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
92 lines
3.2 KiB
LLVM
92 lines
3.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple aarch64-none-linux-gnu < %s | FileCheck %s
|
|
|
|
declare <16 x i32> @llvm.abs.v16i32(<16 x i32>, i1 immarg)
|
|
declare i32 @llvm.vector.reduce.add.v16i32(<16 x i32>)
|
|
|
|
define i32 @test_sad_v16i8_zext(ptr nocapture readonly %a, ptr nocapture readonly %b) {
|
|
; CHECK-LABEL: test_sad_v16i8_zext:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ldr q0, [x0]
|
|
; CHECK-NEXT: ldr q1, [x1]
|
|
; CHECK-NEXT: uabdl v2.8h, v1.8b, v0.8b
|
|
; CHECK-NEXT: uabal2 v2.8h, v1.16b, v0.16b
|
|
; CHECK-NEXT: uaddlv s0, v2.8h
|
|
; CHECK-NEXT: fmov w0, s0
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%0 = load <16 x i8>, ptr %a
|
|
%1 = zext <16 x i8> %0 to <16 x i32>
|
|
%2 = load <16 x i8>, ptr %b
|
|
%3 = zext <16 x i8> %2 to <16 x i32>
|
|
%4 = sub nsw <16 x i32> %3, %1
|
|
%5 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> %4, i1 true)
|
|
%6 = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %5)
|
|
ret i32 %6
|
|
}
|
|
|
|
define i32 @test_sad_v16i8_sext(ptr nocapture readonly %a, ptr nocapture readonly %b) {
|
|
; CHECK-LABEL: test_sad_v16i8_sext:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ldr q0, [x0]
|
|
; CHECK-NEXT: ldr q1, [x1]
|
|
; CHECK-NEXT: sabdl v2.8h, v1.8b, v0.8b
|
|
; CHECK-NEXT: sabal2 v2.8h, v1.16b, v0.16b
|
|
; CHECK-NEXT: uaddlv s0, v2.8h
|
|
; CHECK-NEXT: fmov w0, s0
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%0 = load <16 x i8>, ptr %a
|
|
%1 = sext <16 x i8> %0 to <16 x i32>
|
|
%2 = load <16 x i8>, ptr %b
|
|
%3 = sext <16 x i8> %2 to <16 x i32>
|
|
%4 = sub nsw <16 x i32> %3, %1
|
|
%5 = call <16 x i32> @llvm.abs.v16i32(<16 x i32> %4, i1 true)
|
|
%6 = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %5)
|
|
ret i32 %6
|
|
}
|
|
|
|
define i32 @test_sad_v16i8_two_step_zext(ptr noundef readonly %a, ptr noundef readonly %b) {
|
|
; CHECK-LABEL: test_sad_v16i8_two_step_zext:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ldr q0, [x0]
|
|
; CHECK-NEXT: ldr q1, [x1]
|
|
; CHECK-NEXT: uabdl v2.8h, v1.8b, v0.8b
|
|
; CHECK-NEXT: uabal2 v2.8h, v1.16b, v0.16b
|
|
; CHECK-NEXT: uaddlv s0, v2.8h
|
|
; CHECK-NEXT: fmov w0, s0
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%0 = load <16 x i8>, ptr %a
|
|
%1 = zext <16 x i8> %0 to <16 x i16>
|
|
%2 = load <16 x i8>, ptr %b
|
|
%3 = zext <16 x i8> %2 to <16 x i16>
|
|
%4 = sub nsw <16 x i16> %3, %1
|
|
%5 = tail call <16 x i16> @llvm.abs.v16i16(<16 x i16> %4, i1 false)
|
|
%6 = zext <16 x i16> %5 to <16 x i32>
|
|
%7 = tail call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %6)
|
|
ret i32 %7
|
|
}
|
|
|
|
define i32 @test_sad_v16i8_two_step_sext(ptr noundef readonly %a, ptr noundef readonly %b) {
|
|
; CHECK-LABEL: test_sad_v16i8_two_step_sext:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ldr q0, [x0]
|
|
; CHECK-NEXT: ldr q1, [x1]
|
|
; CHECK-NEXT: sabdl v2.8h, v1.8b, v0.8b
|
|
; CHECK-NEXT: sabal2 v2.8h, v1.16b, v0.16b
|
|
; CHECK-NEXT: uaddlv s0, v2.8h
|
|
; CHECK-NEXT: fmov w0, s0
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%0 = load <16 x i8>, ptr %a
|
|
%1 = sext <16 x i8> %0 to <16 x i16>
|
|
%2 = load <16 x i8>, ptr %b
|
|
%3 = sext <16 x i8> %2 to <16 x i16>
|
|
%4 = sub nsw <16 x i16> %3, %1
|
|
%5 = tail call <16 x i16> @llvm.abs.v16i16(<16 x i16> %4, i1 false)
|
|
%6 = zext <16 x i16> %5 to <16 x i32>
|
|
%7 = tail call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %6)
|
|
ret i32 %7
|
|
}
|