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
69 lines
2.4 KiB
LLVM
69 lines
2.4 KiB
LLVM
; RUN: opt < %s -O3 -S | FileCheck %s
|
|
|
|
; Make sure the call to syncthreads is not duplicate here by the LLVM
|
|
; optimizations, because it has the noduplicate attribute set.
|
|
|
|
; CHECK: call void @llvm.nvvm.barrier.cta.sync.aligned.all
|
|
; CHECK-NOT: call void @llvm.nvvm.barrier.cta.sync.aligned.all
|
|
|
|
; Function Attrs: nounwind
|
|
define void @foo(ptr %output) #1 {
|
|
entry:
|
|
%output.addr = alloca ptr, align 8
|
|
store ptr %output, ptr %output.addr, align 8
|
|
%0 = load ptr, ptr %output.addr, align 8
|
|
%1 = load float, ptr %0, align 4
|
|
%conv = fpext float %1 to double
|
|
%cmp = fcmp olt double %conv, 1.000000e+01
|
|
br i1 %cmp, label %if.then, label %if.else
|
|
|
|
if.then: ; preds = %entry
|
|
%2 = load ptr, ptr %output.addr, align 8
|
|
%3 = load float, ptr %2, align 4
|
|
%conv1 = fpext float %3 to double
|
|
%add = fadd double %conv1, 1.000000e+00
|
|
%conv2 = fptrunc double %add to float
|
|
store float %conv2, ptr %2, align 4
|
|
br label %if.end
|
|
|
|
if.else: ; preds = %entry
|
|
%4 = load ptr, ptr %output.addr, align 8
|
|
%5 = load float, ptr %4, align 4
|
|
%conv3 = fpext float %5 to double
|
|
%add4 = fadd double %conv3, 2.000000e+00
|
|
%conv5 = fptrunc double %add4 to float
|
|
store float %conv5, ptr %4, align 4
|
|
br label %if.end
|
|
|
|
if.end: ; preds = %if.else, %if.then
|
|
call void @llvm.nvvm.barrier.cta.sync.aligned.all(i32 0)
|
|
%6 = load ptr, ptr %output.addr, align 8
|
|
%7 = load float, ptr %6, align 4
|
|
%conv7 = fpext float %7 to double
|
|
%cmp8 = fcmp olt double %conv7, 1.000000e+01
|
|
br i1 %cmp8, label %if.then9, label %if.else13
|
|
|
|
if.then9: ; preds = %if.end
|
|
%8 = load ptr, ptr %output.addr, align 8
|
|
%9 = load float, ptr %8, align 4
|
|
%conv10 = fpext float %9 to double
|
|
%add11 = fadd double %conv10, 3.000000e+00
|
|
%conv12 = fptrunc double %add11 to float
|
|
store float %conv12, ptr %8, align 4
|
|
br label %if.end17
|
|
|
|
if.else13: ; preds = %if.end
|
|
%10 = load ptr, ptr %output.addr, align 8
|
|
%11 = load float, ptr %10, align 4
|
|
%conv14 = fpext float %11 to double
|
|
%add15 = fadd double %conv14, 4.000000e+00
|
|
%conv16 = fptrunc double %add15 to float
|
|
store float %conv16, ptr %10, align 4
|
|
br label %if.end17
|
|
|
|
if.end17: ; preds = %if.else13, %if.then9
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: noduplicate nounwind
|
|
declare void @llvm.nvvm.barrier0() #2 |