[PATCH] D155213: [HIP] Add `-fno-offload-uniform-block`
yaxunl updated this revision to Diff 544812.
yaxunl marked an inline comment as done.
yaxunl added a reviewer: Anastasia.
yaxunl added a comment.
revised by comments
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D155213/new/
https://reviews.llvm.org/D155213
Files:
clang/include/clang/Basic/CodeGenOptions.def
clang/include/clang/Basic/LangOptions.def
clang/include/clang/Driver/Options.td
clang/lib/CodeGen/CGCall.cpp
clang/lib/CodeGen/Targets/AMDGPU.cpp
clang/lib/Driver/ToolChains/Clang.cpp
clang/test/CodeGenCUDA/amdgpu-kernel-attrs.cu
clang/test/CodeGenOpenCL/cl-uniform-wg-size.cl
clang/test/Driver/hip-options.hip
clang/test/Driver/opencl.cl
Index: clang/test/Driver/opencl.cl
===
--- clang/test/Driver/opencl.cl
+++ clang/test/Driver/opencl.cl
@@ -17,6 +17,8 @@
// RUN: %clang -S -### -cl-denorms-are-zero %s 2>&1 | FileCheck --check-prefix=CHECK-DENORMS-ARE-ZERO %s
// RUN: %clang -S -### -cl-fp32-correctly-rounded-divide-sqrt %s 2>&1 | FileCheck --check-prefix=CHECK-ROUND-DIV %s
// RUN: %clang -S -### -cl-uniform-work-group-size %s 2>&1 | FileCheck --check-prefix=CHECK-UNIFORM-WG %s
+// RUN: %clang -S -### -foffload-uniform-block %s 2>&1 | FileCheck --check-prefix=CHECK-UNIFORM-WG %s
+// RUN: %clang -S -### -fno-offload-uniform-block -cl-uniform-work-group-size %s 2>&1 | FileCheck --check-prefix=CHECK-UNIFORM-WG %s
// RUN: not %clang -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
// RUN: not %clang -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
// RUN: %clang -S -### -target spir-unknown-unknown %s 2>&1 | FileCheck --check-prefix=CHECK-W-SPIR-COMPAT %s
@@ -44,7 +46,7 @@
// CHECK-DENORMS-ARE-ZERO-NOT: "-cl-denorms-are-zero"
// CHECK-ROUND-DIV: "-cc1" {{.*}} "-cl-fp32-correctly-rounded-divide-sqrt"
-// CHECK-UNIFORM-WG: "-cc1" {{.*}} "-cl-uniform-work-group-size"
+// CHECK-UNIFORM-WG: "-cc1" {{.*}} "-foffload-uniform-block"
// CHECK-C99: error: invalid value 'c99' in '-cl-std=c99'
// CHECK-INVALID: error: invalid value 'invalid' in '-cl-std=invalid'
Index: clang/test/Driver/hip-options.hip
===
--- clang/test/Driver/hip-options.hip
+++ clang/test/Driver/hip-options.hip
@@ -205,3 +205,27 @@
// RUN: %clang -fdriver-only -Werror --target=x86_64-unknown-linux-gnu -nostdinc -nostdlib -fgpu-approx-transcendentals \
// RUN: -x c++ %s 2>&1 | count 0
+/ Check -fno-offload-uniform-block is passed to clang -cc1 but
+// (default) -fno-offload-uniform-block is not.
+
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -nogpuinc -nogpulib -fno-offload-uniform-block \
+// RUN: --cuda-gpu-arch=gfx906 %s 2>&1 | FileCheck -check-prefix=NOUNIBLK %s
+
+// NOUNIBLK: "-cc1"{{.*}} "-triple" "amdgcn-amd-amdhsa" {{.*}} "-fno-offload-uniform-block"
+// NOUNIBLK: "-cc1"{{.*}} "-triple" "x86_64-unknown-linux-gnu" {{.*}} "-fno-offload-uniform-block"
+
+// RUN: %clang -### -nogpuinc -nogpulib -foffload-uniform-block \
+// RUN: --cuda-gpu-arch=gfx906 %s 2>&1 | FileCheck -check-prefix=UNIBLK %s
+
+// UNIBLK: "-cc1"{{.*}} "-triple" "amdgcn-amd-amdhsa" {{.*}} "-foffload-uniform-block"
+// UNIBLK: "-cc1"{{.*}} "-triple" "x86_64-unknown-linux-gnu" {{.*}} "-foffload-uniform-block"
+
+// RUN: %clang -### -nogpuinc -nogpulib \
+// RUN: --cuda-gpu-arch=gfx906 %s 2>&1 | FileCheck -check-prefix=DEFUNIBLK %s
+
+// DEFUNIBLK-NOT: "-f{{(no-)?}}offload-uniform-block"
+
+// Check no warnings for -f[no-]offload-uniform-block.
+
+// RUN: %clang -fdriver-only -Werror --target=x86_64-unknown-linux-gnu -nogpuinc -nogpulib -fno-offload-uniform-block \
+// RUN: -foffload-uniform-block --cuda-gpu-arch=gfx906 %s 2>&1 | count 0
Index: clang/test/CodeGenOpenCL/cl-uniform-wg-size.cl
===
--- clang/test/CodeGenOpenCL/cl-uniform-wg-size.cl
+++ clang/test/CodeGenOpenCL/cl-uniform-wg-size.cl
@@ -1,6 +1,7 @@
// RUN: %clang_cc1 -emit-llvm -O0 -cl-std=CL1.2 -o - %s 2>&1 | FileCheck %s -check-prefixes CHECK,CHECK-UNIFORM
// RUN: %clang_cc1 -emit-llvm -O0 -cl-std=CL2.0 -o - %s 2>&1 | FileCheck %s -check-prefixes CHECK,CHECK-NONUNIFORM
// RUN: %clang_cc1 -emit-llvm -O0 -cl-std=CL2.0 -cl-uniform-work-group-size -o - %s 2>&1 | FileCheck %s -check-prefixes CHECK,CHECK-UNIFORM
+// RUN: %clang_cc1 -emit-llvm -O0 -cl-std=CL2.0 -foffload-uniform-block -o - %s 2>&1 | FileCheck %s -check-prefixes CHECK,CHECK-UNIFORM
kernel void ker() {};
// CHECK: define{{.*}}@ker() #0
Index: clang/test/CodeGenCUDA/amdgpu-kernel-attrs.cu
===
--- clang/test/CodeGenCUDA/amdgpu-kernel-attrs.cu
+++ clang/test/CodeGenCUDA/amdgpu-kernel-attrs.cu
@@ -10,10 +10,18 @@
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm \
// RUN: -verify -o - -x hip %s | FileCheck -check-prefix=NAMD %s
+// RUN: %clang_cc1 -triple
[PATCH] D155213: [HIP] Add `-fno-offload-uniform-block`
yaxunl marked an inline comment as done.
yaxunl added inline comments.
Comment at: clang/lib/CodeGen/CGCall.cpp:2391
if (TargetDecl->hasAttr()) {
if (getLangOpts().OpenCLVersion <= 120) {
scchan wrote:
> The block here needs to be aware of this new flag.
Now that `-foffload-uniform-block` has the same default value as
`-cl-uniform-work-group-size` for OpenCL. we can make
`-cl-uniform-work-group-size` an alias to `-foffload-uniform-block`. will update
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D155213/new/
https://reviews.llvm.org/D155213
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
[PATCH] D155213: [HIP] Add `-fno-offload-uniform-block`
scchan added inline comments.
Comment at: clang/lib/CodeGen/CGCall.cpp:2391
if (TargetDecl->hasAttr()) {
if (getLangOpts().OpenCLVersion <= 120) {
The block here needs to be aware of this new flag.
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D155213/new/
https://reviews.llvm.org/D155213
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
[PATCH] D155213: [HIP] Add `-fno-offload-uniform-block`
yaxunl updated this revision to Diff 544491.
yaxunl edited the summary of this revision.
yaxunl added a comment.
make the option generic for offloading languages
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D155213/new/
https://reviews.llvm.org/D155213
Files:
clang/include/clang/Basic/LangOptions.def
clang/include/clang/Driver/Options.td
clang/lib/CodeGen/CGCall.cpp
clang/lib/CodeGen/Targets/AMDGPU.cpp
clang/lib/Driver/ToolChains/Clang.cpp
clang/test/CodeGenCUDA/amdgpu-kernel-attrs.cu
clang/test/Driver/hip-options.hip
Index: clang/test/Driver/hip-options.hip
===
--- clang/test/Driver/hip-options.hip
+++ clang/test/Driver/hip-options.hip
@@ -205,3 +205,27 @@
// RUN: %clang -fdriver-only -Werror --target=x86_64-unknown-linux-gnu -nostdinc -nostdlib -fgpu-approx-transcendentals \
// RUN: -x c++ %s 2>&1 | count 0
+/ Check -fno-offload-uniform-block is passed to clang -cc1 but
+// (default) -fno-offload-uniform-block is not.
+
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -nogpuinc -nogpulib -fno-offload-uniform-block \
+// RUN: --cuda-gpu-arch=gfx906 %s 2>&1 | FileCheck -check-prefix=NOUNIBLK %s
+
+// NOUNIBLK: "-cc1"{{.*}} "-triple" "amdgcn-amd-amdhsa" {{.*}} "-fno-offload-uniform-block"
+// NOUNIBLK: "-cc1"{{.*}} "-triple" "x86_64-unknown-linux-gnu" {{.*}} "-fno-offload-uniform-block"
+
+// RUN: %clang -### -nogpuinc -nogpulib -foffload-uniform-block \
+// RUN: --cuda-gpu-arch=gfx906 %s 2>&1 | FileCheck -check-prefix=UNIBLK %s
+
+// UNIBLK: "-cc1"{{.*}} "-triple" "amdgcn-amd-amdhsa" {{.*}} "-foffload-uniform-block"
+// UNIBLK: "-cc1"{{.*}} "-triple" "x86_64-unknown-linux-gnu" {{.*}} "-foffload-uniform-block"
+
+// RUN: %clang -### -nogpuinc -nogpulib \
+// RUN: --cuda-gpu-arch=gfx906 %s 2>&1 | FileCheck -check-prefix=DEFUNIBLK %s
+
+// DEFUNIBLK-NOT: "-f{{(no-)?}}offload-uniform-block"
+
+// Check no warnings for -f[no-]offload-uniform-block.
+
+// RUN: %clang -fdriver-only -Werror --target=x86_64-unknown-linux-gnu -nogpuinc -nogpulib -fno-offload-uniform-block \
+// RUN: -foffload-uniform-block --cuda-gpu-arch=gfx906 %s 2>&1 | count 0
Index: clang/test/CodeGenCUDA/amdgpu-kernel-attrs.cu
===
--- clang/test/CodeGenCUDA/amdgpu-kernel-attrs.cu
+++ clang/test/CodeGenCUDA/amdgpu-kernel-attrs.cu
@@ -10,10 +10,18 @@
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm \
// RUN: -verify -o - -x hip %s | FileCheck -check-prefix=NAMD %s
+// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -foffload-uniform-block \
+// RUN: -fcuda-is-device -emit-llvm -o - -x hip %s \
+// RUN: | FileCheck -check-prefixes=CHECK,DEFAULT %s
+// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -fno-offload-uniform-block \
+// RUN: -fcuda-is-device -emit-llvm -o - -x hip %s \
+// RUN: | FileCheck -check-prefixes=NOUB %s
+
#include "Inputs/cuda.h"
__global__ void flat_work_group_size_default() {
// CHECK: define{{.*}} amdgpu_kernel void @_Z28flat_work_group_size_defaultv() [[FLAT_WORK_GROUP_SIZE_DEFAULT:#[0-9]+]]
+// NOUB: define{{.*}} void @_Z28flat_work_group_size_defaultv() [[NOUB:#[0-9]+]]
}
__attribute__((amdgpu_flat_work_group_size(32, 64))) // expected-no-diagnostics
@@ -45,3 +53,5 @@
// CHECK-DAG: attributes [[WAVES_PER_EU_2]] = {{.*}}"amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[NUM_SGPR_32]] = {{.*}}"amdgpu-num-sgpr"="32"
// CHECK-DAG: attributes [[NUM_VGPR_64]] = {{.*}}"amdgpu-num-vgpr"="64"
+
+// NOUB-NOT: "uniform-work-group-size"="true"
Index: clang/lib/Driver/ToolChains/Clang.cpp
===
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -7264,6 +7264,9 @@
Args.AddLastArg(CmdArgs, options::OPT_fgpu_default_stream_EQ);
}
+ Args.AddLastArg(CmdArgs, options::OPT_foffload_uniform_block,
+ options::OPT_fno_offload_uniform_block);
+
if (IsCudaDevice || IsHIPDevice) {
StringRef InlineThresh =
Args.getLastArgValue(options::OPT_fgpu_inline_threshold_EQ);
Index: clang/lib/CodeGen/Targets/AMDGPU.cpp
===
--- clang/lib/CodeGen/Targets/AMDGPU.cpp
+++ clang/lib/CodeGen/Targets/AMDGPU.cpp
@@ -401,13 +401,6 @@
if (FD)
setFunctionDeclAttributes(FD, F, M);
- const bool IsHIPKernel =
- M.getLangOpts().HIP && FD && FD->hasAttr();
-
- // TODO: This should be moved to language specific attributes instead.
- if (IsHIPKernel)
-F->addFnAttr("uniform-work-group-size", "true");
-
if (M.getContext().getTargetInfo().allowAMDGPUUnsafeFPAtomics())
F->addFnAttr("amdgpu-unsafe-fp-atomics", "true");
Index: clang/lib/CodeGen/CGCall.cpp
===
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -2402,6 +2402,10 @@
[PATCH] D155213: [HIP] Add `-fno-offload-uniform-block`
jdoerfert added a comment. This should be named -foffload*, it should not use HIP in the description, and it should apply to OpenMP as well. CHANGES SINCE LAST ACTION https://reviews.llvm.org/D155213/new/ https://reviews.llvm.org/D155213 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
[PATCH] D155213: [HIP] Add `-fno-offload-uniform-block`
yaxunl added a comment. ping I renamed the option as `-fno-offload-uniform-block`. I switched to `offload` instead of `gpu` because I think in the long run offloading toolchains are not limited to GPUs, therefore sooner or later we will feel `-fgpu-` options are awkward. I did not use `--no-offload-uniform-block` because Options.td does not allow marshalling `--` prefixed options. It needs considerable change to some basic multiclass to achieve that and that would break quite a few established conventions. Therefore I feel it is better to follow the convention. CHANGES SINCE LAST ACTION https://reviews.llvm.org/D155213/new/ https://reviews.llvm.org/D155213 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
[PATCH] D155213: [HIP] Add `-fno-offload-uniform-block`
yaxunl updated this revision to Diff 544345.
yaxunl retitled this revision from "[HIP] Add `-fno-hip-uniform-block`" to
"[HIP] Add `-fno-offload-uniform-block`".
yaxunl edited the summary of this revision.
yaxunl added a comment.
rename the option
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D155213/new/
https://reviews.llvm.org/D155213
Files:
clang/include/clang/Basic/LangOptions.def
clang/include/clang/Driver/Options.td
clang/lib/CodeGen/CGCall.cpp
clang/lib/CodeGen/Targets/AMDGPU.cpp
clang/lib/Driver/ToolChains/Clang.cpp
clang/test/CodeGenHIP/default-attributes.hip
clang/test/Driver/hip-options.hip
Index: clang/test/Driver/hip-options.hip
===
--- clang/test/Driver/hip-options.hip
+++ clang/test/Driver/hip-options.hip
@@ -205,3 +205,24 @@
// RUN: %clang -fdriver-only -Werror --target=x86_64-unknown-linux-gnu -nostdinc -nostdlib -fgpu-approx-transcendentals \
// RUN: -x c++ %s 2>&1 | count 0
+/ Check -fno-offload-uniform-block is passed to clang -cc1 but
+// (default) -fno-offload-uniform-block is not.
+
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -nogpuinc -nogpulib -fno-offload-uniform-block \
+// RUN: --cuda-gpu-arch=gfx906 %s 2>&1 | FileCheck -check-prefix=NOUNIBLK %s
+
+// NOUNIBLK: "-cc1"{{.*}} "-triple" "amdgcn-amd-amdhsa" {{.*}} "-fno-offload-uniform-block"
+// NOUNIBLK: "-cc1"{{.*}} "-triple" "x86_64-unknown-linux-gnu" {{.*}} "-fno-offload-uniform-block"
+
+// RUN: %clang -### -nogpuinc -nogpulib -foffload-uniform-block \
+// RUN: --cuda-gpu-arch=gfx906 %s 2>&1 | FileCheck -check-prefix=UNIBLK %s
+
+// RUN: %clang -### -nogpuinc -nogpulib \
+// RUN: --cuda-gpu-arch=gfx906 %s 2>&1 | FileCheck -check-prefix=UNIBLK %s
+
+// UNIBLK-NOT: "--{{(no-)?}}offload-uniform-block"
+
+// Check no warnings for --[no-]offload-uniform-block.
+
+// RUN: %clang -fdriver-only -Werror --target=x86_64-unknown-linux-gnu -nogpuinc -nogpulib -fno-offload-uniform-block \
+// RUN: -fno-offload-uniform-block --cuda-gpu-arch=gfx906 %s 2>&1 | count 0
Index: clang/test/CodeGenHIP/default-attributes.hip
===
--- clang/test/CodeGenHIP/default-attributes.hip
+++ clang/test/CodeGenHIP/default-attributes.hip
@@ -5,6 +5,9 @@
// RUN: %clang_cc1 -O3 -triple amdgcn-amd-amdhsa -x hip -fno-ident -fcuda-is-device \
// RUN:-emit-llvm -o - %s | FileCheck -check-prefix=OPT %s
+// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -x hip -fno-ident -fcuda-is-device -fno-offload-uniform-block \
+// RUN:-emit-llvm -o - %s | FileCheck -check-prefix=NOUNIBLK %s
+
#define __device__ __attribute__((device))
#define __global__ __attribute__((global))
@@ -20,6 +23,12 @@
// OPT-NEXT: entry:
// OPT-NEXT:ret void
//
+// NOUNIBLK: Function Attrs: convergent mustprogress noinline nounwind optnone
+// NOUNIBLK-LABEL: define {{[^@]+}}@_Z4funcv
+// NOUNIBLK-SAME: () #[[ATTR0:[0-9]+]] {
+// NOUNIBLK-NEXT: entry:
+// NOUNIBLK-NEXT:ret void
+//
__device__ void func() {
}
@@ -36,21 +45,34 @@
// OPT-NEXT: entry:
// OPT-NEXT:ret void
//
+// NOUNIBLK: Function Attrs: convergent mustprogress noinline norecurse nounwind optnone
+// NOUNIBLK-LABEL: define {{[^@]+}}@_Z6kernelv
+// NOUNIBLK-SAME: () #[[ATTR1:[0-9]+]] {
+// NOUNIBLK-NEXT: entry:
+// NOUNIBLK-NEXT:ret void
+//
__global__ void kernel() {
}
//.
-// OPTNONE: attributes #0 = { convergent mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
-// OPTNONE: attributes #1 = { convergent mustprogress noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,1024" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }
+// OPTNONE: attributes #[[ATTR0]] = { convergent mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+// OPTNONE: attributes #[[ATTR1]] = { convergent mustprogress noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,1024" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }
+//.
+// OPT: attributes #[[ATTR0]] = { mustprogress nofree norecurse nosync nounwind willreturn memory(none) "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+// OPT: attributes #[[ATTR1]] = { mustprogress nofree norecurse nosync nounwind willreturn memory(none) "amdgpu-flat-work-group-size"="1,1024" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "uniform-work-group-size"="true" }
+//.
+// NOUNIBLK: attributes #[[ATTR0]] = { convergent mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
+// NOUNIBLK: attributes #[[ATTR1]] = { convergent mustprogress noinline norecurse nounwind optnone "amdgpu-flat-work-group-size"="1,1024" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
//.
-// OPT: attributes #0 = { mustprogress nofree
