Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/promote-alloca-memset.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

142 lines
5.5 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -passes=amdgpu-promote-alloca < %s | FileCheck %s
; Checks that memsets don't block PromoteAlloca.
define amdgpu_kernel void @memset_all_zero(i64 %val) {
; CHECK-LABEL: @memset_all_zero(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[STACK:%.*]] = freeze <6 x i64> poison
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <6 x i64> zeroinitializer, i64 [[VAL:%.*]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <6 x i64> [[TMP0]], i64 [[VAL]], i32 1
; CHECK-NEXT: ret void
;
entry:
%stack = alloca [6 x i64], align 4, addrspace(5)
call void @llvm.memset.p5.i64(ptr addrspace(5) %stack, i8 0, i64 48, i1 false)
store i64 %val, ptr addrspace(5) %stack
%reload = load i64, ptr addrspace(5) %stack
%stack.1 = getelementptr [6 x i64], ptr addrspace(5) %stack, i64 0, i64 1
store i64 %val, ptr addrspace(5) %stack.1
ret void
}
define amdgpu_kernel void @memset_all_5(i64 %val) {
; CHECK-LABEL: @memset_all_5(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[STACK:%.*]] = freeze <4 x i64> poison
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i64> splat (i64 361700864190383365), i64 [[VAL:%.*]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i64> [[TMP0]], i64 [[VAL]], i32 1
; CHECK-NEXT: ret void
;
entry:
%stack = alloca [4 x i64], align 4, addrspace(5)
call void @llvm.memset.p5.i64(ptr addrspace(5) %stack, i8 5, i64 32, i1 false)
store i64 %val, ptr addrspace(5) %stack
%reload = load i64, ptr addrspace(5) %stack
%stack.1 = getelementptr [6 x i64], ptr addrspace(5) %stack, i64 0, i64 1
store i64 %val, ptr addrspace(5) %stack.1
ret void
}
define amdgpu_kernel void @memset_volatile_nopromote(i64 %val) {
; CHECK-LABEL: @memset_volatile_nopromote(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[STACK:%.*]] = alloca [4 x i64], align 4, addrspace(5)
; CHECK-NEXT: call void @llvm.memset.p5.i64(ptr addrspace(5) [[STACK]], i8 0, i64 32, i1 true)
; CHECK-NEXT: store i64 [[VAL:%.*]], ptr addrspace(5) [[STACK]], align 8
; CHECK-NEXT: ret void
;
entry:
%stack = alloca [4 x i64], align 4, addrspace(5)
call void @llvm.memset.p5.i64(ptr addrspace(5) %stack, i8 0, i64 32, i1 true)
store i64 %val, ptr addrspace(5) %stack
ret void
}
define amdgpu_kernel void @memset_badsize_nopromote(i64 %val) {
; CHECK-LABEL: @memset_badsize_nopromote(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[STACK:%.*]] = alloca [4 x i64], align 4, addrspace(5)
; CHECK-NEXT: call void @llvm.memset.p5.i64(ptr addrspace(5) [[STACK]], i8 0, i64 31, i1 true)
; CHECK-NEXT: store i64 [[VAL:%.*]], ptr addrspace(5) [[STACK]], align 8
; CHECK-NEXT: ret void
;
entry:
%stack = alloca [4 x i64], align 4, addrspace(5)
call void @llvm.memset.p5.i64(ptr addrspace(5) %stack, i8 0, i64 31, i1 true)
store i64 %val, ptr addrspace(5) %stack
ret void
}
define amdgpu_kernel void @memset_offset_ptr_nopromote(i64 %val) {
; CHECK-LABEL: @memset_offset_ptr_nopromote(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[STACK:%.*]] = alloca [4 x i64], align 4, addrspace(5)
; CHECK-NEXT: [[GEP:%.*]] = getelementptr [4 x i64], ptr addrspace(5) [[STACK]], i64 0, i64 1
; CHECK-NEXT: call void @llvm.memset.p5.i64(ptr addrspace(5) [[GEP]], i8 0, i64 24, i1 true)
; CHECK-NEXT: store i64 [[VAL:%.*]], ptr addrspace(5) [[STACK]], align 8
; CHECK-NEXT: ret void
;
entry:
%stack = alloca [4 x i64], align 4, addrspace(5)
%gep = getelementptr [4 x i64], ptr addrspace(5) %stack, i64 0, i64 1
call void @llvm.memset.p5.i64(ptr addrspace(5) %gep, i8 0, i64 24, i1 true)
store i64 %val, ptr addrspace(5) %stack
ret void
}
define amdgpu_kernel void @memset_array_ptr_alloca(ptr %out) {
; CHECK-LABEL: @memset_array_ptr_alloca(
; CHECK-NEXT: [[ALLOCA:%.*]] = freeze <6 x ptr> poison
; CHECK-NEXT: store i64 0, ptr [[OUT:%.*]], align 8
; CHECK-NEXT: ret void
;
%alloca = alloca [6 x ptr], align 16, addrspace(5)
call void @llvm.memset.p5.i64(ptr addrspace(5) %alloca, i8 0, i64 48, i1 false)
%load = load i64, ptr addrspace(5) %alloca
store i64 %load, ptr %out
ret void
}
define amdgpu_kernel void @memset_vector_ptr_alloca(ptr %out) {
; CHECK-LABEL: @memset_vector_ptr_alloca(
; CHECK-NEXT: [[ALLOCA:%.*]] = freeze <6 x ptr> poison
; CHECK-NEXT: store i64 0, ptr [[OUT:%.*]], align 8
; CHECK-NEXT: ret void
;
%alloca = alloca <6 x ptr>, align 16, addrspace(5)
call void @llvm.memset.p5.i64(ptr addrspace(5) %alloca, i8 0, i64 48, i1 false)
%load = load i64, ptr addrspace(5) %alloca
store i64 %load, ptr %out
ret void
}
define amdgpu_kernel void @memset_array_of_array_ptr_alloca(ptr %out) {
; CHECK-LABEL: @memset_array_of_array_ptr_alloca(
; CHECK-NEXT: [[ALLOCA:%.*]] = freeze <6 x ptr> poison
; CHECK-NEXT: store i64 0, ptr [[OUT:%.*]], align 8
; CHECK-NEXT: ret void
;
%alloca = alloca [2 x [3 x ptr]], align 16, addrspace(5)
call void @llvm.memset.p5.i64(ptr addrspace(5) %alloca, i8 0, i64 48, i1 false)
%load = load i64, ptr addrspace(5) %alloca
store i64 %load, ptr %out
ret void
}
define amdgpu_kernel void @memset_array_of_vec_ptr_alloca(ptr %out) {
; CHECK-LABEL: @memset_array_of_vec_ptr_alloca(
; CHECK-NEXT: [[ALLOCA:%.*]] = freeze <8 x ptr> poison
; CHECK-NEXT: store i64 0, ptr [[OUT:%.*]], align 8
; CHECK-NEXT: ret void
;
%alloca = alloca [2 x <3 x ptr>], align 16, addrspace(5)
call void @llvm.memset.p5.i64(ptr addrspace(5) %alloca, i8 0, i64 64, i1 false)
%load = load i64, ptr addrspace(5) %alloca
store i64 %load, ptr %out
ret void
}
declare void @llvm.memset.p5.i64(ptr addrspace(5) nocapture writeonly, i8, i64, i1 immarg)