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
35 lines
2.8 KiB
LLVM
35 lines
2.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -passes=gvn -S -enable-gvn-memdep=true < %s | FileCheck %s
|
|
; RUN: opt -passes=gvn -S -enable-gvn-memdep=false < %s | FileCheck %s --check-prefix=MEMDEPFALSE
|
|
|
|
define <4 x float> @forward_binop_with_sel(ptr %0, ptr %1, i32 %a, i32 %b, <4 x float> %passthrough) {
|
|
; CHECK-LABEL: @forward_binop_with_sel(
|
|
; CHECK-NEXT: [[MASK:%.*]] = tail call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[A:%.*]], i32 [[B:%.*]])
|
|
; CHECK-NEXT: [[LOAD_0_0:%.*]] = call <4 x float> @llvm.masked.load.v4f32.p0(ptr align 1 [[TMP0:%.*]], <4 x i1> [[MASK]], <4 x float> zeroinitializer)
|
|
; CHECK-NEXT: [[GEP_0_16:%.*]] = getelementptr i8, ptr [[TMP0]], i32 16
|
|
; CHECK-NEXT: [[LOAD_0_16:%.*]] = call <4 x float> @llvm.masked.load.v4f32.p0(ptr align 1 [[GEP_0_16]], <4 x i1> [[MASK]], <4 x float> zeroinitializer)
|
|
; CHECK-NEXT: [[FMUL:%.*]] = fmul <4 x float> [[LOAD_0_0]], [[LOAD_0_16]]
|
|
; CHECK-NEXT: call void @llvm.masked.store.v4f32.p0(<4 x float> [[FMUL]], ptr align 1 [[TMP1:%.*]], <4 x i1> [[MASK]])
|
|
; CHECK-NEXT: [[TMP3:%.*]] = select <4 x i1> [[MASK]], <4 x float> [[FMUL]], <4 x float> [[PASSTHROUGH:%.*]]
|
|
; CHECK-NEXT: ret <4 x float> [[TMP3]]
|
|
;
|
|
; MEMDEPFALSE-LABEL: @forward_binop_with_sel(
|
|
; MEMDEPFALSE-NEXT: [[MASK:%.*]] = tail call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[A:%.*]], i32 [[B:%.*]])
|
|
; MEMDEPFALSE-NEXT: [[LOAD_0_0:%.*]] = call <4 x float> @llvm.masked.load.v4f32.p0(ptr align 1 [[TMP0:%.*]], <4 x i1> [[MASK]], <4 x float> zeroinitializer)
|
|
; MEMDEPFALSE-NEXT: [[GEP_0_16:%.*]] = getelementptr i8, ptr [[TMP0]], i32 16
|
|
; MEMDEPFALSE-NEXT: [[LOAD_0_16:%.*]] = call <4 x float> @llvm.masked.load.v4f32.p0(ptr align 1 [[GEP_0_16]], <4 x i1> [[MASK]], <4 x float> zeroinitializer)
|
|
; MEMDEPFALSE-NEXT: [[FMUL:%.*]] = fmul <4 x float> [[LOAD_0_0]], [[LOAD_0_16]]
|
|
; MEMDEPFALSE-NEXT: call void @llvm.masked.store.v4f32.p0(<4 x float> [[FMUL]], ptr align 1 [[TMP1:%.*]], <4 x i1> [[MASK]])
|
|
; MEMDEPFALSE-NEXT: [[LOAD_1_0:%.*]] = call <4 x float> @llvm.masked.load.v4f32.p0(ptr align 1 [[TMP1]], <4 x i1> [[MASK]], <4 x float> [[PASSTHROUGH:%.*]])
|
|
; MEMDEPFALSE-NEXT: ret <4 x float> [[LOAD_1_0]]
|
|
;
|
|
%mask = tail call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %a, i32 %b)
|
|
%load.0.0 = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %0, i32 1, <4 x i1> %mask, <4 x float> zeroinitializer)
|
|
%gep.0.16 = getelementptr i8, ptr %0, i32 16
|
|
%load.0.16 = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %gep.0.16, i32 1, <4 x i1> %mask, <4 x float> zeroinitializer)
|
|
%fmul = fmul <4 x float> %load.0.0, %load.0.16
|
|
call void @llvm.masked.store.v4f32.p0(<4 x float> %fmul, ptr %1, i32 1, <4 x i1> %mask)
|
|
%load.1.0 = call <4 x float> @llvm.masked.load.v4f32.p0(ptr %1, i32 1, <4 x i1> %mask, <4 x float> %passthrough)
|
|
ret <4 x float> %load.1.0
|
|
}
|