi1 marked 2 inline comments as done.
ashi1 added a comment.

Revised with Anastasia's comments. Please take a look at the diagnostic to see 
if it is what we want.


http://reviews.llvm.org/D21031

Files:
  include/clang/Basic/DiagnosticFrontendKinds.td
  include/clang/Driver/CC1Options.td
  include/clang/Driver/Options.td
  lib/Driver/Tools.cpp
  lib/Frontend/CompilerInvocation.cpp
  test/Driver/opencl.cl

Index: test/Driver/opencl.cl
===
--- test/Driver/opencl.cl
+++ test/Driver/opencl.cl
@@ -1,15 +1,33 @@
-// RUN: %clang -fsyntax-only %s
-// RUN: %clang -fsyntax-only -std=cl %s
-// RUN: %clang -fsyntax-only -std=cl1.1 %s
-// RUN: %clang -fsyntax-only -std=cl1.2 %s
-// RUN: %clang -fsyntax-only -std=cl2.0 %s
-// RUN: %clang -fsyntax-only -std=CL %s
-// RUN: %clang -fsyntax-only -std=CL1.1 %s
-// RUN: %clang -fsyntax-only -std=CL1.2 %s
-// RUN: %clang -fsyntax-only -std=CL2.0 %s
-// RUN: not %clang_cc1 -std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
-// RUN: not %clang_cc1 -std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
-// CHECK-C99: error: invalid argument '-std=c99' not allowed with 'OpenCL'
-// CHECK-INVALID: error: invalid value 'invalid' in '-std=invalid'
+// RUN: %clang -S -### %s
+// RUN: %clang -S -### -cl-std=CL %s | FileCheck --check-prefix=CHECK-CL %s
+// RUN: %clang -S -### -cl-std=CL1.1 %s | FileCheck --check-prefix=CHECK-CL11 %s
+// RUN: %clang -S -### -cl-std=CL1.2 %s | FileCheck --check-prefix=CHECK-CL12 %s
+// RUN: %clang -S -### -cl-std=CL2.0 %s | FileCheck --check-prefix=CHECK-CL20 %s
+// RUN: %clang -S -### -cl-opt-disable %s | FileCheck --check-prefix=CHECK-OPT-DISABLE %s
+// RUN: %clang -S -### -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-STRICT-ALIASING %s
+// RUN: %clang -S -### -cl-single-precision-constant %s | FileCheck --check-prefix=CHECK-SINGLE-PRECISION-CONST %s
+// RUN: %clang -S -### -cl-finite-math-only %s | FileCheck --check-prefix=CHECK-FINITE-MATH-ONLY %s
+// RUN: %clang -S -### -cl-kernel-arg-info %s | FileCheck --check-prefix=CHECK-KERNEL-ARG-INFO %s
+// RUN: %clang -S -### -cl-unsafe-math-optimizations %s | FileCheck --check-prefix=CHECK-UNSAFE-MATH-OPT %s
+// RUN: %clang -S -### -cl-fast-relaxed-math %s | FileCheck --check-prefix=CHECK-FAST-RELAXED-MATH %s
+// RUN: %clang -S -### -cl-mad-enable %s | FileCheck --check-prefix=CHECK-MAD-ENABLE %s
+// RUN: %clang -S -### -cl-denorms-are-zero %s | FileCheck --check-prefix=CHECK-DENORMS-ARE-ZERO %s
+// RUN: not %clang_cc1 -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
+// RUN: not %clang_cc1 -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
+// CHECK-C99: error: invalid argument '-cl-std=c99' not allowed with 'OpenCL'
+// CHECK-INVALID: error: invalid value 'invalid' in '-cl-std=invalid'
+// CHECK-CL: .*clang.* "-cc1" .* "-cl-std=CL"
+// CHECK-CL11: .*clang.* "-cc1" .* "-cl-std=CL1.1"
+// CHECK-CL12: .*clang.* "-cc1" .* "-cl-std=CL1.2"
+// CHECK-CL20: .*clang.* "-cc1" .* "-cl-std=CL2.0"
+// CHECK-OPT-DISABLE: .*clang.* "-cc1" .* "-cl-opt-disable"
+// CHECK-STRICT-ALIASING: .*clang.* "-cc1" .* "-cl-strict-aliasing"
+// CHECK-SINGLE-PRECISION-CONST: .*clang.* "-cc1" .* "-cl-single-precision-constant"
+// CHECK-FINITE-MATH-ONLY: .*clang.* "-cc1" .* "-cl-finite-math-only"
+// CHECK-KERNEL-ARG-INFO: .*clang.* "-cc1" .* "-cl-kernel-arg-info"
+// CHECK-UNSAFE-MATH-OPT: .*clang.* "-cc1" .* "-cl-unsafe-math-optimizations"
+// CHECK-FAST-RELAXED-MATH: .*clang.* "-cc1" .* "-cl-fast-relaxed-math"
+// CHECK-MAD-ENABLE: .*clang.* "-cc1" .* "-cl-mad-enable"
+// CHECK-DENORMS-ARE-ZERO: .*clang.* "-cc1" .* "-cl-denorms-are-zero"
 
 kernel void func(void);
Index: lib/Frontend/CompilerInvocation.cpp
===
--- lib/Frontend/CompilerInvocation.cpp
+++ lib/Frontend/CompilerInvocation.cpp
@@ -1660,6 +1660,15 @@
   LangStd = OpenCLLangStd;
   }
 
+  // -cl-strict-aliasing needs to emit diagnostic in the case where CL > 1.0.
+  // This option should be deprecated for CL > 1.0 because
+  // this option was added for compatibility with OpenCL 1.0.
+  if (const Arg *A = Args.getLastArg(OPT_cl_strict_aliasing)) {
+if(Opts.OpenCLVersion > 100)
+  Diags.Report(diag::warn_option_depre_ocl_version) 
+  << A->getArgString(Args);
+  }
+
   llvm::Triple T(TargetOpts.Triple);
   CompilerInvocation::setLangDefaults(Opts, IK, T, LangStd);
 
Index: lib/Driver/Tools.cpp
===
--- lib/Driver/Tools.cpp
+++ lib/Driver/Tools.cpp
@@ -5109,6 +5109,40 @@
 CmdArgs.push_back("-arm-restrict-it");
   }
 
+  // Forward -cl options to -cc1
+  if (Arg *A = Args.getLastArg(options::OPT_cl_opt_disable)) {
+CmdArgs.push_back("-cl-opt-disable");
+  }
+  if (Arg *A = Args.getLastArg(options::OPT_cl_strict_aliasing)) {
+

Re: [PATCH] D21031: [OpenCL] Allow -cl-std and other standard -cl- options in driver

2016-06-20 Thread Aaron En Ye Shi via cfe-commits 
ashi1 marked 6 inline comments as done.
ashi1 added a comment.

F2085685: D21031.patch 



Comment at: include/clang/Driver/CC1Options.td:670
@@ -669,21 +669,3 @@
 
-def cl_opt_disable : Flag<["-"], "cl-opt-disable">,
-  HelpText<"OpenCL only. This option disables all optimizations. The default 
is optimizations are enabled.">;
-def cl_strict_aliasing : Flag<["-"], "cl-strict-aliasing">,
-  HelpText<"OpenCL only. This option does nothing and is for compatibility 
with OpenCL 1.0">;
-def cl_single_precision_constant : Flag<["-"], "cl-single-precision-constant">,
-  HelpText<"OpenCL only. Treat double precision floating-point constant as 
single precision constant.">;
-def cl_finite_math_only : Flag<["-"], "cl-finite-math-only">,
-  HelpText<"OpenCL only. Allow floating-point optimizations that assume 
arguments and results are not NaNs or +-Inf.">;
-def cl_kernel_arg_info : Flag<["-"], "cl-kernel-arg-info">,
-  HelpText<"OpenCL only. Generate kernel argument metadata.">;
-def cl_unsafe_math_optimizations : Flag<["-"], "cl-unsafe-math-optimizations">,
-  HelpText<"OpenCL only. Allow unsafe floating-point optimizations.  Also 
implies -cl-no-signed-zeros and -cl-mad-enable">;
-def cl_fast_relaxed_math : Flag<["-"], "cl-fast-relaxed-math">,
-  HelpText<"OpenCL only. Sets -cl-finite-math-only and 
-cl-unsafe-math-optimizations, and defines __FAST_RELAXED_MATH__">;
-def cl_mad_enable : Flag<["-"], "cl-mad-enable">,
-  HelpText<"OpenCL only. Enable less precise MAD instructions to be 
generated.">;
-def cl_std_EQ : Joined<["-"], "cl-std=">,
-  HelpText<"OpenCL language standard to compile for">;
-def cl_denorms_are_zero : Flag<["-"], "cl-denorms-are-zero">,
-  HelpText<"OpenCL only. Allow denormals to be flushed to zero">;
+//def cl_opt_disable : Flag<["-"], "cl-opt-disable">,
+//  HelpText<"OpenCL only. This option disables all optimizations. The default 
is optimizations are enabled.">;

Anastasia wrote:
> Is this code below to be removed?
Yes, I removed the code from CC1Options.td and added replacement in Options.td


Comment at: include/clang/Driver/CC1Options.td:673
@@ +672,3 @@
+//def cl_strict_aliasing : Flag<["-"], "cl-strict-aliasing">,
+//  HelpText<"OpenCL only. This option does nothing and is for compatibility 
with OpenCL 1.0">;
+//def cl_single_precision_constant : Flag<["-"], 
"cl-single-precision-constant">,

Anastasia wrote:
> This option does nothing and is for compatibility with OpenCL 1.0 -> This 
> option is added for compatibility with OpenCL 1.0.
>  finish with .
> 
> Btw, ideally this option should be deprivcated for CL > 1.0. Could we give 
> diagnostic in this case?
I've added a diagnostic. Can you take a look?


http://reviews.llvm.org/D21031



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D21031: [OpenCL] Allow -cl-std and other standard -cl- options in driver

2016-06-06 Thread Aaron En Ye Shi via cfe-commits 
ashi1 created this revision.
ashi1 added a reviewer: Anastasia.
ashi1 added subscribers: yaxunl, cfe-commits, pxli168, bader, rsmith, nhaustov.

Allow -cl-std and other standard -cl- options from cc1 to driver.

Added a test for the options moved.

http://reviews.llvm.org/D21031

Files:
  include/clang/Driver/CC1Options.td
  include/clang/Driver/Options.td
  lib/Driver/Tools.cpp
  test/Driver/opencl.cl

Index: test/Driver/opencl.cl
===
--- /dev/null
+++ test/Driver/opencl.cl
@@ -0,0 +1,33 @@
+// RUN: %clang -S -### %s
+// RUN: %clang -S -### -cl-std=CL %s | FileCheck --check-prefix=CHECK-CL %s
+// RUN: %clang -S -### -cl-std=CL1.1 %s | FileCheck --check-prefix=CHECK-CL11 %s
+// RUN: %clang -S -### -cl-std=CL1.2 %s | FileCheck --check-prefix=CHECK-CL12 %s
+// RUN: %clang -S -### -cl-std=CL2.0 %s | FileCheck --check-prefix=CHECK-CL20 %s
+// RUN: %clang -S -### -cl-opt-disable %s | FileCheck --check-prefix=CHECK-OPT-DISABLE %s
+// RUN: %clang -S -### -cl-strict-aliasing %s | FileCheck --check-prefix=CHECK-STRICT-ALIASING %s
+// RUN: %clang -S -### -cl-single-precision-constant %s | FileCheck --check-prefix=CHECK-SINGLE-PRECISION-CONST %s
+// RUN: %clang -S -### -cl-finite-math-only %s | FileCheck --check-prefix=CHECK-FINITE-MATH-ONLY %s
+// RUN: %clang -S -### -cl-kernel-arg-info %s | FileCheck --check-prefix=CHECK-KERNEL-ARG-INFO %s
+// RUN: %clang -S -### -cl-unsafe-math-optimizations %s | FileCheck --check-prefix=CHECK-UNSAFE-MATH-OPT %s
+// RUN: %clang -S -### -cl-fast-relaxed-math %s | FileCheck --check-prefix=CHECK-FAST-RELAXED-MATH %s
+// RUN: %clang -S -### -cl-mad-enable %s | FileCheck --check-prefix=CHECK-MAD-ENABLE %s
+// RUN: %clang -S -### -cl-denorms-are-zero %s | FileCheck --check-prefix=CHECK-DENORMS-ARE-ZERO %s
+// RUN: not %clang_cc1 -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
+// RUN: not %clang_cc1 -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
+// CHECK-C99: error: invalid argument '-cl-std=c99' not allowed with 'OpenCL'
+// CHECK-INVALID: error: invalid value 'invalid' in '-cl-std=invalid'
+// CHECK-CL: .*clang.* "-cc1" .* "-cl-std=CL"
+// CHECK-CL11: .*clang.* "-cc1" .* "-cl-std=CL1.1"
+// CHECK-CL12: .*clang.* "-cc1" .* "-cl-std=CL1.2"
+// CHECK-CL20: .*clang.* "-cc1" .* "-cl-std=CL2.0"
+// CHECK-OPT-DISABLE: .*clang.* "-cc1" .* "-cl-opt-disable"
+// CHECK-STRICT-ALIASING: .*clang.* "-cc1" .* "-cl-strict-aliasing"
+// CHECK-SINGLE-PRECISION-CONST: .*clang.* "-cc1" .* "-cl-single-precision-constant"
+// CHECK-FINITE-MATH-ONLY: .*clang.* "-cc1" .* "-cl-finite-math-only"
+// CHECK-KERNEL-ARG-INFO: .*clang.* "-cc1" .* "-cl-kernel-arg-info"
+// CHECK-UNSAFE-MATH-OPT: .*clang.* "-cc1" .* "-cl-unsafe-math-optimizations"
+// CHECK-FAST-RELAXED-MATH: .*clang.* "-cc1" .* "-cl-fast-relaxed-math"
+// CHECK-MAD-ENABLE: .*clang.* "-cc1" .* "-cl-mad-enable"
+// CHECK-DENORMS-ARE-ZERO: .*clang.* "-cc1" .* "-cl-denorms-are-zero"
+
+kernel void func(void);
\ No newline at end of file
Index: lib/Driver/Tools.cpp
===
--- lib/Driver/Tools.cpp
+++ lib/Driver/Tools.cpp
@@ -5065,6 +5065,40 @@
 CmdArgs.push_back("-arm-restrict-it");
   }
 
+  // Forward -cl options to -cc1
+  if (Arg *A = Args.getLastArg(options::OPT_cl_opt_disable)) {
+CmdArgs.push_back("-cl-opt-disable");
+  }
+  if (Arg *A = Args.getLastArg(options::OPT_cl_strict_aliasing)) {
+CmdArgs.push_back("-cl-strict-aliasing");
+  }
+  if (Arg *A = Args.getLastArg(options::OPT_cl_single_precision_constant)) {
+CmdArgs.push_back("-cl-single-precision-constant");
+  }
+  if (Arg *A = Args.getLastArg(options::OPT_cl_finite_math_only)) {
+CmdArgs.push_back("-cl-finite-math-only");
+  }
+  if (Arg *A = Args.getLastArg(options::OPT_cl_kernel_arg_info)) {
+CmdArgs.push_back("-cl-kernel-arg-info");
+  }
+  if (Arg *A = Args.getLastArg(options::OPT_cl_unsafe_math_optimizations)) {
+CmdArgs.push_back("-cl-unsafe-math-optimizations");
+  }
+  if (Arg *A = Args.getLastArg(options::OPT_cl_fast_relaxed_math)) {
+CmdArgs.push_back("-cl-fast-relaxed-math");
+  }
+  if (Arg *A = Args.getLastArg(options::OPT_cl_mad_enable)) {
+CmdArgs.push_back("-cl-mad-enable");
+  }
+  if (Arg *A = Args.getLastArg(options::OPT_cl_std_EQ)) {
+std::string CLStdStr = "-cl-std=";
+CLStdStr += A->getValue();
+CmdArgs.push_back(Args.MakeArgString(CLStdStr));
+  }
+  if (Arg *A = Args.getLastArg(options::OPT_cl_denorms_are_zero)) {
+CmdArgs.push_back("-cl-denorms-are-zero");
+  }
+
   // Forward -f options with positive and negative forms; we translate
   // these by hand.
   if (Arg *A = Args.getLastArg(options::OPT_fprofile_sample_use_EQ)) {
Index: include/clang/Driver/Options.td
===
--- include/clang/Driver/Options.td
+++ include/clang/Driver/Options.td
@@ -78,6 +78,7 @@
 def i_Group

Re: [PATCH] D17578: [OpenCL]Allowing explicit conversion of "0" to event_t type

2016-05-17 Thread Aaron En Ye Shi via cfe-commits 
ashi1 added a comment.

Xiuli, are you OK with this patch?


http://reviews.llvm.org/D17578



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Re: [PATCH] D17578: [OpenCL]Allowing explicit conversion of "0" to event_t type

2016-05-10 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 56615.
ashi1 added a comment.

Modified the testcase. Tested this diff on clang-test and it passes.


http://reviews.llvm.org/D17578

Files:
  include/clang/Basic/DiagnosticSemaKinds.td
  lib/Sema/SemaCast.cpp
  test/CodeGenOpenCL/event_t.cl
  test/SemaOpenCL/event_t.cl

Index: test/SemaOpenCL/event_t.cl
===
--- test/SemaOpenCL/event_t.cl
+++ test/SemaOpenCL/event_t.cl
@@ -14,5 +14,6 @@
   foo(e);
   foo(0);
   foo(5); // expected-error {{passing 'int' to parameter of incompatible type 
'event_t'}}
+  foo((event_t)1); // expected-error {{cannot cast non-zero value '1' to 
'event_t'}}
 }
 
Index: test/CodeGenOpenCL/event_t.cl
===
--- test/CodeGenOpenCL/event_t.cl
+++ test/CodeGenOpenCL/event_t.cl
@@ -9,4 +9,6 @@
 // CHECK: call {{.*}}void @foo(%opencl.event_t* %
   foo(0);
 // CHECK: call {{.*}}void @foo(%opencl.event_t* null)
+  foo((event_t)0);
+// CHECK: call {{.*}}void @foo(%opencl.event_t* null)
 }
Index: lib/Sema/SemaCast.cpp
===
--- lib/Sema/SemaCast.cpp
+++ lib/Sema/SemaCast.cpp
@@ -2347,6 +2347,22 @@
   return;
 }
 
+// OpenCL v2.0 s6.13.10 - Allow casts from '0' to event_t type.
+if (Self.getLangOpts().OpenCL && DestType->isEventT()) {
+  llvm::APSInt CastInt;
+  if (SrcExpr.get()->EvaluateAsInt(CastInt, Self.Context)) {
+if (0 == CastInt) {
+  Kind = CK_ZeroToOCLEvent;
+  return;
+}
+Self.Diag(OpRange.getBegin(),
+  diag::error_opencl_cast_non_zero_to_event_t)
+  << CastInt.toString(10) << SrcExpr.get()->getSourceRange();
+SrcExpr = ExprError();
+return;
+  }
+}
+
 // Reject any other conversions to non-scalar types.
 Self.Diag(OpRange.getBegin(), diag::err_typecheck_cond_expect_scalar)
   << DestType << SrcExpr.get()->getSourceRange();
Index: include/clang/Basic/DiagnosticSemaKinds.td
===
--- include/clang/Basic/DiagnosticSemaKinds.td
+++ include/clang/Basic/DiagnosticSemaKinds.td
@@ -7800,6 +7800,8 @@
   "sampler_t variable required - got %0">;
 def err_wrong_sampler_addressspace: Error<
   "sampler type cannot be used with the __local and __global address space 
qualifiers">;
+def error_opencl_cast_non_zero_to_event_t : Error<
+  "cannot cast non-zero value '%0' to 'event_t'">;
 def err_opencl_global_invalid_addr_space : Error<
   "%select{program scope|static local|extern}0 variable must reside in %1 
address space">;
 def err_missing_actual_pipe_type : Error<


Index: test/SemaOpenCL/event_t.cl
===
--- test/SemaOpenCL/event_t.cl
+++ test/SemaOpenCL/event_t.cl
@@ -14,5 +14,6 @@
   foo(e);
   foo(0);
   foo(5); // expected-error {{passing 'int' to parameter of incompatible type 'event_t'}}
+  foo((event_t)1); // expected-error {{cannot cast non-zero value '1' to 'event_t'}}
 }
 
Index: test/CodeGenOpenCL/event_t.cl
===
--- test/CodeGenOpenCL/event_t.cl
+++ test/CodeGenOpenCL/event_t.cl
@@ -9,4 +9,6 @@
 // CHECK: call {{.*}}void @foo(%opencl.event_t* %
   foo(0);
 // CHECK: call {{.*}}void @foo(%opencl.event_t* null)
+  foo((event_t)0);
+// CHECK: call {{.*}}void @foo(%opencl.event_t* null)
 }
Index: lib/Sema/SemaCast.cpp
===
--- lib/Sema/SemaCast.cpp
+++ lib/Sema/SemaCast.cpp
@@ -2347,6 +2347,22 @@
   return;
 }
 
+// OpenCL v2.0 s6.13.10 - Allow casts from '0' to event_t type.
+if (Self.getLangOpts().OpenCL && DestType->isEventT()) {
+  llvm::APSInt CastInt;
+  if (SrcExpr.get()->EvaluateAsInt(CastInt, Self.Context)) {
+if (0 == CastInt) {
+  Kind = CK_ZeroToOCLEvent;
+  return;
+}
+Self.Diag(OpRange.getBegin(),
+  diag::error_opencl_cast_non_zero_to_event_t)
+  << CastInt.toString(10) << SrcExpr.get()->getSourceRange();
+SrcExpr = ExprError();
+return;
+  }
+}
+
 // Reject any other conversions to non-scalar types.
 Self.Diag(OpRange.getBegin(), diag::err_typecheck_cond_expect_scalar)
   << DestType << SrcExpr.get()->getSourceRange();
Index: include/clang/Basic/DiagnosticSemaKinds.td
===
--- include/clang/Basic/DiagnosticSemaKinds.td
+++ include/clang/Basic/DiagnosticSemaKinds.td
@@ -7800,6 +7800,8 @@
   "sampler_t variable required - got %0">;
 def err_wrong_sampler_addressspace: Error<
   "sampler type cannot be used with the __local and __global address space qualifiers">;
+def error_opencl_cast_non_zero_to_event_t : Error<
+  "cannot cast non-zero value '%0' to 'event_t'">;
 def

Re: [PATCH] D17578: [OpenCL]Allowing explicit conversion of "0" to event_t type

2016-05-10 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 56599.
ashi1 added a comment.

Added changes for comments from majnemer.


http://reviews.llvm.org/D17578

Files:
  include/clang/Basic/DiagnosticSemaKinds.td
  lib/Sema/SemaCast.cpp
  test/CodeGenOpenCL/event_t.cl
  test/SemaOpenCL/event_t.cl

Index: test/SemaOpenCL/event_t.cl
===
--- test/SemaOpenCL/event_t.cl
+++ test/SemaOpenCL/event_t.cl
@@ -14,5 +14,6 @@
   foo(e);
   foo(0);
   foo(5); // expected-error {{passing 'int' to parameter of incompatible type 
'event_t'}}
+  foo((event_t)1); // expected-error {{cannot cast non-zero value 'int' to 
'event_t'}}
 }
 
Index: test/CodeGenOpenCL/event_t.cl
===
--- test/CodeGenOpenCL/event_t.cl
+++ test/CodeGenOpenCL/event_t.cl
@@ -9,4 +9,6 @@
 // CHECK: call {{.*}}void @foo(%opencl.event_t* %
   foo(0);
 // CHECK: call {{.*}}void @foo(%opencl.event_t* null)
+  foo((event_t)0);
+// CHECK: call {{.*}}void @foo(%opencl.event_t* null)
 }
Index: lib/Sema/SemaCast.cpp
===
--- lib/Sema/SemaCast.cpp
+++ lib/Sema/SemaCast.cpp
@@ -2347,6 +2347,22 @@
   return;
 }
 
+// OpenCL v2.0 s6.13.10 - Allow casts from '0' to event_t type.
+if (Self.getLangOpts().OpenCL && DestType->isEventT()) {
+  llvm::APSInt CastInt;
+  if (SrcExpr.get()->EvaluateAsInt(CastInt, Self.Context)) {
+if (0 == CastInt) {
+  Kind = CK_ZeroToOCLEvent;
+  return;
+}
+Self.Diag(OpRange.getBegin(),
+  diag::error_opencl_cast_non_zero_to_event_t)
+  << CastInt.toString(10) << SrcExpr.get()->getSourceRange();
+SrcExpr = ExprError();
+return;
+  }
+}
+
 // Reject any other conversions to non-scalar types.
 Self.Diag(OpRange.getBegin(), diag::err_typecheck_cond_expect_scalar)
   << DestType << SrcExpr.get()->getSourceRange();
Index: include/clang/Basic/DiagnosticSemaKinds.td
===
--- include/clang/Basic/DiagnosticSemaKinds.td
+++ include/clang/Basic/DiagnosticSemaKinds.td
@@ -7800,6 +7800,8 @@
   "sampler_t variable required - got %0">;
 def err_wrong_sampler_addressspace: Error<
   "sampler type cannot be used with the __local and __global address space 
qualifiers">;
+def error_opencl_cast_non_zero_to_event_t : Error<
+  "cannot cast non-zero value '%0' to 'event_t'">;
 def err_opencl_global_invalid_addr_space : Error<
   "%select{program scope|static local|extern}0 variable must reside in %1 
address space">;
 def err_missing_actual_pipe_type : Error<


Index: test/SemaOpenCL/event_t.cl
===
--- test/SemaOpenCL/event_t.cl
+++ test/SemaOpenCL/event_t.cl
@@ -14,5 +14,6 @@
   foo(e);
   foo(0);
   foo(5); // expected-error {{passing 'int' to parameter of incompatible type 'event_t'}}
+  foo((event_t)1); // expected-error {{cannot cast non-zero value 'int' to 'event_t'}}
 }
 
Index: test/CodeGenOpenCL/event_t.cl
===
--- test/CodeGenOpenCL/event_t.cl
+++ test/CodeGenOpenCL/event_t.cl
@@ -9,4 +9,6 @@
 // CHECK: call {{.*}}void @foo(%opencl.event_t* %
   foo(0);
 // CHECK: call {{.*}}void @foo(%opencl.event_t* null)
+  foo((event_t)0);
+// CHECK: call {{.*}}void @foo(%opencl.event_t* null)
 }
Index: lib/Sema/SemaCast.cpp
===
--- lib/Sema/SemaCast.cpp
+++ lib/Sema/SemaCast.cpp
@@ -2347,6 +2347,22 @@
   return;
 }
 
+// OpenCL v2.0 s6.13.10 - Allow casts from '0' to event_t type.
+if (Self.getLangOpts().OpenCL && DestType->isEventT()) {
+  llvm::APSInt CastInt;
+  if (SrcExpr.get()->EvaluateAsInt(CastInt, Self.Context)) {
+if (0 == CastInt) {
+  Kind = CK_ZeroToOCLEvent;
+  return;
+}
+Self.Diag(OpRange.getBegin(),
+  diag::error_opencl_cast_non_zero_to_event_t)
+  << CastInt.toString(10) << SrcExpr.get()->getSourceRange();
+SrcExpr = ExprError();
+return;
+  }
+}
+
 // Reject any other conversions to non-scalar types.
 Self.Diag(OpRange.getBegin(), diag::err_typecheck_cond_expect_scalar)
   << DestType << SrcExpr.get()->getSourceRange();
Index: include/clang/Basic/DiagnosticSemaKinds.td
===
--- include/clang/Basic/DiagnosticSemaKinds.td
+++ include/clang/Basic/DiagnosticSemaKinds.td
@@ -7800,6 +7800,8 @@
   "sampler_t variable required - got %0">;
 def err_wrong_sampler_addressspace: Error<
   "sampler type cannot be used with the __local and __global address space qualifiers">;
+def error_opencl_cast_non_zero_to_event_t : Error<
+  "cannot cast non-zero value '%0' to 'event_t'">;
 def

Re: [PATCH] D17578: [OpenCL]Allowing explicit conversion of "0" to event_t type

2016-05-10 Thread Aaron En Ye Shi via cfe-commits 
ashi1 marked 5 inline comments as done.
ashi1 added a comment.

http://reviews.llvm.org/D17578



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Re: [PATCH] D17578: [OpenCL]Allowing explicit conversion of "0" to event_t type

2016-02-26 Thread Aaron En Ye Shi via cfe-commits 
ashi1 updated this revision to Diff 49219.
ashi1 marked an inline comment as done.
ashi1 added a comment.

Revised with Xiuli Pan's comments.


http://reviews.llvm.org/D17578

Files:
  include/clang/Basic/DiagnosticSemaKinds.td
  lib/Sema/SemaCast.cpp
  test/CodeGenOpenCL/event_t.cl
  test/SemaOpenCL/event_t.cl

Index: test/SemaOpenCL/event_t.cl
===
--- test/SemaOpenCL/event_t.cl
+++ test/SemaOpenCL/event_t.cl
@@ -14,5 +14,6 @@
   foo(e);
   foo(0);
   foo(5); // expected-error {{passing 'int' to parameter of incompatible type 
'event_t'}}
+  foo((event_t)1); // expected-error {{cannot cast non-zero value 'int' to 
'event_t'}}
 }
 
Index: test/CodeGenOpenCL/event_t.cl
===
--- test/CodeGenOpenCL/event_t.cl
+++ test/CodeGenOpenCL/event_t.cl
@@ -9,4 +9,6 @@
 // CHECK: call {{.*}}void @foo(%opencl.event_t* %
   foo(0);
 // CHECK: call {{.*}}void @foo(%opencl.event_t* null)
+  foo((event_t)0);
+// CHECK: call {{.*}}void @foo(%opencl.event_t* null)
 }
Index: lib/Sema/SemaCast.cpp
===
--- lib/Sema/SemaCast.cpp
+++ lib/Sema/SemaCast.cpp
@@ -2313,6 +2313,23 @@
   return;
 }
 
+// OpenCL v2.0 s6.13.10 - Allow casts from '0' to event_t type.
+if (Self.getLangOpts().OpenCL && DestType->isEventT()) {
+  llvm::APSInt intValue;
+  if (SrcExpr.get()->EvaluateAsInt(intValue, Self.Context)) {
+if (0 == intValue) {
+  Kind = CK_ZeroToOCLEvent;
+  return;
+} else {
+  Self.Diag(OpRange.getBegin(),
+diag::error_opencl_cast_non_zero_to_event_t)
+<< intValue.toString(10) << 
SrcExpr.get()->getSourceRange();
+  SrcExpr = ExprError();
+  return;
+}
+  }
+}
+
 // Reject any other conversions to non-scalar types.
 Self.Diag(OpRange.getBegin(), diag::err_typecheck_cond_expect_scalar)
   << DestType << SrcExpr.get()->getSourceRange();
Index: include/clang/Basic/DiagnosticSemaKinds.td
===
--- include/clang/Basic/DiagnosticSemaKinds.td
+++ include/clang/Basic/DiagnosticSemaKinds.td
@@ -7677,6 +7677,8 @@
   "sampler_t variable required - got %0">;
 def err_wrong_sampler_addressspace: Error<
   "sampler type cannot be used with the __local and __global address space 
qualifiers">;
+def error_opencl_cast_non_zero_to_event_t : Error<
+  "cannot cast non-zero value '%0' to 'event_t'">;
 def err_opencl_global_invalid_addr_space : Error<
   "program scope variable must reside in %0 address space">;
 def err_missing_actual_pipe_type : Error<


Index: test/SemaOpenCL/event_t.cl
===
--- test/SemaOpenCL/event_t.cl
+++ test/SemaOpenCL/event_t.cl
@@ -14,5 +14,6 @@
   foo(e);
   foo(0);
   foo(5); // expected-error {{passing 'int' to parameter of incompatible type 'event_t'}}
+  foo((event_t)1); // expected-error {{cannot cast non-zero value 'int' to 'event_t'}}
 }
 
Index: test/CodeGenOpenCL/event_t.cl
===
--- test/CodeGenOpenCL/event_t.cl
+++ test/CodeGenOpenCL/event_t.cl
@@ -9,4 +9,6 @@
 // CHECK: call {{.*}}void @foo(%opencl.event_t* %
   foo(0);
 // CHECK: call {{.*}}void @foo(%opencl.event_t* null)
+  foo((event_t)0);
+// CHECK: call {{.*}}void @foo(%opencl.event_t* null)
 }
Index: lib/Sema/SemaCast.cpp
===
--- lib/Sema/SemaCast.cpp
+++ lib/Sema/SemaCast.cpp
@@ -2313,6 +2313,23 @@
   return;
 }
 
+// OpenCL v2.0 s6.13.10 - Allow casts from '0' to event_t type.
+if (Self.getLangOpts().OpenCL && DestType->isEventT()) {
+  llvm::APSInt intValue;
+  if (SrcExpr.get()->EvaluateAsInt(intValue, Self.Context)) {
+if (0 == intValue) {
+  Kind = CK_ZeroToOCLEvent;
+  return;
+} else {
+  Self.Diag(OpRange.getBegin(),
+diag::error_opencl_cast_non_zero_to_event_t)
+<< intValue.toString(10) << SrcExpr.get()->getSourceRange();
+  SrcExpr = ExprError();
+  return;
+}
+  }
+}
+
 // Reject any other conversions to non-scalar types.
 Self.Diag(OpRange.getBegin(), diag::err_typecheck_cond_expect_scalar)
   << DestType << SrcExpr.get()->getSourceRange();
Index: include/clang/Basic/DiagnosticSemaKinds.td
===
--- include/clang/Basic/DiagnosticSemaKinds.td
+++ include/clang/Basic/DiagnosticSemaKinds.td
@@ -7677,6 +7677,8 @@
   "sampler_t variable required - got %0">;
 def err_wrong_sampler_addressspace: Error<
   "sampler type cannot be used with the __local and __global address space qualifiers">;
+def error_opencl_cast_non_zero_to_event_t : Error<
+  "cannot cast non-zero

[PATCH] D17578: [OpenCL]Allowing explicit conversion of "0" to event_t type

2016-02-24 Thread Aaron En Ye Shi via cfe-commits 
ashi1 created this revision.
ashi1 added reviewers: Anastasia, pxli168, yaxunl.
ashi1 added subscribers: pekka.jaaskelainen, tstellarAMD, cfe-commits.

This patch will allow the cast of 0 to event_t type.

http://reviews.llvm.org/D17578

Files:
  include/clang/Basic/DiagnosticSemaKinds.td
  lib/Sema/SemaCast.cpp
  test/CodeGenOpenCL/event_t.cl

Index: test/CodeGenOpenCL/event_t.cl
===
--- test/CodeGenOpenCL/event_t.cl
+++ test/CodeGenOpenCL/event_t.cl
@@ -9,4 +9,6 @@
 // CHECK: call {{.*}}void @foo(%opencl.event_t* %
   foo(0);
 // CHECK: call {{.*}}void @foo(%opencl.event_t* null)
+  foo((event_t)0);
+// CHECK: call {{.*}}void @foo(%opencl.event_t* null)
 }
Index: lib/Sema/SemaCast.cpp
===
--- lib/Sema/SemaCast.cpp
+++ lib/Sema/SemaCast.cpp
@@ -2313,6 +2313,23 @@
   return;
 }
 
+// for OpenCL, allow casts from '0' to event_t type
+if ((Self.getLangOpts().OpenCL) && DestType->isEventT()) {
+  llvm::APSInt intValue;
+  if(SrcExpr.get()->EvaluateAsInt(intValue, Self.getASTContext())) {
+if(0 == intValue) {
+  Kind = CK_IntegralToPointer;
+  return;
+} else {
+Self.Diag(OpRange.getBegin(),
+  diag::error_opencl_cast_non_zero_to_event_t)
+  << intValue.toString(10) << SrcExpr.get()->getSourceRange();
+SrcExpr = ExprError();
+return;
+}
+  }
+}
+
 // Reject any other conversions to non-scalar types.
 Self.Diag(OpRange.getBegin(), diag::err_typecheck_cond_expect_scalar)
   << DestType << SrcExpr.get()->getSourceRange();
Index: include/clang/Basic/DiagnosticSemaKinds.td
===
--- include/clang/Basic/DiagnosticSemaKinds.td
+++ include/clang/Basic/DiagnosticSemaKinds.td
@@ -7676,7 +7676,9 @@
 def err_sampler_argument_required : Error<
   "sampler_t variable required - got %0">;
 def err_wrong_sampler_addressspace: Error<
-  "sampler type cannot be used with the __local and __global address space 
qualifiers">;
+  "sampler type cannot be used with the __local and __global address space 
qualifiers">;
+def error_opencl_cast_non_zero_to_event_t : Error<
+  "cannot cast non-zero value '%0' to 'event_t'">;
 def err_opencl_global_invalid_addr_space : Error<
   "program scope variable must reside in %0 address space">;
 def err_missing_actual_pipe_type : Error<


Index: test/CodeGenOpenCL/event_t.cl
===
--- test/CodeGenOpenCL/event_t.cl
+++ test/CodeGenOpenCL/event_t.cl
@@ -9,4 +9,6 @@
 // CHECK: call {{.*}}void @foo(%opencl.event_t* %
   foo(0);
 // CHECK: call {{.*}}void @foo(%opencl.event_t* null)
+  foo((event_t)0);
+// CHECK: call {{.*}}void @foo(%opencl.event_t* null)
 }
Index: lib/Sema/SemaCast.cpp
===
--- lib/Sema/SemaCast.cpp
+++ lib/Sema/SemaCast.cpp
@@ -2313,6 +2313,23 @@
   return;
 }
 
+// for OpenCL, allow casts from '0' to event_t type
+if ((Self.getLangOpts().OpenCL) && DestType->isEventT()) {
+  llvm::APSInt intValue;
+  if(SrcExpr.get()->EvaluateAsInt(intValue, Self.getASTContext())) {
+if(0 == intValue) {
+  Kind = CK_IntegralToPointer;
+  return;
+} else {
+Self.Diag(OpRange.getBegin(),
+  diag::error_opencl_cast_non_zero_to_event_t)
+  << intValue.toString(10) << SrcExpr.get()->getSourceRange();
+SrcExpr = ExprError();
+return;
+}
+  }
+}
+
 // Reject any other conversions to non-scalar types.
 Self.Diag(OpRange.getBegin(), diag::err_typecheck_cond_expect_scalar)
   << DestType << SrcExpr.get()->getSourceRange();
Index: include/clang/Basic/DiagnosticSemaKinds.td
===
--- include/clang/Basic/DiagnosticSemaKinds.td
+++ include/clang/Basic/DiagnosticSemaKinds.td
@@ -7676,7 +7676,9 @@
 def err_sampler_argument_required : Error<
   "sampler_t variable required - got %0">;
 def err_wrong_sampler_addressspace: Error<
-  "sampler type cannot be used with the __local and __global address space qualifiers">;
+  "sampler type cannot be used with the __local and __global address space qualifiers">;
+def error_opencl_cast_non_zero_to_event_t : Error<
+  "cannot cast non-zero value '%0' to 'event_t'">;
 def err_opencl_global_invalid_addr_space : Error<
   "program scope variable must reside in %0 address space">;
 def err_missing_actual_pipe_type : Error<
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits