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
110 lines
3.7 KiB
LLVM
110 lines
3.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --extra_scrub
|
|
; RUN: llc -mtriple=aarch64 -mattr=+sha3 < %s | FileCheck --check-prefix=SHA3 %s
|
|
; RUN: llc -mtriple=aarch64 -mattr=-sha3 < %s | FileCheck --check-prefix=NOSHA3 %s
|
|
; RUN: llc -mtriple=aarch64 -mattr=+sve2 < %s | FileCheck --check-prefix=SVE2 %s
|
|
; RUN: llc -mtriple=aarch64 -mattr=+sha3,+sve2 < %s | FileCheck --check-prefix=SHA3 %s
|
|
|
|
define <2 x i64> @bcax_64x2(<2 x i64> %0, <2 x i64> %1, <2 x i64> %2) {
|
|
; SHA3-LABEL: bcax_64x2:
|
|
; SHA3: // %bb.0:
|
|
; SHA3-NEXT: bcax v0.16b, v2.16b, v0.16b, v1.16b
|
|
; SHA3-NEXT: ret
|
|
;
|
|
; NOSHA3-LABEL: bcax_64x2:
|
|
; NOSHA3: // %bb.0:
|
|
; NOSHA3-NEXT: bic v0.16b, v0.16b, v1.16b
|
|
; NOSHA3-NEXT: eor v0.16b, v0.16b, v2.16b
|
|
; NOSHA3-NEXT: ret
|
|
;
|
|
; SVE2-LABEL: bcax_64x2:
|
|
; SVE2: // %bb.0:
|
|
; SVE2-NEXT: // kill: def $q2 killed $q2 def $z2
|
|
; SVE2-NEXT: // kill: def $q1 killed $q1 def $z1
|
|
; SVE2-NEXT: // kill: def $q0 killed $q0 def $z0
|
|
; SVE2-NEXT: bcax z2.d, z2.d, z0.d, z1.d
|
|
; SVE2-NEXT: mov v0.16b, v2.16b
|
|
; SVE2-NEXT: ret
|
|
%4 = xor <2 x i64> %1, <i64 -1, i64 -1>
|
|
%5 = and <2 x i64> %4, %0
|
|
%6 = xor <2 x i64> %5, %2
|
|
ret <2 x i64> %6
|
|
}
|
|
|
|
define <4 x i32> @bcax_32x4(<4 x i32> %0, <4 x i32> %1, <4 x i32> %2) {
|
|
; SHA3-LABEL: bcax_32x4:
|
|
; SHA3: // %bb.0:
|
|
; SHA3-NEXT: bcax v0.16b, v2.16b, v0.16b, v1.16b
|
|
; SHA3-NEXT: ret
|
|
;
|
|
; NOSHA3-LABEL: bcax_32x4:
|
|
; NOSHA3: // %bb.0:
|
|
; NOSHA3-NEXT: bic v0.16b, v0.16b, v1.16b
|
|
; NOSHA3-NEXT: eor v0.16b, v0.16b, v2.16b
|
|
; NOSHA3-NEXT: ret
|
|
;
|
|
; SVE2-LABEL: bcax_32x4:
|
|
; SVE2: // %bb.0:
|
|
; SVE2-NEXT: // kill: def $q2 killed $q2 def $z2
|
|
; SVE2-NEXT: // kill: def $q1 killed $q1 def $z1
|
|
; SVE2-NEXT: // kill: def $q0 killed $q0 def $z0
|
|
; SVE2-NEXT: bcax z2.d, z2.d, z0.d, z1.d
|
|
; SVE2-NEXT: mov v0.16b, v2.16b
|
|
; SVE2-NEXT: ret
|
|
%4 = xor <4 x i32> %1, <i32 -1, i32 -1, i32 -1, i32 -1>
|
|
%5 = and <4 x i32> %4, %0
|
|
%6 = xor <4 x i32> %5, %2
|
|
ret <4 x i32> %6
|
|
}
|
|
|
|
define <8 x i16> @bcax_16x8(<8 x i16> %0, <8 x i16> %1, <8 x i16> %2) {
|
|
; SHA3-LABEL: bcax_16x8:
|
|
; SHA3: // %bb.0:
|
|
; SHA3-NEXT: bcax v0.16b, v2.16b, v0.16b, v1.16b
|
|
; SHA3-NEXT: ret
|
|
;
|
|
; NOSHA3-LABEL: bcax_16x8:
|
|
; NOSHA3: // %bb.0:
|
|
; NOSHA3-NEXT: bic v0.16b, v0.16b, v1.16b
|
|
; NOSHA3-NEXT: eor v0.16b, v0.16b, v2.16b
|
|
; NOSHA3-NEXT: ret
|
|
;
|
|
; SVE2-LABEL: bcax_16x8:
|
|
; SVE2: // %bb.0:
|
|
; SVE2-NEXT: // kill: def $q2 killed $q2 def $z2
|
|
; SVE2-NEXT: // kill: def $q1 killed $q1 def $z1
|
|
; SVE2-NEXT: // kill: def $q0 killed $q0 def $z0
|
|
; SVE2-NEXT: bcax z2.d, z2.d, z0.d, z1.d
|
|
; SVE2-NEXT: mov v0.16b, v2.16b
|
|
; SVE2-NEXT: ret
|
|
%4 = xor <8 x i16> %1, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
|
|
%5 = and <8 x i16> %4, %0
|
|
%6 = xor <8 x i16> %5, %2
|
|
ret <8 x i16> %6
|
|
}
|
|
|
|
define <16 x i8> @bcax_8x16(<16 x i8> %0, <16 x i8> %1, <16 x i8> %2) {
|
|
; SHA3-LABEL: bcax_8x16:
|
|
; SHA3: // %bb.0:
|
|
; SHA3-NEXT: bcax v0.16b, v2.16b, v0.16b, v1.16b
|
|
; SHA3-NEXT: ret
|
|
;
|
|
; NOSHA3-LABEL: bcax_8x16:
|
|
; NOSHA3: // %bb.0:
|
|
; NOSHA3-NEXT: bic v0.16b, v0.16b, v1.16b
|
|
; NOSHA3-NEXT: eor v0.16b, v0.16b, v2.16b
|
|
; NOSHA3-NEXT: ret
|
|
;
|
|
; SVE2-LABEL: bcax_8x16:
|
|
; SVE2: // %bb.0:
|
|
; SVE2-NEXT: // kill: def $q2 killed $q2 def $z2
|
|
; SVE2-NEXT: // kill: def $q1 killed $q1 def $z1
|
|
; SVE2-NEXT: // kill: def $q0 killed $q0 def $z0
|
|
; SVE2-NEXT: bcax z2.d, z2.d, z0.d, z1.d
|
|
; SVE2-NEXT: mov v0.16b, v2.16b
|
|
; SVE2-NEXT: ret
|
|
%4 = xor <16 x i8> %1, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
|
|
%5 = and <16 x i8> %4, %0
|
|
%6 = xor <16 x i8> %5, %2
|
|
ret <16 x i8> %6
|
|
}
|