Skip to content

[CUDA] Add support for sm101 and sm120 target architectures #127187

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Feb 19, 2025
Merged

[CUDA] Add support for sm101 and sm120 target architectures #127187

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
a55c76b
Add support for sm101 target architecture (Tegra Blackwell)
Feb 14, 2025
af2bf2f
Add support for sm120 as well.
Feb 14, 2025
e01df6d
Code style fixes - part1.
Feb 17, 2025
6d5688e
Code style fixes - part2.
Feb 18, 2025
e4a639f
Merge branch 'main' into users/jodelek/sm101
jodelek Feb 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions clang/include/clang/Basic/BuiltinsNVPTX.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,12 +21,14 @@ class SM<string version, list<SMFeatures> newer_list> : SMFeatures {
!strconcat(f, "|", newer.Features));
}

let Features = "sm_120a" in def SM_120a : SMFeatures;
let Features = "sm_101a" in def SM_101a : SMFeatures;
let Features = "sm_100a" in def SM_100a : SMFeatures;

def SM_100 : SM<"100", [SM_100a]>;

let Features = "sm_90a" in def SM_90a : SMFeatures;

def SM_120 : SM<"120", [SM_120a]>;
def SM_101 : SM<"101", [SM_101a, SM_120]>;
def SM_100 : SM<"100", [SM_100a, SM_101]>;
def SM_90 : SM<"90", [SM_90a, SM_100]>;
def SM_89 : SM<"89", [SM_90]>;
def SM_87 : SM<"87", [SM_89]>;
Expand Down
4 changes: 4 additions & 0 deletions clang/include/clang/Basic/Cuda.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,10 @@ enum class OffloadArch {
SM_90a,
SM_100,
SM_100a,
SM_101,
SM_101a,
SM_120,
SM_120a,
GFX600,
GFX601,
GFX602,
Expand Down
8 changes: 8 additions & 0 deletions clang/lib/Basic/Cuda.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,6 +100,10 @@ static const OffloadArchToStringMap arch_names[] = {
SM(90a), // Hopper
SM(100), // Blackwell
SM(100a), // Blackwell
SM(101), // Blackwell
SM(101a), // Blackwell
SM(120), // Blackwell
SM(120a), // Blackwell
GFX(600), // gfx600
GFX(601), // gfx601
GFX(602), // gfx602
Expand Down Expand Up @@ -230,6 +234,10 @@ CudaVersion MinVersionForOffloadArch(OffloadArch A) {
return CudaVersion::CUDA_120;
case OffloadArch::SM_100:
case OffloadArch::SM_100a:
case OffloadArch::SM_101:
case OffloadArch::SM_101a:
case OffloadArch::SM_120:
case OffloadArch::SM_120a:
return CudaVersion::CUDA_128;
default:
llvm_unreachable("invalid enum");
Expand Down
23 changes: 18 additions & 5 deletions clang/lib/Basic/Targets/NVPTX.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,7 +185,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,

if (Opts.CUDAIsDevice || Opts.OpenMPIsTargetDevice || !HostTarget) {
// Set __CUDA_ARCH__ for the GPU specified.
std::string CUDAArchCode = [this] {
llvm::StringRef CUDAArchCode = [this] {
switch (GPU) {
case OffloadArch::GFX600:
case OffloadArch::GFX601:
Expand Down Expand Up @@ -292,14 +292,27 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
case OffloadArch::SM_100:
case OffloadArch::SM_100a:
return "1000";
case OffloadArch::SM_101:
case OffloadArch::SM_101a:
return "1010";
case OffloadArch::SM_120:
case OffloadArch::SM_120a:
return "1200";
}
llvm_unreachable("unhandled OffloadArch");
}();
Builder.defineMacro("__CUDA_ARCH__", CUDAArchCode);
if (GPU == OffloadArch::SM_90a)
Builder.defineMacro("__CUDA_ARCH_FEAT_SM90_ALL", "1");
if (GPU == OffloadArch::SM_100a)
Builder.defineMacro("__CUDA_ARCH_FEAT_SM100_ALL", "1");
switch(GPU) {
case OffloadArch::SM_90a:
case OffloadArch::SM_100a:
case OffloadArch::SM_101a:
case OffloadArch::SM_120a:
Builder.defineMacro("__CUDA_ARCH_FEAT_SM" + CUDAArchCode.drop_back() + "_ALL", "1");
break;
default:
// Do nothing if this is not an enhanced architecture.
break;
}
}
}

Expand Down
4 changes: 4 additions & 0 deletions clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2278,6 +2278,10 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(const OMPRequiresDecl *D) {
case OffloadArch::SM_90a:
case OffloadArch::SM_100:
case OffloadArch::SM_100a:
case OffloadArch::SM_101:
case OffloadArch::SM_101a:
case OffloadArch::SM_120:
case OffloadArch::SM_120a:
case OffloadArch::GFX600:
case OffloadArch::GFX601:
case OffloadArch::GFX602:
Expand Down
4 changes: 4 additions & 0 deletions clang/test/Misc/target-invalid-cpu-note/nvptx.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,10 @@
// CHECK-SAME: {{^}}, sm_90a
// CHECK-SAME: {{^}}, sm_100
// CHECK-SAME: {{^}}, sm_100a
// CHECK-SAME: {{^}}, sm_101
// CHECK-SAME: {{^}}, sm_101a
// CHECK-SAME: {{^}}, sm_120
// CHECK-SAME: {{^}}, sm_120a
// CHECK-SAME: {{^}}, gfx600
// CHECK-SAME: {{^}}, gfx601
// CHECK-SAME: {{^}}, gfx602
Expand Down