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
196 lines
7.5 KiB
LLVM
196 lines
7.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
|
|
; RUN: llc < %s -mtriple=aarch64 | FileCheck %s --check-prefixes=CHECK,CHECK-SD
|
|
; RUN: llc < %s -mtriple=aarch64 -global-isel | FileCheck %s --check-prefixes=CHECK,CHECK-GI
|
|
|
|
declare <8 x i16> @llvm.aarch64.neon.uhadd.v8i16(<8 x i16>, <8 x i16>)
|
|
declare <8 x i16> @llvm.aarch64.neon.urhadd.v8i16(<8 x i16>, <8 x i16>)
|
|
declare <8 x i16> @llvm.aarch64.neon.shadd.v8i16(<8 x i16>, <8 x i16>)
|
|
declare <8 x i16> @llvm.aarch64.neon.srhadd.v8i16(<8 x i16>, <8 x i16>)
|
|
|
|
define <8 x i16> @haddu_zext(<8 x i8> %a0, <8 x i8> %a1) {
|
|
; CHECK-SD-LABEL: haddu_zext:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: uhadd v0.8b, v0.8b, v1.8b
|
|
; CHECK-SD-NEXT: ushll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: haddu_zext:
|
|
; 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: mvni v2.8h, #254, lsl #8
|
|
; CHECK-GI-NEXT: uhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: and v0.16b, v0.16b, v2.16b
|
|
; CHECK-GI-NEXT: ret
|
|
%x0 = zext <8 x i8> %a0 to <8 x i16>
|
|
%x1 = zext <8 x i8> %a1 to <8 x i16>
|
|
%hadd = call <8 x i16> @llvm.aarch64.neon.uhadd.v8i16(<8 x i16> %x0, <8 x i16> %x1)
|
|
%res = and <8 x i16> %hadd, <i16 511, i16 511, i16 511, i16 511,i16 511, i16 511, i16 511, i16 511>
|
|
ret <8 x i16> %res
|
|
}
|
|
|
|
define <8 x i16> @rhaddu_zext(<8 x i8> %a0, <8 x i8> %a1) {
|
|
; CHECK-SD-LABEL: rhaddu_zext:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: urhadd v0.8b, v0.8b, v1.8b
|
|
; CHECK-SD-NEXT: ushll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: rhaddu_zext:
|
|
; 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: mvni v2.8h, #254, lsl #8
|
|
; CHECK-GI-NEXT: urhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: and v0.16b, v0.16b, v2.16b
|
|
; CHECK-GI-NEXT: ret
|
|
%x0 = zext <8 x i8> %a0 to <8 x i16>
|
|
%x1 = zext <8 x i8> %a1 to <8 x i16>
|
|
%hadd = call <8 x i16> @llvm.aarch64.neon.urhadd.v8i16(<8 x i16> %x0, <8 x i16> %x1)
|
|
%res = and <8 x i16> %hadd, <i16 511, i16 511, i16 511, i16 511, i16 511, i16 511, i16 511, i16 511>
|
|
ret <8 x i16> %res
|
|
}
|
|
|
|
define <8 x i16> @hadds_zext(<8 x i8> %a0, <8 x i8> %a1) {
|
|
; CHECK-SD-LABEL: hadds_zext:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: uhadd v0.8b, v0.8b, v1.8b
|
|
; CHECK-SD-NEXT: ushll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: hadds_zext:
|
|
; 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: mvni v2.8h, #254, lsl #8
|
|
; CHECK-GI-NEXT: shadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: and v0.16b, v0.16b, v2.16b
|
|
; CHECK-GI-NEXT: ret
|
|
%x0 = zext <8 x i8> %a0 to <8 x i16>
|
|
%x1 = zext <8 x i8> %a1 to <8 x i16>
|
|
%hadd = call <8 x i16> @llvm.aarch64.neon.shadd.v8i16(<8 x i16> %x0, <8 x i16> %x1)
|
|
%res = and <8 x i16> %hadd, <i16 511, i16 511, i16 511, i16 511, i16 511, i16 511, i16 511, i16 511>
|
|
ret <8 x i16> %res
|
|
}
|
|
|
|
define <8 x i16> @shaddu_zext(<8 x i8> %a0, <8 x i8> %a1) {
|
|
; CHECK-SD-LABEL: shaddu_zext:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: ushll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: ushll v1.8h, v1.8b, #0
|
|
; CHECK-SD-NEXT: srhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: shaddu_zext:
|
|
; 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: mvni v2.8h, #254, lsl #8
|
|
; CHECK-GI-NEXT: srhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: and v0.16b, v0.16b, v2.16b
|
|
; CHECK-GI-NEXT: ret
|
|
%x0 = zext <8 x i8> %a0 to <8 x i16>
|
|
%x1 = zext <8 x i8> %a1 to <8 x i16>
|
|
%hadd = call <8 x i16> @llvm.aarch64.neon.srhadd.v8i16(<8 x i16> %x0, <8 x i16> %x1)
|
|
%res = and <8 x i16> %hadd, <i16 511, i16 511, i16 511, i16 511, i16 511, i16 511, i16 511, i16 511>
|
|
ret <8 x i16> %res
|
|
}
|
|
|
|
; ; negative tests
|
|
|
|
define <8 x i16> @haddu_sext(<8 x i8> %a0, <8 x i8> %a1) {
|
|
; CHECK-SD-LABEL: haddu_sext:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: sshll v1.8h, v1.8b, #0
|
|
; CHECK-SD-NEXT: uhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-SD-NEXT: bic v0.8h, #254, lsl #8
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: haddu_sext:
|
|
; 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: mvni v2.8h, #254, lsl #8
|
|
; CHECK-GI-NEXT: uhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: and v0.16b, v0.16b, v2.16b
|
|
; CHECK-GI-NEXT: ret
|
|
%x0 = sext <8 x i8> %a0 to <8 x i16>
|
|
%x1 = sext <8 x i8> %a1 to <8 x i16>
|
|
%hadd = call <8 x i16> @llvm.aarch64.neon.uhadd.v8i16(<8 x i16> %x0, <8 x i16> %x1)
|
|
%res = and <8 x i16> %hadd, <i16 511, i16 511, i16 511, i16 511,i16 511, i16 511, i16 511, i16 511>
|
|
ret <8 x i16> %res
|
|
}
|
|
|
|
define <8 x i16> @urhadd_sext(<8 x i8> %a0, <8 x i8> %a1) {
|
|
; CHECK-SD-LABEL: urhadd_sext:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: sshll v1.8h, v1.8b, #0
|
|
; CHECK-SD-NEXT: urhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-SD-NEXT: bic v0.8h, #254, lsl #8
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: urhadd_sext:
|
|
; 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: mvni v2.8h, #254, lsl #8
|
|
; CHECK-GI-NEXT: urhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: and v0.16b, v0.16b, v2.16b
|
|
; CHECK-GI-NEXT: ret
|
|
%x0 = sext <8 x i8> %a0 to <8 x i16>
|
|
%x1 = sext <8 x i8> %a1 to <8 x i16>
|
|
%hadd = call <8 x i16> @llvm.aarch64.neon.urhadd.v8i16(<8 x i16> %x0, <8 x i16> %x1)
|
|
%res = and <8 x i16> %hadd, <i16 511, i16 511, i16 511, i16 511,i16 511, i16 511, i16 511, i16 511>
|
|
ret <8 x i16> %res
|
|
}
|
|
|
|
define <8 x i16> @hadds_sext(<8 x i8> %a0, <8 x i8> %a1) {
|
|
; CHECK-SD-LABEL: hadds_sext:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: shadd v0.8b, v0.8b, v1.8b
|
|
; CHECK-SD-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: bic v0.8h, #254, lsl #8
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: hadds_sext:
|
|
; 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: mvni v2.8h, #254, lsl #8
|
|
; CHECK-GI-NEXT: shadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: and v0.16b, v0.16b, v2.16b
|
|
; CHECK-GI-NEXT: ret
|
|
%x0 = sext <8 x i8> %a0 to <8 x i16>
|
|
%x1 = sext <8 x i8> %a1 to <8 x i16>
|
|
%hadd = call <8 x i16> @llvm.aarch64.neon.shadd.v8i16(<8 x i16> %x0, <8 x i16> %x1)
|
|
%res = and <8 x i16> %hadd, <i16 511, i16 511, i16 511, i16 511, i16 511, i16 511, i16 511, i16 511>
|
|
ret <8 x i16> %res
|
|
}
|
|
|
|
define <8 x i16> @shaddu_sext(<8 x i8> %a0, <8 x i8> %a1) {
|
|
; CHECK-SD-LABEL: shaddu_sext:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: srhadd v0.8b, v0.8b, v1.8b
|
|
; CHECK-SD-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: bic v0.8h, #254, lsl #8
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: shaddu_sext:
|
|
; 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: mvni v2.8h, #254, lsl #8
|
|
; CHECK-GI-NEXT: srhadd v0.8h, v0.8h, v1.8h
|
|
; CHECK-GI-NEXT: and v0.16b, v0.16b, v2.16b
|
|
; CHECK-GI-NEXT: ret
|
|
%x0 = sext <8 x i8> %a0 to <8 x i16>
|
|
%x1 = sext <8 x i8> %a1 to <8 x i16>
|
|
%hadd = call <8 x i16> @llvm.aarch64.neon.srhadd.v8i16(<8 x i16> %x0, <8 x i16> %x1)
|
|
%res = and <8 x i16> %hadd, <i16 511, i16 511, i16 511, i16 511, i16 511, i16 511, i16 511, i16 511>
|
|
ret <8 x i16> %res
|
|
}
|
|
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
; CHECK: {{.*}}
|