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
59 lines
3.7 KiB
LLVM
59 lines
3.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: opt < %s -passes=gvn -S | FileCheck %s
|
|
|
|
declare void @llvm.masked.scatter.v2i32.v2p0(<2 x i32> , <2 x ptr> , i32 , <2 x i1> )
|
|
declare <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr>, i32, <2 x i1>, <2 x i32>)
|
|
|
|
; This test ensures that masked scatter and gather operations, which take vectors of pointers,
|
|
; do not have pointer aliasing ignored when being processed.
|
|
; No scatter/gather calls should end up eliminated.
|
|
|
|
define spir_kernel void @test(<2 x ptr> %in1, <2 x ptr> %in2, ptr %out) {
|
|
; CHECK-LABEL: define spir_kernel void @test(
|
|
; CHECK-SAME: <2 x ptr> [[IN1:%.*]], <2 x ptr> [[IN2:%.*]], ptr [[OUT:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[TMP_0:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[TMP_1:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[TMP_I:%.*]] = insertelement <2 x ptr> undef, ptr [[TMP_0]], i32 0
|
|
; CHECK-NEXT: [[TMP:%.*]] = insertelement <2 x ptr> [[TMP_I]], ptr [[TMP_1]], i32 1
|
|
; CHECK-NEXT: [[IN1_V:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr> align 1 [[IN1]], <2 x i1> splat (i1 true), <2 x i32> undef)
|
|
; CHECK-NEXT: [[IN2_V:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr> align 1 [[IN2]], <2 x i1> splat (i1 true), <2 x i32> undef)
|
|
; CHECK-NEXT: call void @llvm.masked.scatter.v2i32.v2p0(<2 x i32> [[IN1_V]], <2 x ptr> align 1 [[TMP]], <2 x i1> splat (i1 true))
|
|
; CHECK-NEXT: [[TMP_V_0:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr> align 1 [[TMP]], <2 x i1> splat (i1 true), <2 x i32> undef)
|
|
; CHECK-NEXT: call void @llvm.masked.scatter.v2i32.v2p0(<2 x i32> [[IN2_V]], <2 x ptr> align 1 [[TMP]], <2 x i1> splat (i1 true))
|
|
; CHECK-NEXT: [[TMP_V_1:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr> align 1 [[TMP]], <2 x i1> splat (i1 true), <2 x i32> undef)
|
|
; CHECK-NEXT: [[TMP_V_1_0:%.*]] = extractelement <2 x i32> [[TMP_V_1]], i32 0
|
|
; CHECK-NEXT: [[TMP_V_1_1:%.*]] = extractelement <2 x i32> [[TMP_V_1]], i32 1
|
|
; CHECK-NEXT: store i32 [[TMP_V_1_0]], ptr [[OUT]], align 4
|
|
; CHECK-NEXT: [[OUT_1:%.*]] = getelementptr i32, ptr [[OUT]], i32 1
|
|
; CHECK-NEXT: store i32 [[TMP_V_1_1]], ptr [[OUT_1]], align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
; Just some temporary storage
|
|
%tmp.0 = alloca i32
|
|
%tmp.1 = alloca i32
|
|
%tmp.i = insertelement <2 x ptr> undef, ptr %tmp.0, i32 0
|
|
%tmp = insertelement <2 x ptr> %tmp.i, ptr %tmp.1, i32 1
|
|
; Read from in1 and in2
|
|
%in1.v = call <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr> %in1, i32 1, <2 x i1> <i1 true, i1 true>, <2 x i32> undef) #1
|
|
%in2.v = call <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr> %in2, i32 1, <2 x i1> <i1 true, i1 true>, <2 x i32> undef) #1
|
|
; Store in1 to the allocas
|
|
call void @llvm.masked.scatter.v2i32.v2p0(<2 x i32> %in1.v, <2 x ptr> %tmp, i32 1, <2 x i1> <i1 true, i1 true>);
|
|
; Read in1 from the allocas
|
|
; This gather should alias the scatter we just saw
|
|
%tmp.v.0 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr> %tmp, i32 1, <2 x i1> <i1 true, i1 true>, <2 x i32> undef) #1
|
|
; Store in2 to the allocas
|
|
call void @llvm.masked.scatter.v2i32.v2p0(<2 x i32> %in2.v, <2 x ptr> %tmp, i32 1, <2 x i1> <i1 true, i1 true>);
|
|
; Read in2 from the allocas
|
|
; This gather should alias the scatter we just saw, and not be eliminated
|
|
%tmp.v.1 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0(<2 x ptr> %tmp, i32 1, <2 x i1> <i1 true, i1 true>, <2 x i32> undef) #1
|
|
; Store in2 to out for good measure
|
|
%tmp.v.1.0 = extractelement <2 x i32> %tmp.v.1, i32 0
|
|
%tmp.v.1.1 = extractelement <2 x i32> %tmp.v.1, i32 1
|
|
store i32 %tmp.v.1.0, ptr %out
|
|
%out.1 = getelementptr i32, ptr %out, i32 1
|
|
store i32 %tmp.v.1.1, ptr %out.1
|
|
ret void
|
|
}
|