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
46 lines
2.1 KiB
LLVM
46 lines
2.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -stop-after=irtranslator < %s | FileCheck %s
|
|
|
|
define ptr @ptrmask_flat_i64(ptr %ptr, i64 %mask) {
|
|
; CHECK-LABEL: name: ptrmask_flat_i64
|
|
; CHECK: bb.1 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
|
|
; CHECK-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
|
|
; CHECK-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
|
|
; CHECK-NEXT: [[MV1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
|
|
; CHECK-NEXT: [[PTRMASK:%[0-9]+]]:_(p0) = G_PTRMASK [[MV]], [[MV1]](s64)
|
|
; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[PTRMASK]](p0)
|
|
; CHECK-NEXT: $vgpr0 = COPY [[UV]](s32)
|
|
; CHECK-NEXT: $vgpr1 = COPY [[UV1]](s32)
|
|
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
|
|
%masked = call ptr @llvm.ptrmask.p0.i64(ptr %ptr, i64 %mask)
|
|
ret ptr %masked
|
|
}
|
|
|
|
define ptr addrspace(3) @ptrmask_local_i32(ptr addrspace(3) %ptr, i32 %mask) {
|
|
; CHECK-LABEL: name: ptrmask_local_i32
|
|
; CHECK: bb.1 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(p3) = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; CHECK-NEXT: [[PTRMASK:%[0-9]+]]:_(p3) = G_PTRMASK [[COPY]], [[COPY1]](s32)
|
|
; CHECK-NEXT: $vgpr0 = COPY [[PTRMASK]](p3)
|
|
; CHECK-NEXT: SI_RETURN implicit $vgpr0
|
|
%masked = call ptr addrspace(3) @llvm.ptrmask.p3.i32(ptr addrspace(3) %ptr, i32 %mask)
|
|
ret ptr addrspace(3) %masked
|
|
}
|
|
|
|
; Seems to not work
|
|
; define <2 x ptr> @ptrmask_flat_i64_v2(<2 x ptr> %ptr, <2 x i64> %mask) {
|
|
; %masked = call <2 x ptr> @llvm.ptrmask.v2p0.v2i64(<2 x ptr> %ptr, <2 x i64> %mask)
|
|
; ret <2 x ptr> %masked
|
|
; }
|
|
|
|
declare ptr @llvm.ptrmask.p0.i64(ptr, i64)
|
|
declare ptr addrspace(3) @llvm.ptrmask.p3.i32(ptr addrspace(3), i32)
|