[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Phabricator via Phabricator via cfe-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rC360265: [OpenMP][Clang] Support for target math functions 
(authored by gbercea, committed by ).

Changed prior to commit:
  https://reviews.llvm.org/D61399?vs=198664=198677#toc

Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChain.cpp
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h
  test/Driver/openmp-offload-gpu.c
  test/Headers/Inputs/include/cmath
  test/Headers/Inputs/include/limits
  test/Headers/Inputs/include/math.h
  test/Headers/nvptx_device_cmath_functions.c
  test/Headers/nvptx_device_cmath_functions.cpp
  test/Headers/nvptx_device_math_functions.c
  test/Headers/nvptx_device_math_functions.cpp

Index: lib/Headers/__clang_cuda_libdevice_declares.h
===
--- lib/Headers/__clang_cuda_libdevice_declares.h
+++ lib/Headers/__clang_cuda_libdevice_declares.h
@@ -10,443 +10,453 @@
 #ifndef __CLANG_CUDA_LIBDEVICE_DECLARES_H__
 #define __CLANG_CUDA_LIBDEVICE_DECLARES_H__
 
+#if defined(__cplusplus)
 extern "C" {
+#endif
 
-__device__ int __nv_abs(int __a);
-__device__ double __nv_acos(double __a);
-__device__ float __nv_acosf(float __a);
-__device__ double __nv_acosh(double __a);
-__device__ float __nv_acoshf(float __a);
-__device__ double __nv_asin(double __a);
-__device__ float __nv_asinf(float __a);
-__device__ double __nv_asinh(double __a);
-__device__ float __nv_asinhf(float __a);
-__device__ double __nv_atan2(double __a, double __b);
-__device__ float __nv_atan2f(float __a, float __b);
-__device__ double __nv_atan(double __a);
-__device__ float __nv_atanf(float __a);
-__device__ double __nv_atanh(double __a);
-__device__ float __nv_atanhf(float __a);
-__device__ int __nv_brev(int __a);
-__device__ long long __nv_brevll(long long __a);
-__device__ int __nv_byte_perm(int __a, int __b, int __c);
-__device__ double __nv_cbrt(double __a);
-__device__ float __nv_cbrtf(float __a);
-__device__ double __nv_ceil(double __a);
-__device__ float __nv_ceilf(float __a);
-__device__ int __nv_clz(int __a);
-__device__ int __nv_clzll(long long __a);
-__device__ double __nv_copysign(double __a, double __b);
-__device__ float __nv_copysignf(float __a, float __b);
-__device__ double __nv_cos(double __a);
-__device__ float __nv_cosf(float __a);
-__device__ double __nv_cosh(double __a);
-__device__ float __nv_coshf(float __a);
-__device__ double __nv_cospi(double __a);
-__device__ float __nv_cospif(float __a);
-__device__ double __nv_cyl_bessel_i0(double __a);
-__device__ float __nv_cyl_bessel_i0f(float __a);
-__device__ double __nv_cyl_bessel_i1(double __a);
-__device__ float __nv_cyl_bessel_i1f(float __a);
-__device__ double __nv_dadd_rd(double __a, double __b);
-__device__ double __nv_dadd_rn(double __a, double __b);
-__device__ double __nv_dadd_ru(double __a, double __b);
-__device__ double __nv_dadd_rz(double __a, double __b);
-__device__ double __nv_ddiv_rd(double __a, double __b);
-__device__ double __nv_ddiv_rn(double __a, double __b);
-__device__ double __nv_ddiv_ru(double __a, double __b);
-__device__ double __nv_ddiv_rz(double __a, double __b);
-__device__ double __nv_dmul_rd(double __a, double __b);
-__device__ double __nv_dmul_rn(double __a, double __b);
-__device__ double __nv_dmul_ru(double __a, double __b);
-__device__ double __nv_dmul_rz(double __a, double __b);
-__device__ float __nv_double2float_rd(double __a);
-__device__ float __nv_double2float_rn(double __a);
-__device__ float __nv_double2float_ru(double __a);
-__device__ float __nv_double2float_rz(double __a);
-__device__ int __nv_double2hiint(double __a);
-__device__ int __nv_double2int_rd(double __a);
-__device__ int __nv_double2int_rn(double __a);
-__device__ int __nv_double2int_ru(double __a);
-__device__ int __nv_double2int_rz(double __a);
-__device__ long long __nv_double2ll_rd(double __a);
-__device__ long long __nv_double2ll_rn(double __a);
-__device__ long long __nv_double2ll_ru(double __a);
-__device__ long long __nv_double2ll_rz(double __a);
-__device__ int __nv_double2loint(double __a);
-__device__ unsigned int __nv_double2uint_rd(double __a);
-__device__ unsigned int __nv_double2uint_rn(double __a);
-__device__ unsigned int __nv_double2uint_ru(double __a);
-__device__ unsigned int __nv_double2uint_rz(double __a);
-__device__ unsigned long long __nv_double2ull_rd(double __a);
-__device__ unsigned long long __nv_double2ull_rn(double __a);
-__device__ unsigned long long __nv_double2ull_ru(double __a);
-__device__ unsigned long long __nv_double2ull_rz(double __a);

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea updated this revision to Diff 198664.
gtbercea added a comment.

- Eliminate declarations of functions not needed for math function resolution.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChain.cpp
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h
  test/Driver/openmp-offload-gpu.c
  test/Headers/Inputs/include/cmath
  test/Headers/Inputs/include/limits
  test/Headers/Inputs/include/math.h
  test/Headers/nvptx_device_cmath_functions.c
  test/Headers/nvptx_device_cmath_functions.cpp
  test/Headers/nvptx_device_math_functions.c
  test/Headers/nvptx_device_math_functions.cpp

Index: test/Headers/nvptx_device_math_functions.cpp
===
--- /dev/null
+++ test/Headers/nvptx_device_math_functions.cpp
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_math.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -internal-isystem %S/Inputs/include -include stdlib.h -include limits -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_math_functions.c
===
--- /dev/null
+++ test/Headers/nvptx_device_math_functions.c
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_math.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_cmath_functions.cpp
===
--- /dev/null
+++ test/Headers/nvptx_device_cmath_functions.cpp
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include cmath -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_math.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include cmath -internal-isystem %S/Inputs/include -include stdlib.h -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, 

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea updated this revision to Diff 198578.
gtbercea added a comment.

- Fix move to openmp_wrapper folder. Fix header ordering problem.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChain.cpp
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h
  test/Driver/openmp-offload-gpu.c
  test/Headers/Inputs/include/cmath
  test/Headers/Inputs/include/limits
  test/Headers/Inputs/include/math.h
  test/Headers/nvptx_device_cmath_functions.c
  test/Headers/nvptx_device_cmath_functions.cpp
  test/Headers/nvptx_device_math_functions.c
  test/Headers/nvptx_device_math_functions.cpp

Index: test/Headers/nvptx_device_math_functions.cpp
===
--- /dev/null
+++ test/Headers/nvptx_device_math_functions.cpp
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_math.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -internal-isystem %S/Inputs/include -include stdlib.h -include limits -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_math_functions.c
===
--- /dev/null
+++ test/Headers/nvptx_device_math_functions.c
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_math.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_cmath_functions.cpp
===
--- /dev/null
+++ test/Headers/nvptx_device_cmath_functions.cpp
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include cmath -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_math.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -include cmath -internal-isystem %S/Inputs/include -include stdlib.h -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Jonas Devlieghere via Phabricator via cfe-commits]

JDevlieghere added inline comments.



Comment at: lib/Headers/CMakeLists.txt:36
   bmiintrin.h
+  openmp_wrappers/math.h
+  openmp_wrappers/cmath

hfinkel wrote:
> JDevlieghere wrote:
> > This doesn't do what you think it would do. The files are copied into the 
> > root of the resource directory, which causes stage 2 build failures on 
> > GreenDragon. 
> Can you provide a link to the failure log? Is the problem that the files are 
> not copied into their subdirectory?
Correct. There's not much to see, but here's a build that fails because of 
this: http://green.lab.llvm.org/green/view/LLDB/job/lldb-cmake/25557/console

```
CMake Error at cmake/modules/HandleLLVMOptions.cmake:497 (message):
  LLVM_ENABLE_MODULES is not supported by this compiler
```
The cmake log output, which I grabbed from the bot is more descriptive:
```
Performing C++ SOURCE FILE Test CXX_SUPPORTS_MODULES failed with the following 
output:
Change Dir: 
/Users/buildslave/jenkins/workspace/lldb-cmake/lldb-build/CMakeFiles/CMakeTmp

Run Build Command:"/usr/local/bin/ninja" "cmTC_0dd11"
[1/2] Building CXX object CMakeFiles/cmTC_0dd11.dir/src.cxx.o
FAILED: CMakeFiles/cmTC_0dd11.dir/src.cxx.o
/Users/buildslave/jenkins/workspace/lldb-cmake/host-compiler/bin/clang++
-fPIC -fvisibility-inlines-hidden -Werror=date-time 
-Werror=unguarded-availability-new -std=c++11 -DCXX_SUPPORTS_MODULES  
-Werror=unguarded-availability-new -fmodules 
-fmodules-cache-path=/Users/buildslave/jenkins/workspace/lldb-cmake/lldb-build/module.cache
 -fcxx-modules -isysroot 
/Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX10.14.sdk
 -mmacosx-version-min=10.9 -o CMakeFiles/cmTC_0dd11.dir/src.cxx.o -c src.cxx
While building module 'Darwin' imported from 
/Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX10.14.sdk/usr/include/assert.h:42:
While building module 'std' imported from 
/Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX10.14.sdk/usr/include/tgmath.h:27:
In file included from :2:
/Users/buildslave/jenkins/workspace/lldb-cmake/host-compiler/bin/../include/c++/v1/ctype.h:38:15:
 fatal error: cyclic dependency in module 'Darwin': Darwin -> std -> Darwin
#include_next 
  ^
While building module 'Darwin' imported from 
/Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX10.14.sdk/usr/include/assert.h:42:
In file included from :89:
In file included from 
/Users/buildslave/jenkins/workspace/lldb-cmake/host-compiler/lib/clang/9.0.0/include/tgmath.h:21:
/Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX10.14.sdk/usr/include/tgmath.h:27:10:
 fatal error: could not build module 'std'
#include 
 ^
In file included from src.cxx:2:
In file included from 
/Users/buildslave/jenkins/workspace/lldb-cmake/host-compiler/bin/../include/c++/v1/cassert:20:
/Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX10.14.sdk/usr/include/assert.h:42:10:
 fatal error: could not build module 'Darwin'
#include 
 ^
3 errors generated.
ninja: build stopped: subcommand failed.

Source file was:
#undef NDEBUG
   #include 
   #define NDEBUG
   #include 
   int main() { assert(this code is not compiled); }
```


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Hal Finkel via Phabricator via cfe-commits]

hfinkel added inline comments.



Comment at: lib/Headers/CMakeLists.txt:36
   bmiintrin.h
+  openmp_wrappers/math.h
+  openmp_wrappers/cmath

JDevlieghere wrote:
> This doesn't do what you think it would do. The files are copied into the 
> root of the resource directory, which causes stage 2 build failures on 
> GreenDragon. 
Can you provide a link to the failure log? Is the problem that the files are 
not copied into their subdirectory?


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Jonas Devlieghere via Phabricator via cfe-commits]

JDevlieghere added a comment.

I've reverted this in rL360192  because it 
breaks stage 2 builds on GreenDragon. Please see the commit message and the 
inline comment for more details.




Comment at: lib/Headers/CMakeLists.txt:36
   bmiintrin.h
+  openmp_wrappers/math.h
+  openmp_wrappers/cmath

This doesn't do what you think it would do. The files are copied into the root 
of the resource directory, which causes stage 2 build failures on GreenDragon. 


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Phabricator via Phabricator via cfe-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rC360063: [OpenMP][Clang] Support for target math functions 
(authored by gbercea, committed by ).

Changed prior to commit:
  https://reviews.llvm.org/D61399?vs=198311=198314#toc

Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h
  test/Driver/openmp-offload-gpu.c
  test/Headers/Inputs/include/cmath
  test/Headers/Inputs/include/limits
  test/Headers/Inputs/include/math.h
  test/Headers/nvptx_device_cmath_functions.c
  test/Headers/nvptx_device_cmath_functions.cpp
  test/Headers/nvptx_device_math_functions.c
  test/Headers/nvptx_device_math_functions.cpp

Index: test/Headers/nvptx_device_cmath_functions.cpp
===
--- test/Headers/nvptx_device_cmath_functions.cpp
+++ test/Headers/nvptx_device_cmath_functions.cpp
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include cmath -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include cmath -internal-isystem %S/Inputs/include -include stdlib.h -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_math_functions.c
===
--- test/Headers/nvptx_device_math_functions.c
+++ test/Headers/nvptx_device_math_functions.c
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_cmath_functions.c
===
--- test/Headers/nvptx_device_cmath_functions.c
+++ test/Headers/nvptx_device_cmath_functions.c
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include cmath -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include cmath -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/Inputs/include/math.h
===
--- 

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea updated this revision to Diff 198311.
gtbercea added a comment.

- Address comments.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h
  test/Driver/openmp-offload-gpu.c
  test/Headers/Inputs/include/cmath
  test/Headers/Inputs/include/limits
  test/Headers/Inputs/include/math.h
  test/Headers/nvptx_device_cmath_functions.c
  test/Headers/nvptx_device_cmath_functions.cpp
  test/Headers/nvptx_device_math_functions.c
  test/Headers/nvptx_device_math_functions.cpp

Index: test/Headers/nvptx_device_math_functions.cpp
===
--- /dev/null
+++ test/Headers/nvptx_device_math_functions.cpp
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -internal-isystem %S/Inputs/include -include stdlib.h -include limits -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_math_functions.c
===
--- /dev/null
+++ test/Headers/nvptx_device_math_functions.c
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_cmath_functions.cpp
===
--- /dev/null
+++ test/Headers/nvptx_device_cmath_functions.cpp
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include cmath -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include cmath -internal-isystem %S/Inputs/include -include stdlib.h -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_cmath_functions.c
===
--- /dev/null
+++ test/Headers/nvptx_device_cmath_functions.c
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// 

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Alexey Bataev via Phabricator via cfe-commits]

ABataev accepted this revision.
ABataev added a comment.
This revision is now accepted and ready to land.

LG with a nit.




Comment at: lib/Headers/__clang_cuda_cmath.h:444
 using ::roundf;
+#ifndef _OPENMP
 using ::scalblnf;

gtbercea wrote:
> ABataev wrote:
> > I see that the same guard is used 
> > `lib/Headers/__clang_cuda_device_functions.h`, but for different set of 
> > functions. Is this ok?
> Yep, it's intentional. Again the variant issue.
Then again, add TODO or FIXME


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea marked an inline comment as done.
gtbercea added inline comments.



Comment at: lib/Headers/__clang_cuda_cmath.h:444
 using ::roundf;
+#ifndef _OPENMP
 using ::scalblnf;

ABataev wrote:
> I see that the same guard is used 
> `lib/Headers/__clang_cuda_device_functions.h`, but for different set of 
> functions. Is this ok?
Yep, it's intentional. Again the variant issue.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Alexey Bataev via Phabricator via cfe-commits]

ABataev added inline comments.



Comment at: lib/Headers/__clang_cuda_cmath.h:444
 using ::roundf;
+#ifndef _OPENMP
 using ::scalblnf;

I see that the same guard is used 
`lib/Headers/__clang_cuda_device_functions.h`, but for different set of 
functions. Is this ok?


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea updated this revision to Diff 198301.
gtbercea added a comment.

- Address comments.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h
  test/Driver/openmp-offload-gpu.c
  test/Headers/Inputs/include/cmath
  test/Headers/Inputs/include/limits
  test/Headers/Inputs/include/math.h
  test/Headers/nvptx_device_cmath_functions.c
  test/Headers/nvptx_device_cmath_functions.cpp
  test/Headers/nvptx_device_math_functions.c
  test/Headers/nvptx_device_math_functions.cpp

Index: test/Headers/nvptx_device_math_functions.cpp
===
--- /dev/null
+++ test/Headers/nvptx_device_math_functions.cpp
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -internal-isystem %S/Inputs/include -include stdlib.h -include limits -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_math_functions.c
===
--- /dev/null
+++ test/Headers/nvptx_device_math_functions.c
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_cmath_functions.cpp
===
--- /dev/null
+++ test/Headers/nvptx_device_cmath_functions.cpp
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include cmath -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include cmath -internal-isystem %S/Inputs/include -include stdlib.h -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_cmath_functions.c
===
--- /dev/null
+++ test/Headers/nvptx_device_cmath_functions.c
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// 

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Alexey Bataev via Phabricator via cfe-commits]

ABataev added inline comments.



Comment at: lib/Headers/__clang_cuda_cmath.h:54
 __DEVICE__ float fmod(float __x, float __y) { return ::fmodf(__x, __y); }
+#ifndef _OPENMP
 __DEVICE__ int fpclassify(float __x) {

gtbercea wrote:
> ABataev wrote:
> > Why we have this guard here? It does not work for OpenMP? Why?
> Because all the FP_XXX macros are defined in cmath and for OpenMP we can't 
> include it yet because we don't support variant yet.
The better to add TODO or FIXME to fix this once `variant` construct in 
supported.



Comment at: lib/Headers/__clang_cuda_device_functions.h:49
+#if defined(__cplusplus)
 __DEVICE__ void __brkpt(int __a) { __brkpt(); }
+#endif

gtbercea wrote:
> ABataev wrote:
> > Can we do anything with this in С mode? I mean, to allow it in C.
> We can if we rename the function.
Take a look here, probably it will solve the problem:
https://clang.llvm.org/docs/AttributeReference.html#overloadable


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea marked 2 inline comments as done.
gtbercea added inline comments.



Comment at: lib/Headers/__clang_cuda_cmath.h:54
 __DEVICE__ float fmod(float __x, float __y) { return ::fmodf(__x, __y); }
+#ifndef _OPENMP
 __DEVICE__ int fpclassify(float __x) {

ABataev wrote:
> Why we have this guard here? It does not work for OpenMP? Why?
Because all the FP_XXX macros are defined in cmath and for OpenMP we can't 
include it yet because we don't support variant yet.



Comment at: lib/Headers/__clang_cuda_device_functions.h:49
+#if defined(__cplusplus)
 __DEVICE__ void __brkpt(int __a) { __brkpt(); }
+#endif

ABataev wrote:
> Can we do anything with this in С mode? I mean, to allow it in C.
We can if we rename the function.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Alexey Bataev via Phabricator via cfe-commits]

ABataev added inline comments.



Comment at: lib/Headers/__clang_cuda_cmath.h:54
 __DEVICE__ float fmod(float __x, float __y) { return ::fmodf(__x, __y); }
+#ifndef _OPENMP
 __DEVICE__ int fpclassify(float __x) {

Why we have this guard here? It does not work for OpenMP? Why?



Comment at: lib/Headers/__clang_cuda_device_functions.h:49
+#if defined(__cplusplus)
 __DEVICE__ void __brkpt(int __a) { __brkpt(); }
+#endif

Can we do anything with this in С mode? I mean, to allow it in C.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Johannes Doerfert via Phabricator via cfe-commits]

jdoerfert added a comment.

Alexey, is this is good to go now?


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea updated this revision to Diff 198108.
gtbercea added a comment.

- Add new tests. Add stub headers.
- Remove old tests.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h
  test/Driver/openmp-offload-gpu.c
  test/Headers/Inputs/include/cmath
  test/Headers/Inputs/include/limits
  test/Headers/Inputs/include/math.h
  test/Headers/nvptx_device_cmath_functions.c
  test/Headers/nvptx_device_cmath_functions.cpp
  test/Headers/nvptx_device_math_functions.c
  test/Headers/nvptx_device_math_functions.cpp

Index: test/Headers/nvptx_device_math_functions.cpp
===
--- /dev/null
+++ test/Headers/nvptx_device_math_functions.cpp
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -internal-isystem %S/Inputs/include -include stdlib.h -include limits -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_math_functions.c
===
--- /dev/null
+++ test/Headers/nvptx_device_math_functions.c
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include math.h -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include math.h -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_cmath_functions.cpp
===
--- /dev/null
+++ test/Headers/nvptx_device_cmath_functions.cpp
@@ -0,0 +1,21 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -include cmath -x c++ -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include cmath -internal-isystem %S/Inputs/include -include stdlib.h -x c++ -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck -check-prefix CHECK-YES %s
+
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @__nv_sqrt(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__nv_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call double @__nv_modf(double
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/Headers/nvptx_device_cmath_functions.c
===
--- /dev/null
+++ test/Headers/nvptx_device_cmath_functions.c
@@ -0,0 +1,21 @@
+// Test calling of device math functions.

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea updated this revision to Diff 198105.
gtbercea added a comment.

- Add driver test.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h
  test/CodeGen/nvptx_device_cmath_functions.c
  test/CodeGen/nvptx_device_math_functions.c
  test/Driver/openmp-offload-gpu.c

Index: test/Driver/openmp-offload-gpu.c
===
--- test/Driver/openmp-offload-gpu.c
+++ test/Driver/openmp-offload-gpu.c
@@ -278,3 +278,8 @@
 // RUN:   | FileCheck -check-prefix=CUDA_RED_RECS %s
 // CUDA_RED_RECS: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"
 // CUDA_RED_RECS-SAME: "-fopenmp-cuda-teams-reduction-recs-num=2048"
+
+// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=OPENMP_NVPTX_WRAPPERS %s
+// OPENMP_NVPTX_WRAPPERS: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"
+// OPENMP_NVPTX_WRAPPERS-SAME: "-internal-isystem" "{{.*}}openmp_wrappers"
Index: test/CodeGen/nvptx_device_math_functions.c
===
--- /dev/null
+++ test/CodeGen/nvptx_device_math_functions.c
@@ -0,0 +1,24 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang -fmath-errno -S -emit-llvm -o - %s -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda | FileCheck -check-prefix CHECK-YES %s
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @llvm.nvvm.sqrt.rn.d(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__internal_accurate_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call double @llvm.nvvm.trunc.d(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.lo(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call double @llvm.nvvm.lohi.i2d(i32
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/CodeGen/nvptx_device_cmath_functions.c
===
--- /dev/null
+++ test/CodeGen/nvptx_device_cmath_functions.c
@@ -0,0 +1,24 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang++ -fmath-errno -S -emit-llvm -o - %s -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda | FileCheck -check-prefix CHECK-YES %s
+#include 
+
+void test_math_funcs(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @llvm.nvvm.sqrt.rn.d(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__internal_accurate_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call double @llvm.nvvm.trunc.d(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.lo(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call double @llvm.nvvm.lohi.i2d(i32
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: lib/Headers/openmp_wrappers/math.h
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/math.h
@@ -0,0 +1,17 @@
+/*===- math.h - Alternative math.h header --===
+ *
+ * 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
+ *
+ *===---===
+ */
+
+#include <__clang_openmp_math.h>
+
+#ifndef __CLANG_NO_HOST_MATH__
+#include_next 
+#else
+#undef __CLANG_NO_HOST_MATH__
+#endif
+
Index: lib/Headers/openmp_wrappers/cmath
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/cmath
@@ -0,0 +1,16 @@
+/*===-- cmath - Alternative cmath header ---===
+ *
+ * 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
+ *
+ *===---===
+ */
+
+#include <__clang_openmp_math.h>
+
+#ifndef 

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Hal Finkel via Phabricator via cfe-commits]

hfinkel added a comment.

> It is up to you. I don't have strong objections if you think this will work 
> as required. Just the tests must be fixed, especially codegen tests.

Thanks, Alexey. I think this will work as required, and then we'll be able to 
update it when we get declare variant. Agreed on the tests (on all points).


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Alexey Bataev via Phabricator via cfe-commits]

ABataev added a comment.

In D61399#1490189 , @hfinkel wrote:

> > Still, I think we need to prvide the default implementation of those 
> > non-standard functions (they can be very simple, maybe reporting error is 
> > going to be enough), which can be overriden by user.
>
> I appreciate your motivation, and I agree with you to some extent. I don't 
> object to having generic versions of useful math functions, but I don't think 
> they should be required. It's not reasonable to make someone add generic 
> versions of every function which happens to appear in a 
> system/target-specific math.h header. NVPTX won't be the only target that has 
> target-optimized functions that get pulled in, even from our own headers, but 
> system headers also have differences anyway depending on what preprocessor 
> macros are defined. In the end, people can write portable code if they stick 
> to what's in the standard, and we should make it reasonably easy for them to 
> step outside of the standard to do what they need to do when the standard 
> subset of available functionality doesn't meet their needs for whatever 
> reason. This is what we do for C/C++, where we provide intrinsics and other 
> system functions for those who can't write their code only using the 
> facilities that C/C++ provide.
>
> In any case, I think that we can figure out how to add generic versions of 
> non-standard math functions in a separate thread. I think that we should move 
> forward with this and then make progress on generic versions separately. It's 
> also possible that we want to fold this discussion into the discussion on an 
> LLVM math library (we've talked about this for some time in the context of 
> vector math libraries, and I'd not thought about accelerators in this 
> context, but maybe this is all related).


It is up to you. I don't have strong objections if you think this will work as 
required. Just the tests must be fixed, especially codegen tests.




Comment at: test/CodeGen/nvptx_device_cmath_functions.c:1
+// Test calling of device math functions.
+///==///

1. Provide tests for C++ too.
2. Do not use driver to generate the code, use frontend.
3. Do not include real system header files. Use some stubs instead.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Hal Finkel via Phabricator via cfe-commits]

hfinkel added a comment.

> Still, I think we need to prvide the default implementation of those 
> non-standard functions (they can be very simple, maybe reporting error is 
> going to be enough), which can be overriden by user.

I appreciate your motivation, and I agree with you to some extent. I don't 
object to having generic versions of useful math functions, but I don't think 
they should be required. It's not reasonable to make someone add generic 
versions of every function which happens to appear in a system/target-specific 
math.h header. NVPTX won't be the only target that has target-optimized 
functions that get pulled in, even from our own headers, but system headers 
also have differences anyway depending on what preprocessor macros are defined. 
In the end, people can write portable code if they stick to what's in the 
standard, and we should make it reasonably easy for them to step outside of the 
standard to do what they need to do when the standard subset of available 
functionality doesn't meet their needs for whatever reason. This is what we do 
for C/C++, where we provide intrinsics and other system functions for those who 
can't write their code only using the facilities that C/C++ provide.

In any case, I think that we can figure out how to add generic versions of 
non-standard math functions in a separate thread. I think that we should move 
forward with this and then make progress on generic versions separately. It's 
also possible that we want to fold this discussion into the discussion on an 
LLVM math library (we've talked about this for some time in the context of 
vector math libraries, and I'd not thought about accelerators in this context, 
but maybe this is all related).


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea added a comment.

In D61399#1489762 , @ABataev wrote:

> In D61399#1489757 , @gtbercea wrote:
>
> > @ABataev this patch works for both C and C++ and for both math.h and cmath 
> > headers.
>
>
> Did you test it for the builtins? like `pow`, `powf` and `powl`? How are the 
> builtins resolved with this patch?


I have. There are tests for this.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Alexey Bataev via Phabricator via cfe-commits]

ABataev added a comment.

In D61399#1489757 , @gtbercea wrote:

> @ABataev this patch works for both C and C++ and for both math.h and cmath 
> headers.


Did you test it for the builtins? like `pow`, `powf` and `powl`? How are the 
builtins resolved with this patch?


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea added a comment.

@ABataev this patch works for both C and C++ and for both math.h and cmath 
headers.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Alexey Bataev via Phabricator via cfe-commits]

ABataev added a comment.

In D61399#1488897 , @hfinkel wrote:

> In D61399#1488366 , @ABataev wrote:
>
> > In D61399#1488329 , @hfinkel wrote:
> >
> > > In D61399#1488309 , @ABataev 
> > > wrote:
> > >
> > > > In D61399#1488299 , @hfinkel 
> > > > wrote:
> > > >
> > > > > In D61399#1488262 , @ABataev 
> > > > > wrote:
> > > > >
> > > > > > I don't like this implementation. Seems to me, it breaks one of the 
> > > > > > OpenMP standard requirements: the program can be compiled without 
> > > > > > openmp support. I assume, that with this includes the program won't 
> > > > > > be able to be compiled without OpenMP support anymore because it 
> > > > > > may use some device-specific math functions explicitly.
> > > > > >  Instead, I would like to see some additional, device-scpecific 
> > > > > > math header file, that must be included explicitly to support some 
> > > > > > device-specific math functions. And we need to provide default 
> > > > > > implementations for those extra math functions for all the 
> > > > > > platforms we're going to support, including default host 
> > > > > > implementations.
> > > > >
> > > > >
> > > > > Can you provide an example of a conforming program that can't be 
> > > > > compiled without OpenMP support? Regardless of the use of any 
> > > > > device-specific functions (which isn't covered by the standard, of 
> > > > > course, but might be needed in practice), the code still needs to be 
> > > > > compilable by the host in order to generate the host-fallback 
> > > > > version. This doesn't change that. Thus, any program that uses 
> > > > > anything from this math.h, etc. needs to compile for the host, and 
> > > > > thus, likely compiles without OpenMP support. Maybe I'm missing your 
> > > > > point, however.
> > > >
> > > >
> > > > Assume we have something like this:
> > > >
> > > >   #pragma omp target if(cond)
> > > >   a = __nv_();
> > > >
> > > >
> > > > Instead of `__nv_xxx` you can try to use any Cuda-specific function, 
> > > > which is not the part of the standard `math.h`/`cmath` files. Will it 
> > > > be compilable even with OpenMP?
> > >
> > >
> > > I don't think that this changes that one way or the other. Your example 
> > > won't work, AFAIK, unless you do something like:
> > >
> > >   #pragma omp target if(cond)
> > >   #ifdef __NVPTX__
> > >   a = __nv_();
> > >   #else
> > >   a = something_on_the_host;
> > >   #endif
> > >   
> > >
> > > and anything from these headers that doesn't also have a host version 
> > > will suffer the same fate: if it won't also compile for the host (one way 
> > > or another), then it won't work.
> >
> >
> > The problem with this header file is that it allows to use those 
> > Cuda-specific functions unconditionally in some cases:
> >
> >   #pragma omp target
> >   a = __nv_();
> >
> >
> > It won't require any target-specific guards to compile this code (if we 
> > compile it only for Cuda-specific devices) and we're loosing the 
> > consistency here: in some cases target regions will require special device 
> > guards, in others, with the same function calls, it is not. And the worst 
> > thing, is that we implicitly allow to introduce this kind of incostistency 
> > into users code. That's why I would prefer to see a special kind of the 
> > include file, NVPTX specific, that must be included explicitly, so the user 
> > explictly commanded to use some target-specific math functions, if he 
> > really wants it. Plus, maybe, in this files we need force check of the 
> > platform and warn users that the functions from this header file must be 
> > used using device-specific checks. Or provide some kind of the default 
> > implementations for all the platforms, that do not support those math 
> > function natively.
>
>
> I believe that I understand your point, but two things:
>
> 1. I think that you're mistaken on the underlying premise. That code will not 
> meaningfully compile without ifdefs, even if only CUDA-specific devices are 
> the only ones selected. We *always* compile code for the host as well, not 
> for offloading proper, but for the fallback (for execution when the 
> offloading fails). If I emulate this situation by writing this:
>
>
>
>   #ifdef __NVPTX__
>   int __nv_floor();
>   #endif
>  
>   int main() {
>   #pragma omp target
>   __nv_floor();
>   }
>   
>
> and try to compile using Clang with -fopenmp -fopenmp-targets=nvptx64, the 
> compilation fails:
>
>   int1.cpp:8:1: error: use of undeclared identifier '__nv_floor'
>   
>
> and this is because, when we invoke the compilation for the host, there is no 
> declaration for that function. This is true even though nvptx64 is the only 
> target for which the code is being compiled 

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea updated this revision to Diff 197911.
gtbercea added a comment.

- Address comments.
- Add math and cmath inclusion tests.
- Add driver test.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h
  test/CodeGen/nvptx_device_cmath_functions.c
  test/CodeGen/nvptx_device_math_functions.c
  test/Driver/openmp-offload-gpu.c

Index: test/Driver/openmp-offload-gpu.c
===
--- test/Driver/openmp-offload-gpu.c
+++ test/Driver/openmp-offload-gpu.c
@@ -278,3 +278,8 @@
 // RUN:   | FileCheck -check-prefix=CUDA_RED_RECS %s
 // CUDA_RED_RECS: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"
 // CUDA_RED_RECS-SAME: "-fopenmp-cuda-teams-reduction-recs-num=2048"
+
+// RUN:   %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
+// RUN:   | FileCheck -check-prefix=OPENMP_NVPTX_WRAPPERS %s
+// OPENMP_NVPTX_WRAPPERS: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"
+// OPENMP_NVPTX_WRAPPERS-SAME: "-internal-isystem" "{{.*}}openmp_wrappers"
Index: test/CodeGen/nvptx_device_math_functions.c
===
--- /dev/null
+++ test/CodeGen/nvptx_device_math_functions.c
@@ -0,0 +1,24 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang -fmath-errno -S -emit-llvm -o - %s -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda | FileCheck -check-prefix CHECK-YES %s
+#include 
+
+void test_sqrt(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @llvm.nvvm.sqrt.rn.d(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__internal_accurate_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call double @llvm.nvvm.trunc.d(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.lo(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call double @llvm.nvvm.lohi.i2d(i32
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: test/CodeGen/nvptx_device_cmath_functions.c
===
--- /dev/null
+++ test/CodeGen/nvptx_device_cmath_functions.c
@@ -0,0 +1,24 @@
+// Test calling of device math functions.
+///==///
+
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang++ -fmath-errno -S -emit-llvm -o - %s -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda | FileCheck -check-prefix CHECK-YES %s
+#include 
+
+void test_math_funcs(double a1) {
+  #pragma omp target
+  {
+// CHECK-YES: call double @llvm.nvvm.sqrt.rn.d(double
+double l1 = sqrt(a1);
+// CHECK-YES: call double @__internal_accurate_pow(double
+double l2 = pow(a1, a1);
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call double @llvm.nvvm.trunc.d(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.lo(double
+// CHECK-YES: call i32 @llvm.nvvm.d2i.hi(double
+// CHECK-YES: call double @llvm.nvvm.lohi.i2d(i32
+double l3 = modf(a1 + 3.5, );
+  }
+}
Index: lib/Headers/openmp_wrappers/math.h
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/math.h
@@ -0,0 +1,17 @@
+/*===- math.h - Alternative math.h header --===
+ *
+ * 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
+ *
+ *===---===
+ */
+
+#include <__clang_openmp_math.h>
+
+#ifndef __CLANG_NO_HOST_MATH__
+#include_next 
+#else
+#undef __CLANG_NO_HOST_MATH__
+#endif
+
Index: lib/Headers/openmp_wrappers/cmath
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/cmath
@@ -0,0 +1,16 @@
+/*===-- cmath - Alternative cmath header ---===
+ *
+ * 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
+ *
+ *===---===
+ */
+

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Hal Finkel via Phabricator via cfe-commits]

hfinkel added a comment.

In D61399#1488366 , @ABataev wrote:

> In D61399#1488329 , @hfinkel wrote:
>
> > In D61399#1488309 , @ABataev wrote:
> >
> > > In D61399#1488299 , @hfinkel 
> > > wrote:
> > >
> > > > In D61399#1488262 , @ABataev 
> > > > wrote:
> > > >
> > > > > I don't like this implementation. Seems to me, it breaks one of the 
> > > > > OpenMP standard requirements: the program can be compiled without 
> > > > > openmp support. I assume, that with this includes the program won't 
> > > > > be able to be compiled without OpenMP support anymore because it may 
> > > > > use some device-specific math functions explicitly.
> > > > >  Instead, I would like to see some additional, device-scpecific math 
> > > > > header file, that must be included explicitly to support some 
> > > > > device-specific math functions. And we need to provide default 
> > > > > implementations for those extra math functions for all the platforms 
> > > > > we're going to support, including default host implementations.
> > > >
> > > >
> > > > Can you provide an example of a conforming program that can't be 
> > > > compiled without OpenMP support? Regardless of the use of any 
> > > > device-specific functions (which isn't covered by the standard, of 
> > > > course, but might be needed in practice), the code still needs to be 
> > > > compilable by the host in order to generate the host-fallback version. 
> > > > This doesn't change that. Thus, any program that uses anything from 
> > > > this math.h, etc. needs to compile for the host, and thus, likely 
> > > > compiles without OpenMP support. Maybe I'm missing your point, however.
> > >
> > >
> > > Assume we have something like this:
> > >
> > >   #pragma omp target if(cond)
> > >   a = __nv_();
> > >
> > >
> > > Instead of `__nv_xxx` you can try to use any Cuda-specific function, 
> > > which is not the part of the standard `math.h`/`cmath` files. Will it be 
> > > compilable even with OpenMP?
> >
> >
> > I don't think that this changes that one way or the other. Your example 
> > won't work, AFAIK, unless you do something like:
> >
> >   #pragma omp target if(cond)
> >   #ifdef __NVPTX__
> >   a = __nv_();
> >   #else
> >   a = something_on_the_host;
> >   #endif
> >   
> >
> > and anything from these headers that doesn't also have a host version will 
> > suffer the same fate: if it won't also compile for the host (one way or 
> > another), then it won't work.
>
>
> The problem with this header file is that it allows to use those 
> Cuda-specific functions unconditionally in some cases:
>
>   #pragma omp target
>   a = __nv_();
>
>
> It won't require any target-specific guards to compile this code (if we 
> compile it only for Cuda-specific devices) and we're loosing the consistency 
> here: in some cases target regions will require special device guards, in 
> others, with the same function calls, it is not. And the worst thing, is that 
> we implicitly allow to introduce this kind of incostistency into users code. 
> That's why I would prefer to see a special kind of the include file, NVPTX 
> specific, that must be included explicitly, so the user explictly commanded 
> to use some target-specific math functions, if he really wants it. Plus, 
> maybe, in this files we need force check of the platform and warn users that 
> the functions from this header file must be used using device-specific 
> checks. Or provide some kind of the default implementations for all the 
> platforms, that do not support those math function natively.


I believe that I understand your point, but two things:

1. I think that you're mistaken on the underlying premise. That code will not 
meaningfully compile without ifdefs, even if only CUDA-specific devices are the 
only ones selected. We *always* compile code for the host as well, not for 
offloading proper, but for the fallback (for execution when the offloading 
fails). If I emulate this situation by writing this:



  #ifdef __NVPTX__
  int __nv_floor();
  #endif
  
  int main() {
  #pragma omp target
  __nv_floor();
  }

and try to compile using Clang with -fopenmp -fopenmp-targets=nvptx64, the 
compilation fails:

  int1.cpp:8:1: error: use of undeclared identifier '__nv_floor'

and this is because, when we invoke the compilation for the host, there is no 
declaration for that function. This is true even though nvptx64 is the only 
target for which the code is being compiled (because we always also compile the 
host fallback).

2. I believe that the future state -- what we get by following this patch, and 
then when declare variant is available using that -- gives us all what we want. 
When we have declare variant, then all of the definitions in these headers will 
be declared as variants only 

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Alexey Bataev via Phabricator via cfe-commits]

ABataev added a comment.

In D61399#1488329 , @hfinkel wrote:

> In D61399#1488309 , @ABataev wrote:
>
> > In D61399#1488299 , @hfinkel wrote:
> >
> > > In D61399#1488262 , @ABataev 
> > > wrote:
> > >
> > > > I don't like this implementation. Seems to me, it breaks one of the 
> > > > OpenMP standard requirements: the program can be compiled without 
> > > > openmp support. I assume, that with this includes the program won't be 
> > > > able to be compiled without OpenMP support anymore because it may use 
> > > > some device-specific math functions explicitly.
> > > >  Instead, I would like to see some additional, device-scpecific math 
> > > > header file, that must be included explicitly to support some 
> > > > device-specific math functions. And we need to provide default 
> > > > implementations for those extra math functions for all the platforms 
> > > > we're going to support, including default host implementations.
> > >
> > >
> > > Can you provide an example of a conforming program that can't be compiled 
> > > without OpenMP support? Regardless of the use of any device-specific 
> > > functions (which isn't covered by the standard, of course, but might be 
> > > needed in practice), the code still needs to be compilable by the host in 
> > > order to generate the host-fallback version. This doesn't change that. 
> > > Thus, any program that uses anything from this math.h, etc. needs to 
> > > compile for the host, and thus, likely compiles without OpenMP support. 
> > > Maybe I'm missing your point, however.
> >
> >
> > Assume we have something like this:
> >
> >   #pragma omp target if(cond)
> >   a = __nv_();
> >
> >
> > Instead of `__nv_xxx` you can try to use any Cuda-specific function, which 
> > is not the part of the standard `math.h`/`cmath` files. Will it be 
> > compilable even with OpenMP?
>
>
> I don't think that this changes that one way or the other. Your example won't 
> work, AFAIK, unless you do something like:
>
>   #pragma omp target if(cond)
>   #ifdef __NVPTX__
>   a = __nv_();
>   #else
>   a = something_on_the_host;
>   #endif
>   
>
> and anything from these headers that doesn't also have a host version will 
> suffer the same fate: if it won't also compile for the host (one way or 
> another), then it won't work.


The problem with this header file is that it allows to use those Cuda-specific 
functions unconditionally in some cases:

  #pragma omp target
  a = __nv_();

It won't require any target-specific guards to compile this code (if we compile 
it only for Cuda-specific devices) and we're loosing the consistency here: in 
some cases target regions will require special device guards, in others, with 
the same function calls, it is not. And the worst thing, is that we implicitly 
allow to introduce this kind of incostistency into users code. That's why I 
would prefer to see a special kind of the include file, NVPTX specific, that 
must be included explicitly, so the user explictly commanded to use some 
target-specific math functions, if he really wants it. Plus, maybe, in this 
files we need force check of the platform and warn users that the functions 
from this header file must be used using device-specific checks. Or provide 
some kind of the default implementations for all the platforms, that do not 
support those math function natively.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Hal Finkel via Phabricator via cfe-commits]

hfinkel added a comment.

In D61399#1488309 , @ABataev wrote:

> In D61399#1488299 , @hfinkel wrote:
>
> > In D61399#1488262 , @ABataev wrote:
> >
> > > I don't like this implementation. Seems to me, it breaks one of the 
> > > OpenMP standard requirements: the program can be compiled without openmp 
> > > support. I assume, that with this includes the program won't be able to 
> > > be compiled without OpenMP support anymore because it may use some 
> > > device-specific math functions explicitly.
> > >  Instead, I would like to see some additional, device-scpecific math 
> > > header file, that must be included explicitly to support some 
> > > device-specific math functions. And we need to provide default 
> > > implementations for those extra math functions for all the platforms 
> > > we're going to support, including default host implementations.
> >
> >
> > Can you provide an example of a conforming program that can't be compiled 
> > without OpenMP support? Regardless of the use of any device-specific 
> > functions (which isn't covered by the standard, of course, but might be 
> > needed in practice), the code still needs to be compilable by the host in 
> > order to generate the host-fallback version. This doesn't change that. 
> > Thus, any program that uses anything from this math.h, etc. needs to 
> > compile for the host, and thus, likely compiles without OpenMP support. 
> > Maybe I'm missing your point, however.
>
>
> Assume we have something like this:
>
>   #pragma omp target if(cond)
>   a = __nv_();
>
>
> Instead of `__nv_xxx` you can try to use any Cuda-specific function, which is 
> not the part of the standard `math.h`/`cmath` files. Will it be compilable 
> even with OpenMP?


I don't think that this changes that one way or the other. Your example won't 
work, AFAIK, unless you do something like:

  #pragma omp target if(cond)
  #ifdef __NVPTX__
  a = __nv_();
  #else
  a = something_on_the_host;
  #endif

and anything from these headers that doesn't also have a host version will 
suffer the same fate: if it won't also compile for the host (one way or 
another), then it won't work.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Alexey Bataev via Phabricator via cfe-commits]

ABataev added a comment.

In D61399#1488299 , @hfinkel wrote:

> In D61399#1488262 , @ABataev wrote:
>
> > I don't like this implementation. Seems to me, it breaks one of the OpenMP 
> > standard requirements: the program can be compiled without openmp support. 
> > I assume, that with this includes the program won't be able to be compiled 
> > without OpenMP support anymore because it may use some device-specific math 
> > functions explicitly.
> >  Instead, I would like to see some additional, device-scpecific math header 
> > file, that must be included explicitly to support some device-specific math 
> > functions. And we need to provide default implementations for those extra 
> > math functions for all the platforms we're going to support, including 
> > default host implementations.
>
>
> Can you provide an example of a conforming program that can't be compiled 
> without OpenMP support? Regardless of the use of any device-specific 
> functions (which isn't covered by the standard, of course, but might be 
> needed in practice), the code still needs to be compilable by the host in 
> order to generate the host-fallback version. This doesn't change that. Thus, 
> any program that uses anything from this math.h, etc. needs to compile for 
> the host, and thus, likely compiles without OpenMP support. Maybe I'm missing 
> your point, however.


Assume we have something like this:

  #pragma omp target if(cond)
  a = __nv_();

Instead of `__nv_xxx` you can try to use any Cuda-specific function, which is 
not the part of the standard `math.h`/`cmath` files. Will it be compilable even 
with OpenMP?


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Hal Finkel via Phabricator via cfe-commits]

hfinkel added a comment.

In D61399#1488262 , @ABataev wrote:

> I don't like this implementation. Seems to me, it breaks one of the OpenMP 
> standard requirements: the program can be compiled without openmp support. I 
> assume, that with this includes the program won't be able to be compiled 
> without OpenMP support anymore because it may use some device-specific math 
> functions explicitly.
>  Instead, I would like to see some additional, device-scpecific math header 
> file, that must be included explicitly to support some device-specific math 
> functions. And we need to provide default implementations for those extra 
> math functions for all the platforms we're going to support, including 
> default host implementations.


Can you provide an example of a conforming program that can't be compiled 
without OpenMP support? Regardless of the use of any device-specific functions 
(which isn't covered by the standard, of course, but might be needed in 
practice), the code still needs to be compilable by the host in order to 
generate the host-fallback version. This doesn't change that. Thus, any program 
that uses anything from this math.h, etc. needs to compile for the host, and 
thus, likely compiles without OpenMP support. Maybe I'm missing your point, 
however.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Alexey Bataev via Phabricator via cfe-commits]

ABataev added a comment.

Moreover, I think this will cause troubles even in simple cases. Assume we have 
`target if(cond)` construct. In this case we will need to compile the target 
region for both, the device and the host. If the target region uses some 
device-specific math functions, it will break the compilation for the host.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Alexey Bataev via Phabricator via cfe-commits]

ABataev added a comment.

I don't like this implementation. Seems to me, it breaks one of the OpenMP 
standard requirements: the program can be compiled without openmp support. I 
assume, that with this includes the program won't be able to be compiled 
without OpenMP support anymore because it may use some device-specific math 
functions explicitly.
Instead, I would like to see some additional, device-scpecific math header 
file, that must be included explicitly to support some device-specific math 
functions. And we need to provide default implementations for those extra math 
functions for all the platforms we're going to support, including default host 
implementations.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Hal Finkel via Phabricator via cfe-commits]

hfinkel accepted this revision.
hfinkel added inline comments.
This revision is now accepted and ready to land.



Comment at: lib/Driver/ToolChains/Clang.cpp:1163
+  llvm::sys::path::append(P, "openmp_wrappers");
+  CmdArgs.push_back("-internal-isystem");
+  CmdArgs.push_back(Args.MakeArgString(P));

Please add a driver test covering this.



Comment at: lib/Headers/openmp_wrappers/__clang_openmp_math.h:20
+/// respectively. This is actually what the Clang-CUDA code path does, using
+/// __device__ instead of variants to avoid redeclarations and get the desired
+/// overload resolution.

And this is why I wanted to just make `__device__` work in OpenMP mode. But, as 
a temporary solution until we get `declare variant` working, I'm okay with this.

Modulo the naming nit and the missing driver test, LGTM.



Comment at: lib/Headers/openmp_wrappers/__clang_openmp_math.h:46
+/// Magic macro for stopping the math.h/cmath host header from being included.
+#define __NO_HOST_MATH__
+

I'd prefer that, as this is clang specific, we make this clear by naming this 
`__CLANG_NO_HOST_MATH__`.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea updated this revision to Diff 197798.
gtbercea added a comment.

- Clean-up. Add header.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h

Index: lib/Headers/openmp_wrappers/math.h
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/math.h
@@ -0,0 +1,17 @@
+/*===- math.h - Alternative math.h header --===
+ *
+ * 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
+ *
+ *===---===
+ */
+
+#include <__clang_openmp_math.h>
+
+#ifndef __NO_HOST_MATH__
+#include_next 
+#else
+#undef __NO_HOST_MATH__
+#endif
+
Index: lib/Headers/openmp_wrappers/cmath
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/cmath
@@ -0,0 +1,16 @@
+/*===-- cmath - Alternative cmath header ---===
+ *
+ * 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
+ *
+ *===---===
+ */
+
+#include <__clang_openmp_math.h>
+
+#ifndef __NO_HOST_MATH__
+#include_next 
+#else
+#undef __NO_HOST_MATH__
+#endif
Index: lib/Headers/openmp_wrappers/__clang_openmp_math.h
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/__clang_openmp_math.h
@@ -0,0 +1,49 @@
+/*=== __clang_openmp_math.h - OpenMP target math support ---===
+ *
+ * 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
+ *
+ *===---===
+ */
+
+#if defined(__NVPTX__) && defined(_OPENMP)
+/// TODO:
+/// We are currently reusing the functionality of the Clang-CUDA code path
+/// as an alternative to the host declarations provided by math.h and cmath.
+/// This is suboptimal.
+///
+/// We should instead declare the device functions in a similar way, e.g.,
+/// through OpenMP 5.0 variants, and afterwards populate the module with the
+/// host declarations by unconditionally including the host math.h or cmath,
+/// respectively. This is actually what the Clang-CUDA code path does, using
+/// __device__ instead of variants to avoid redeclarations and get the desired
+/// overload resolution.
+
+#define __CUDA__
+
+#if defined(__cplusplus)
+  #include <__clang_cuda_math_forward_declares.h>
+#endif
+
+// CUDA 9.1 no longer provides declarations for libdevice functions, so we need
+// to provide our own.
+#include <__clang_cuda_libdevice_declares.h>
+
+// Wrappers for many device-side standard library functions became compiler
+// builtins in CUDA-9 and have been removed from the CUDA headers. Clang now
+// provides its own implementation of the wrappers.
+// #if CUDA_VERSION >= 9000
+#include <__clang_cuda_device_functions.h>
+
+#if defined(__cplusplus)
+  #include <__clang_cuda_cmath.h>
+#endif
+
+#undef __CUDA__
+
+/// Magic macro for stopping the math.h/cmath host header from being included.
+#define __NO_HOST_MATH__
+
+#endif
+
Index: lib/Headers/__clang_cuda_math_forward_declares.h
===
--- lib/Headers/__clang_cuda_math_forward_declares.h
+++ lib/Headers/__clang_cuda_math_forward_declares.h
@@ -20,8 +20,12 @@
 // would preclude the use of our own __device__ overloads for these functions.
 
 #pragma push_macro("__DEVICE__")
+#ifdef _OPENMP
+#define __DEVICE__ static __inline__ __attribute__((always_inline))
+#else
 #define __DEVICE__ \
   static __inline__ __attribute__((always_inline)) __attribute__((device))
+#endif
 
 __DEVICE__ double abs(double);
 __DEVICE__ float abs(float);
Index: lib/Headers/__clang_cuda_libdevice_declares.h
===
--- lib/Headers/__clang_cuda_libdevice_declares.h
+++ lib/Headers/__clang_cuda_libdevice_declares.h
@@ -10,443 +10,453 @@
 #ifndef __CLANG_CUDA_LIBDEVICE_DECLARES_H__
 #define __CLANG_CUDA_LIBDEVICE_DECLARES_H__
 
+#if 

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Johannes Doerfert via Phabricator via cfe-commits]

jdoerfert added inline comments.



Comment at: lib/Headers/openmp_wrappers/__clang_openmp_math.h:29
+
+#define __forceinline__ __attribute__((always_inline))
+

I think this is a leftover we forgot to remove.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Johannes Doerfert via Phabricator via cfe-commits]

jdoerfert added a comment.

For the record, this is an implementation of the scheme proposed in 
https://reviews.llvm.org/D60907#1484756.
There are drawbacks, see the TODO, but it will give most people a short term 
solution until we get OpenMP 5.0 variants.

Finally, there is a remote chance this will cause trouble to people that use 
math.h/cmath functions, e.g. with the old SSE hack, which are not available 
anymore.
I don't suspect that to happen but if it does we can, again as a short term 
solution, selectively extract declarations from the host cmath into the device 
cmath.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399



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

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea updated this revision to Diff 197638.
gtbercea edited the summary of this revision.
gtbercea added a comment.

- Minor fixes.


Repository:
  rC Clang

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D61399/new/

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h

Index: lib/Headers/openmp_wrappers/math.h
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/math.h
@@ -0,0 +1,10 @@
+// File: clang/lib/Headers/math.h
+
+#include <__clang_openmp_math.h>
+
+#ifndef __NO_HOST_MATH__
+#include_next 
+#else
+#undef __NO_HOST_MATH__
+#endif
+
Index: lib/Headers/openmp_wrappers/cmath
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/cmath
@@ -0,0 +1,7 @@
+#include <__clang_openmp_math.h>
+
+#ifndef __NO_HOST_MATH__
+#include_next 
+#else
+#undef __NO_HOST_MATH__
+#endif
Index: lib/Headers/openmp_wrappers/__clang_openmp_math.h
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/__clang_openmp_math.h
@@ -0,0 +1,51 @@
+/*=== __clang_openmp_math.h - OpenMP target math support ---===
+ *
+ * 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
+ *
+ *===---===
+ */
+
+#if defined(__NVPTX__) && defined(_OPENMP)
+/// TODO:
+/// We are currently reusing the functionality of the Clang-CUDA code path
+/// as an alternative to the host declarations provided by math.h and cmath.
+/// This is suboptimal.
+///
+/// We should instead declare the device functions in a similar way, e.g.,
+/// through OpenMP 5.0 variants, and afterwards populate the module with the
+/// host declarations by unconditionally including the host math.h or cmath,
+/// respectively. This is actually what the Clang-CUDA code path does, using
+/// __device__ instead of variants to avoid redeclarations and get the desired
+/// overload resolution.
+
+#define __CUDA__
+
+#if defined(__cplusplus)
+  #include <__clang_cuda_math_forward_declares.h>
+#endif
+
+#define __forceinline__ __attribute__((always_inline))
+
+// CUDA 9.1 no longer provides declarations for libdevice functions, so we need
+// to provide our own.
+#include <__clang_cuda_libdevice_declares.h>
+
+// Wrappers for many device-side standard library functions became compiler
+// builtins in CUDA-9 and have been removed from the CUDA headers. Clang now
+// provides its own implementation of the wrappers.
+// #if CUDA_VERSION >= 9000
+#include <__clang_cuda_device_functions.h>
+
+#if defined(__cplusplus)
+  #include <__clang_cuda_cmath.h>
+#endif
+
+#undef __CUDA__
+
+/// Magic macro for stopping the math.h/cmath host header from being included.
+#define __NO_HOST_MATH__
+
+#endif
+
Index: lib/Headers/__clang_cuda_math_forward_declares.h
===
--- lib/Headers/__clang_cuda_math_forward_declares.h
+++ lib/Headers/__clang_cuda_math_forward_declares.h
@@ -20,8 +20,12 @@
 // would preclude the use of our own __device__ overloads for these functions.
 
 #pragma push_macro("__DEVICE__")
+#ifdef _OPENMP
+#define __DEVICE__ static __inline__ __attribute__((always_inline))
+#else
 #define __DEVICE__ \
   static __inline__ __attribute__((always_inline)) __attribute__((device))
+#endif
 
 __DEVICE__ double abs(double);
 __DEVICE__ float abs(float);
Index: lib/Headers/__clang_cuda_libdevice_declares.h
===
--- lib/Headers/__clang_cuda_libdevice_declares.h
+++ lib/Headers/__clang_cuda_libdevice_declares.h
@@ -10,443 +10,453 @@
 #ifndef __CLANG_CUDA_LIBDEVICE_DECLARES_H__
 #define __CLANG_CUDA_LIBDEVICE_DECLARES_H__
 
+#if defined(__cplusplus)
 extern "C" {
+#endif
 
-__device__ int __nv_abs(int __a);
-__device__ double __nv_acos(double __a);
-__device__ float __nv_acosf(float __a);
-__device__ double __nv_acosh(double __a);
-__device__ float __nv_acoshf(float __a);
-__device__ double __nv_asin(double __a);
-__device__ float __nv_asinf(float __a);
-__device__ double __nv_asinh(double __a);
-__device__ float __nv_asinhf(float __a);
-__device__ double __nv_atan2(double __a, double __b);
-__device__ float __nv_atan2f(float __a, float __b);
-__device__ double __nv_atan(double __a);
-__device__ float __nv_atanf(float __a);
-__device__ double __nv_atanh(double 

[PATCH] D61399: [OpenMP][Clang] Support for target math functions

[Gheorghe-Teodor Bercea via Phabricator via cfe-commits]

gtbercea created this revision.
gtbercea added reviewers: hfinkel, caomhin, ABataev, tra.
Herald added subscribers: cfe-commits, guansong, mgorny.
Herald added a project: clang.

In this patch we propose a temporary solution to resolving math functions for 
the NVPTX toolchain, temporary until OpenMP variant is supported by Clang.

We intercept the inclusion of math.h and cmath headers and if we are in the 
OpenMP-NVPTX case, we re-use CUDA's math function resolution mechanism.

Authors:
gbercea
@jdoerfert


Repository:
  rC Clang

https://reviews.llvm.org/D61399

Files:
  lib/Driver/ToolChains/Clang.cpp
  lib/Headers/CMakeLists.txt
  lib/Headers/__clang_cuda_cmath.h
  lib/Headers/__clang_cuda_device_functions.h
  lib/Headers/__clang_cuda_libdevice_declares.h
  lib/Headers/__clang_cuda_math_forward_declares.h
  lib/Headers/openmp_wrappers/__clang_openmp_math.h
  lib/Headers/openmp_wrappers/cmath
  lib/Headers/openmp_wrappers/math.h

Index: lib/Headers/openmp_wrappers/math.h
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/math.h
@@ -0,0 +1,9 @@
+// File: clang/lib/Headers/math.h
+
+#include <__clang_openmp_math.h>
+
+#ifndef __NO_HOST_MATH__
+#include_next 
+#else
+#undef __NO_HOST_MATH__
+#endif
\ No newline at end of file
Index: lib/Headers/openmp_wrappers/cmath
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/cmath
@@ -0,0 +1,7 @@
+#include <__clang_openmp_math.h>
+
+#ifndef __NO_HOST_MATH__
+#include_next 
+#else
+#undef __NO_HOST_MATH__
+#endif
Index: lib/Headers/openmp_wrappers/__clang_openmp_math.h
===
--- /dev/null
+++ lib/Headers/openmp_wrappers/__clang_openmp_math.h
@@ -0,0 +1,50 @@
+/*=== __clang_openmp_math.h - OpenMP target math support ---===
+ *
+ * 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
+ *
+ *===---===
+ */
+
+#if defined(__NVPTX__) && defined(_OPENMP)
+/// TODO:
+/// We are currently reusing the functionality of the Clang-CUDA code path
+/// as an alternative to the host declarations provided by math.h and cmath.
+/// This is suboptimal.
+///
+/// We should instead declare the device functions in a similar way, e.g.,
+/// through OpenMP 5.0 variants, and afterwards populate the module with the
+/// host declarations by unconditionally including the host math.h or cmath,
+/// respectively. This is actually what the Clang-CUDA code path does, using
+/// __device__ instead of variants to avoid redeclarations and get the desired
+/// overload resolution.
+
+#define __CUDA__
+
+#if defined(__cplusplus)
+  #include <__clang_cuda_math_forward_declares.h>
+#endif
+
+#define __forceinline__ __attribute__((always_inline))
+
+// CUDA 9.1 no longer provides declarations for libdevice functions, so we need
+// to provide our own.
+#include <__clang_cuda_libdevice_declares.h>
+
+// Wrappers for many device-side standard library functions became compiler
+// builtins in CUDA-9 and have been removed from the CUDA headers. Clang now
+// provides its own implementation of the wrappers.
+// #if CUDA_VERSION >= 9000
+#include <__clang_cuda_device_functions.h>
+
+#if defined(__cplusplus)
+  #include <__clang_cuda_cmath.h>
+#endif
+
+#undef __CUDA__
+
+/// Magic macro for stopping the math.h/cmath host header from being included.
+#define __NO_HOST_MATH__
+
+#endif
\ No newline at end of file
Index: lib/Headers/__clang_cuda_math_forward_declares.h
===
--- lib/Headers/__clang_cuda_math_forward_declares.h
+++ lib/Headers/__clang_cuda_math_forward_declares.h
@@ -20,8 +20,12 @@
 // would preclude the use of our own __device__ overloads for these functions.
 
 #pragma push_macro("__DEVICE__")
+#ifdef _OPENMP
+#define __DEVICE__ static __inline__ __attribute__((always_inline))
+#else
 #define __DEVICE__ \
   static __inline__ __attribute__((always_inline)) __attribute__((device))
+#endif
 
 __DEVICE__ double abs(double);
 __DEVICE__ float abs(float);
Index: lib/Headers/__clang_cuda_libdevice_declares.h
===
--- lib/Headers/__clang_cuda_libdevice_declares.h
+++ lib/Headers/__clang_cuda_libdevice_declares.h
@@ -10,443 +10,453 @@
 #ifndef __CLANG_CUDA_LIBDEVICE_DECLARES_H__
 #define __CLANG_CUDA_LIBDEVICE_DECLARES_H__
 
+#if defined(__cplusplus)
 extern "C" {
+#endif
 
-__device__ int __nv_abs(int __a);
-__device__ double __nv_acos(double __a);
-__device__ float __nv_acosf(float __a);
-__device__ double __nv_acosh(double __a);
-__device__ float __nv_acoshf(float __a);
-__device__ double __nv_asin(double