Files
TheRock/compiler/amd-llvm/llvm/test/Transforms/LoopUnroll/AMDGPU/unroll-cost-call.ll
T
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

78 lines
3.1 KiB
LLVM

; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -mcpu=hawaii -passes=loop-unroll -unroll-threshold=100 -unroll-peel-count=0 -unroll-allow-partial=false -unroll-max-iteration-count-to-analyze=16 < %s | FileCheck %s
; CHECK-LABEL: @test_intrinsic_call_cost(
; CHECK-NOT: br i1
define amdgpu_kernel void @test_intrinsic_call_cost(ptr addrspace(1) noalias nocapture %out, ptr addrspace(1) noalias nocapture %in) #0 {
entry:
br label %for.body
for.body:
%indvars.iv = phi i32 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%sum.02 = phi float [ %fmul, %for.body ], [ 0.0, %entry ]
%arrayidx.in = getelementptr inbounds float, ptr addrspace(1) %in, i32 %indvars.iv
%arrayidx.out = getelementptr inbounds float, ptr addrspace(1) %out, i32 %indvars.iv
%load = load float, ptr addrspace(1) %arrayidx.in
%call = call float @llvm.minnum.f32(float %load, float 1.0);
%fmul = fmul float %call, %sum.02
store float %fmul, ptr addrspace(1) %arrayidx.out
%indvars.iv.next = add i32 %indvars.iv, 1
%exitcond = icmp eq i32 %indvars.iv.next, 16
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}
; CHECK-LABEL: @test_func_call_cost(
; CHECK: br i1 %exitcond
define amdgpu_kernel void @test_func_call_cost(ptr addrspace(1) noalias nocapture %out, ptr addrspace(1) noalias nocapture %in) #0 {
entry:
br label %for.body
for.body:
%indvars.iv = phi i32 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%sum.02 = phi float [ %fmul, %for.body ], [ 0.0, %entry ]
%arrayidx.in = getelementptr inbounds float, ptr addrspace(1) %in, i32 %indvars.iv
%arrayidx.out = getelementptr inbounds float, ptr addrspace(1) %out, i32 %indvars.iv
%load = load float, ptr addrspace(1) %arrayidx.in
%fptr = load ptr, ptr addrspace(4) null
%call = tail call float %fptr(float %load, float 1.0)
%fmul = fmul float %call, %sum.02
store float %fmul, ptr addrspace(1) %arrayidx.out
%indvars.iv.next = add i32 %indvars.iv, 1
%exitcond = icmp eq i32 %indvars.iv.next, 16
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}
; CHECK-LABEL: @test_indirect_call_cost(
; CHECK: br i1 %exitcond
define amdgpu_kernel void @test_indirect_call_cost(ptr addrspace(1) noalias nocapture %out, ptr addrspace(1) noalias nocapture %in) #0 {
entry:
br label %for.body
for.body:
%indvars.iv = phi i32 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%sum.02 = phi float [ %fmul, %for.body ], [ 0.0, %entry ]
%arrayidx.in = getelementptr inbounds float, ptr addrspace(1) %in, i32 %indvars.iv
%arrayidx.out = getelementptr inbounds float, ptr addrspace(1) %out, i32 %indvars.iv
%load = load float, ptr addrspace(1) %arrayidx.in
%min = call float @func(float %load, float 1.0);
%fmul = fmul float %min, %sum.02
store float %fmul, ptr addrspace(1) %arrayidx.out
%indvars.iv.next = add i32 %indvars.iv, 1
%exitcond = icmp eq i32 %indvars.iv.next, 16
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}
declare float @llvm.minnum.f32(float, float) #1
declare float @func(float, float) #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone speculatable }