Skip to content

[flang][cuda] Add missing semi-colon in inlined ptx #166254

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 1 commit into from
Nov 3, 2025
Merged

[flang][cuda] Add missing semi-colon in inlined ptx #166254

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions flang/lib/Optimizer/Builder/IntrinsicCall.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9455,7 +9455,7 @@ void IntrinsicLibrary::genTMABulkS2G(llvm::ArrayRef<fir::ExtendedValue> args) {
builder, loc, dst, src, fir::getBase(args[2]), {}, {});

mlir::NVVM::InlinePtxOp::create(builder, loc, mlir::TypeRange{}, {}, {},
"cp.async.bulk.commit_group", {});
"cp.async.bulk.commit_group;", {});
mlir::NVVM::CpAsyncBulkWaitGroupOp::create(builder, loc,
builder.getI32IntegerAttr(0), {});
}
Expand All @@ -9471,7 +9471,7 @@ static void genTMABulkStore(fir::FirOpBuilder &builder, mlir::Location loc,
mlir::NVVM::CpAsyncBulkSharedCTAToGlobalOp::create(builder, loc, dst, src,
size, {}, {});
mlir::NVVM::InlinePtxOp::create(builder, loc, mlir::TypeRange{}, {}, {},
"cp.async.bulk.commit_group", {});
"cp.async.bulk.commit_group;", {});
mlir::NVVM::CpAsyncBulkWaitGroupOp::create(builder, loc,
builder.getI32IntegerAttr(0), {});
}
Expand Down
16 changes: 8 additions & 8 deletions flang/test/Lower/CUDA/cuda-device-proc.cuf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -490,7 +490,7 @@ end subroutine

! CHECK-LABEL: func.func @_QPtest_bulk_s2g
! CHECL: nvvm.cp.async.bulk.global.shared.cta %{{.*}}, %{{.*}}, %{{.*}} : <1>, <3>
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group"
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group;"
! CHECK: nvvm.cp.async.bulk.wait_group 0

attributes(device) subroutine testAtomicCasLoop(aa, n)
Expand Down Expand Up @@ -671,7 +671,7 @@ end subroutine

! CHECK-LABEL: func.func @_QPtest_tma_bulk_store_c4
! CHECK: nvvm.cp.async.bulk.global.shared.cta %{{.*}}, %{{.*}}, %{{.*}} : <1>, <3>
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group"
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group;"
! CHECK: nvvm.cp.async.bulk.wait_group 0

attributes(global) subroutine test_tma_bulk_store_c8(c, n)
Expand All @@ -684,7 +684,7 @@ end subroutine

! CHECK-LABEL: func.func @_QPtest_tma_bulk_store_c8
! CHECK: nvvm.cp.async.bulk.global.shared.cta %{{.*}}, %{{.*}}, %{{.*}} : <1>, <3>
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group"
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group;"
! CHECK: nvvm.cp.async.bulk.wait_group 0

attributes(global) subroutine test_tma_bulk_store_i4(c, n)
Expand All @@ -697,7 +697,7 @@ end subroutine

! CHECK-LABEL: func.func @_QPtest_tma_bulk_store_i4
! CHECK: nvvm.cp.async.bulk.global.shared.cta %{{.*}}, %{{.*}}, %{{.*}} : <1>, <3>
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group"
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group;"
! CHECK: nvvm.cp.async.bulk.wait_group 0

attributes(global) subroutine test_tma_bulk_store_i8(c, n)
Expand All @@ -710,7 +710,7 @@ end subroutine

! CHECK-LABEL: func.func @_QPtest_tma_bulk_store_i8
! CHECK: nvvm.cp.async.bulk.global.shared.cta %{{.*}}, %{{.*}}, %{{.*}} : <1>, <3>
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group"
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group;"
! CHECK: nvvm.cp.async.bulk.wait_group 0


Expand All @@ -724,7 +724,7 @@ end subroutine

! CHECK-LABEL: func.func @_QPtest_tma_bulk_store_r2
! CHECK: nvvm.cp.async.bulk.global.shared.cta %{{.*}}, %{{.*}}, %{{.*}} : <1>, <3>
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group"
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group;"
! CHECK: nvvm.cp.async.bulk.wait_group 0

attributes(global) subroutine test_tma_bulk_store_r4(c, n)
Expand All @@ -737,7 +737,7 @@ end subroutine

! CHECK-LABEL: func.func @_QPtest_tma_bulk_store_r4
! CHECK: nvvm.cp.async.bulk.global.shared.cta %{{.*}}, %{{.*}}, %{{.*}} : <1>, <3>
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group"
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group;"
! CHECK: nvvm.cp.async.bulk.wait_group 0

attributes(global) subroutine test_tma_bulk_store_r8(c, n)
Expand All @@ -750,5 +750,5 @@ end subroutine

! CHECK-LABEL: func.func @_QPtest_tma_bulk_store_r8
! CHECK: nvvm.cp.async.bulk.global.shared.cta %{{.*}}, %{{.*}}, %{{.*}} : <1>, <3>
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group"
! CHECK: nvvm.inline_ptx "cp.async.bulk.commit_group;"
! CHECK: nvvm.cp.async.bulk.wait_group 0
Loading