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
88 lines
3.1 KiB
LLVM
88 lines
3.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mtriple=aarch64 < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SD
|
|
; RUN: llc -mtriple=aarch64 -global-isel < %s | FileCheck %s --check-prefixes=CHECK,CHECK-GI
|
|
|
|
define <8 x i8> @avgceil_u_i8_to_i16(<8 x i8> %a, <8 x i8> %b) {
|
|
; CHECK-SD-LABEL: avgceil_u_i8_to_i16:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: urhadd v0.8b, v0.8b, v1.8b
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: avgceil_u_i8_to_i16:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: ushll v0.8h, v0.8b, #0
|
|
; CHECK-GI-NEXT: ushll v1.8h, v1.8b, #0
|
|
; CHECK-GI-NEXT: urhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: xtn v0.8b, v0.8h
|
|
; CHECK-GI-NEXT: ret
|
|
%a16 = zext <8 x i8> %a to <8 x i16>
|
|
%b16 = zext <8 x i8> %b to <8 x i16>
|
|
%avg16 = call <8 x i16> @llvm.aarch64.neon.urhadd.v8i16(<8 x i16> %a16, <8 x i16> %b16)
|
|
%r = trunc <8 x i16> %avg16 to <8 x i8>
|
|
ret <8 x i8> %r
|
|
}
|
|
|
|
|
|
define <8 x i8> @test_avgceil_s(<8 x i8> %a, <8 x i8> %b) {
|
|
; CHECK-SD-LABEL: test_avgceil_s:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: srhadd v0.8b, v0.8b, v1.8b
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: test_avgceil_s:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-GI-NEXT: sshll v1.8h, v1.8b, #0
|
|
; CHECK-GI-NEXT: srhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: xtn v0.8b, v0.8h
|
|
; CHECK-GI-NEXT: ret
|
|
%a16 = sext <8 x i8> %a to <8 x i16>
|
|
%b16 = sext <8 x i8> %b to <8 x i16>
|
|
%avg16 = call <8 x i16> @llvm.aarch64.neon.srhadd.v8i16(<8 x i16> %a16, <8 x i16> %b16)
|
|
%res = trunc <8 x i16> %avg16 to <8 x i8>
|
|
ret <8 x i8> %res
|
|
}
|
|
|
|
define <8 x i8> @avgfloor_u_i8_to_i16(<8 x i8> %a, <8 x i8> %b) {
|
|
; CHECK-SD-LABEL: avgfloor_u_i8_to_i16:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: uhadd v0.8b, v0.8b, v1.8b
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: avgfloor_u_i8_to_i16:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: ushll v0.8h, v0.8b, #0
|
|
; CHECK-GI-NEXT: ushll v1.8h, v1.8b, #0
|
|
; CHECK-GI-NEXT: uhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: xtn v0.8b, v0.8h
|
|
; CHECK-GI-NEXT: ret
|
|
%a16 = zext <8 x i8> %a to <8 x i16>
|
|
%b16 = zext <8 x i8> %b to <8 x i16>
|
|
%avg16 = call <8 x i16> @llvm.aarch64.neon.uhadd.v8i16(<8 x i16> %a16, <8 x i16> %b16)
|
|
%res = trunc <8 x i16> %avg16 to <8 x i8>
|
|
ret <8 x i8> %res
|
|
}
|
|
|
|
define <8 x i8> @test_avgfloor_s(<8 x i8> %a, <8 x i8> %b) {
|
|
; CHECK-SD-LABEL: test_avgfloor_s:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: shadd v0.8b, v0.8b, v1.8b
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: test_avgfloor_s:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-GI-NEXT: sshll v1.8h, v1.8b, #0
|
|
; CHECK-GI-NEXT: shadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: xtn v0.8b, v0.8h
|
|
; CHECK-GI-NEXT: ret
|
|
%a16 = sext <8 x i8> %a to <8 x i16>
|
|
%b16 = sext <8 x i8> %b to <8 x i16>
|
|
%avg16 = call <8 x i16> @llvm.aarch64.neon.shadd.v8i16(<8 x i16> %a16, <8 x i16> %b16)
|
|
%res = trunc <8 x i16> %avg16 to <8 x i8>
|
|
ret <8 x i8> %res
|
|
}
|
|
|
|
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
; CHECK: {{.*}}
|