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
68 lines
2.6 KiB
LLVM
68 lines
2.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=aarch64-unknown-unknown -mcpu=cyclone -mattr=+slow-misaligned-128store | FileCheck %s --check-prefixes=CHECK,SPLITTING
|
|
; RUN: llc < %s -mtriple=aarch64 -mattr=-slow-misaligned-128store | FileCheck %s --check-prefixes=CHECK,MISALIGNED
|
|
|
|
@g0 = external dso_local global <3 x float>, align 16
|
|
@g1 = external dso_local global <3 x float>, align 4
|
|
|
|
define void @blam() {
|
|
; SPLITTING-LABEL: blam:
|
|
; SPLITTING: // %bb.0:
|
|
; SPLITTING-NEXT: adrp x8, g1
|
|
; SPLITTING-NEXT: add x8, x8, :lo12:g1
|
|
; SPLITTING-NEXT: adrp x9, g0
|
|
; SPLITTING-NEXT: ldr d0, [x9, :lo12:g0]
|
|
; SPLITTING-NEXT: str d0, [x8]
|
|
; SPLITTING-NEXT: ret
|
|
;
|
|
; MISALIGNED-LABEL: blam:
|
|
; MISALIGNED: // %bb.0:
|
|
; MISALIGNED-NEXT: adrp x8, g0
|
|
; MISALIGNED-NEXT: ldr d0, [x8, :lo12:g0]
|
|
; MISALIGNED-NEXT: adrp x8, g1
|
|
; MISALIGNED-NEXT: add x8, x8, :lo12:g1
|
|
; MISALIGNED-NEXT: str d0, [x8]
|
|
; MISALIGNED-NEXT: ret
|
|
%tmp4 = getelementptr inbounds <3 x float>, ptr @g1, i64 0, i64 0
|
|
%tmp5 = load <3 x float>, ptr @g0, align 16
|
|
%tmp6 = extractelement <3 x float> %tmp5, i64 0
|
|
store float %tmp6, ptr %tmp4
|
|
%tmp7 = getelementptr inbounds float, ptr %tmp4, i64 1
|
|
%tmp8 = load <3 x float>, ptr @g0, align 16
|
|
%tmp9 = extractelement <3 x float> %tmp8, i64 1
|
|
store float %tmp9, ptr %tmp7
|
|
ret void;
|
|
}
|
|
|
|
|
|
; PR21711 - Merge vector stores into wider vector stores.
|
|
|
|
; On Cyclone, the stores should not get merged into a 16-byte store because
|
|
; unaligned 16-byte stores are slow. This test would infinite loop when
|
|
; the fastness of unaligned accesses was not specified correctly.
|
|
|
|
define void @merge_vec_extract_stores(<4 x float> %v1, ptr %ptr) {
|
|
; SPLITTING-LABEL: merge_vec_extract_stores:
|
|
; SPLITTING: // %bb.0:
|
|
; SPLITTING-NEXT: add x8, x0, #32
|
|
; SPLITTING-NEXT: str d0, [x0, #24]
|
|
; SPLITTING-NEXT: st1 { v0.d }[1], [x8]
|
|
; SPLITTING-NEXT: ret
|
|
;
|
|
; MISALIGNED-LABEL: merge_vec_extract_stores:
|
|
; MISALIGNED: // %bb.0:
|
|
; MISALIGNED-NEXT: stur q0, [x0, #24]
|
|
; MISALIGNED-NEXT: ret
|
|
%idx0 = getelementptr inbounds <2 x float>, ptr %ptr, i64 3
|
|
%idx1 = getelementptr inbounds <2 x float>, ptr %ptr, i64 4
|
|
|
|
%shuffle0 = shufflevector <4 x float> %v1, <4 x float> undef, <2 x i32> <i32 0, i32 1>
|
|
%shuffle1 = shufflevector <4 x float> %v1, <4 x float> undef, <2 x i32> <i32 2, i32 3>
|
|
|
|
store <2 x float> %shuffle0, ptr %idx0, align 8
|
|
store <2 x float> %shuffle1, ptr %idx1, align 8
|
|
ret void
|
|
}
|
|
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
; CHECK: {{.*}}
|