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
151 lines
7.6 KiB
LLVM
151 lines
7.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii -stop-after=legalizer -o - %s | FileCheck %s
|
|
|
|
; Test behavior of legalizer when vector loads have range metadata,
|
|
; and are lowered by bitcasting to a scalar integer, so we have to
|
|
; drop the range metadata.
|
|
|
|
define <4 x i8> @global_load_v4i8_align4__rangemd(ptr addrspace(1) %ptr) {
|
|
; CHECK-LABEL: name: global_load_v4i8_align4__rangemd
|
|
; CHECK: bb.1 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
|
|
; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[MV]](p1) :: (load (s32) from %ir.ptr, addrspace 1)
|
|
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
|
|
; CHECK-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C]](s32)
|
|
; CHECK-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; CHECK-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C1]](s32)
|
|
; CHECK-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 24
|
|
; CHECK-NEXT: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C2]](s32)
|
|
; CHECK-NEXT: $vgpr0 = COPY [[LOAD]](s32)
|
|
; CHECK-NEXT: $vgpr1 = COPY [[LSHR]](s32)
|
|
; CHECK-NEXT: $vgpr2 = COPY [[LSHR1]](s32)
|
|
; CHECK-NEXT: $vgpr3 = COPY [[LSHR2]](s32)
|
|
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
%load = load <4 x i8>, ptr addrspace(1) %ptr, align 4, !range !0, !noundef !1
|
|
ret <4 x i8> %load
|
|
}
|
|
|
|
; This is also widened.
|
|
define <3 x i8> @global_load_v3i8_align4__rangemd(ptr addrspace(1) %ptr) {
|
|
; CHECK-LABEL: name: global_load_v3i8_align4__rangemd
|
|
; CHECK: bb.1 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
|
|
; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[MV]](p1) :: (load (s32) from %ir.ptr, addrspace 1)
|
|
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
|
|
; CHECK-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C]](s32)
|
|
; CHECK-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; CHECK-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C1]](s32)
|
|
; CHECK-NEXT: $vgpr0 = COPY [[LOAD]](s32)
|
|
; CHECK-NEXT: $vgpr1 = COPY [[LSHR]](s32)
|
|
; CHECK-NEXT: $vgpr2 = COPY [[LSHR1]](s32)
|
|
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1, implicit $vgpr2
|
|
%load = load <3 x i8>, ptr addrspace(1) %ptr, align 4, !range !0, !noundef !1
|
|
ret <3 x i8> %load
|
|
}
|
|
|
|
define <2 x i8> @global_load_v2i8_align2__rangemd(ptr addrspace(1) %ptr) {
|
|
; CHECK-LABEL: name: global_load_v2i8_align2__rangemd
|
|
; CHECK: bb.1 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
|
|
; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[MV]](p1) :: (load (s16) from %ir.ptr, addrspace 1)
|
|
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
|
|
; CHECK-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C]](s32)
|
|
; CHECK-NEXT: $vgpr0 = COPY [[LOAD]](s32)
|
|
; CHECK-NEXT: $vgpr1 = COPY [[LSHR]](s32)
|
|
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
|
|
%load = load <2 x i8>, ptr addrspace(1) %ptr, align 2, !range !0, !noundef !1
|
|
ret <2 x i8> %load
|
|
}
|
|
|
|
define <2 x i64> @global_load_v2i64_align16__rangemd(ptr addrspace(1) %ptr) {
|
|
; CHECK-LABEL: name: global_load_v2i64_align16__rangemd
|
|
; CHECK: bb.1 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
|
|
; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<2 x s64>) = G_LOAD [[MV]](p1) :: (load (<2 x s64>) from %ir.ptr, !range !2, addrspace 1)
|
|
; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[LOAD]](<2 x s64>)
|
|
; CHECK-NEXT: $vgpr0 = COPY [[UV]](s32)
|
|
; CHECK-NEXT: $vgpr1 = COPY [[UV1]](s32)
|
|
; CHECK-NEXT: $vgpr2 = COPY [[UV2]](s32)
|
|
; CHECK-NEXT: $vgpr3 = COPY [[UV3]](s32)
|
|
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
%load = load <2 x i64>, ptr addrspace(1) %ptr, align 16, !range !2, !noundef !1
|
|
ret <2 x i64> %load
|
|
}
|
|
|
|
; This goes the other direction and converts a scalar load to a vector.
|
|
define i128 @global_load_i128_align16__rangemd(ptr addrspace(1) %ptr) {
|
|
; CHECK-LABEL: name: global_load_i128_align16__rangemd
|
|
; CHECK: bb.1 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
|
|
; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<4 x s32>) = G_LOAD [[MV]](p1) :: (load (<4 x s32>) from %ir.ptr, addrspace 1)
|
|
; CHECK-NEXT: [[BITCAST:%[0-9]+]]:_(s128) = G_BITCAST [[LOAD]](<4 x s32>)
|
|
; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BITCAST]](s128)
|
|
; CHECK-NEXT: $vgpr0 = COPY [[UV]](s32)
|
|
; CHECK-NEXT: $vgpr1 = COPY [[UV1]](s32)
|
|
; CHECK-NEXT: $vgpr2 = COPY [[UV2]](s32)
|
|
; CHECK-NEXT: $vgpr3 = COPY [[UV3]](s32)
|
|
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
|
|
%load = load i128, ptr addrspace(1) %ptr, align 16, !range !3, !noundef !1
|
|
ret i128 %load
|
|
}
|
|
|
|
; Load will be zero extended, so we should be able to extend the range
|
|
; metadata.
|
|
define i32 @global_sextload_i8_align1__rangemd(ptr addrspace(1) %ptr) {
|
|
; CHECK-LABEL: name: global_sextload_i8_align1__rangemd
|
|
; CHECK: bb.1 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
|
|
; CHECK-NEXT: [[SEXTLOAD:%[0-9]+]]:_(s32) = G_SEXTLOAD [[MV]](p1) :: (load (s8) from %ir.ptr, !range !0, addrspace 1)
|
|
; CHECK-NEXT: $vgpr0 = COPY [[SEXTLOAD]](s32)
|
|
; CHECK-NEXT: SI_RETURN implicit $vgpr0
|
|
%load = load i8, ptr addrspace(1) %ptr, align 1, !range !0, !noundef !1
|
|
%ext = sext i8 %load to i32
|
|
ret i32 %ext
|
|
}
|
|
|
|
define i32 @global_zextload_i8_align1__rangemd(ptr addrspace(1) %ptr) {
|
|
; CHECK-LABEL: name: global_zextload_i8_align1__rangemd
|
|
; CHECK: bb.1 (%ir-block.0):
|
|
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
|
|
; CHECK-NEXT: {{ $}}
|
|
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
|
|
; CHECK-NEXT: [[SEXTLOAD:%[0-9]+]]:_(s32) = G_SEXTLOAD [[MV]](p1) :: (load (s8) from %ir.ptr, !range !4, addrspace 1)
|
|
; CHECK-NEXT: $vgpr0 = COPY [[SEXTLOAD]](s32)
|
|
; CHECK-NEXT: SI_RETURN implicit $vgpr0
|
|
%load = load i8, ptr addrspace(1) %ptr, align 1, !range !4, !noundef !1
|
|
%ext = sext i8 %load to i32
|
|
ret i32 %ext
|
|
}
|
|
|
|
!0 = !{i8 -32, i8 64}
|
|
!1 = !{}
|
|
!2 = !{i64 -2048, i64 1024}
|
|
!3 = !{i128 -2048, i128 1024}
|
|
!4 = !{i8 8, i8 64}
|