derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
47 lines
1.1 KiB
LLVM
47 lines
1.1 KiB
LLVM
; RUN: llc -O2 -tail-dup-size=100 -enable-tail-merge=0 < %s | FileCheck %s
|
|
; RUN: %if ptxas %{ llc -O2 -tail-dup-size=100 -enable-tail-merge=0 < %s | %ptxas-verify %}
|
|
target triple = "nvptx64-nvidia-cuda"
|
|
|
|
declare void @foo()
|
|
declare void @llvm.nvvm.barrier0()
|
|
|
|
; syncthreads shouldn't be duplicated.
|
|
; CHECK: .func call_syncthreads
|
|
; CHECK: bar.sync
|
|
; CHECK-NOT: bar.sync
|
|
define void @call_syncthreads(ptr %a, ptr %b, i1 %cond, i1 %cond2) nounwind {
|
|
br i1 %cond, label %L1, label %L2
|
|
br i1 %cond2, label %Ret, label %L1
|
|
Ret:
|
|
ret void
|
|
L1:
|
|
store i32 0, ptr %a
|
|
br label %L42
|
|
L2:
|
|
store i32 1, ptr %a
|
|
br label %L42
|
|
L42:
|
|
call void @llvm.nvvm.barrier0()
|
|
br label %Ret
|
|
}
|
|
|
|
; Check that call_syncthreads really does trigger tail duplication.
|
|
; CHECK: .func call_foo
|
|
; CHECK: call
|
|
; CHECK: call
|
|
define void @call_foo(ptr %a, ptr %b, i1 %cond, i1 %cond2) nounwind {
|
|
br i1 %cond, label %L1, label %L2
|
|
br i1 %cond2, label %Ret, label %L1
|
|
Ret:
|
|
ret void
|
|
L1:
|
|
store i32 0, ptr %a
|
|
br label %L42
|
|
L2:
|
|
store i32 1, ptr %a
|
|
br label %L42
|
|
L42:
|
|
call void @foo()
|
|
br label %Ret
|
|
}
|