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
130 lines
6.8 KiB
LLVM
130 lines
6.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -enable-subreg-liveness -mtriple=aarch64-linux-gnu -mattr=+sve,+sve-aes2 < %s | FileCheck %s
|
|
; RUN: llc -enable-subreg-liveness -mtriple=aarch64-linux-gnu -mattr=+sve-aes2,+ssve-aes -force-streaming < %s | FileCheck %s
|
|
|
|
;
|
|
; AESE
|
|
;
|
|
|
|
define { <vscale x 16 x i8>, <vscale x 16 x i8> } @aese_x2(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
|
|
; CHECK-LABEL: aese_x2:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: aese { z0.b, z1.b }, { z0.b, z1.b }, z2.q[0]
|
|
; CHECK-NEXT: ret
|
|
%out = call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.aese.lane.x2(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c, i32 0)
|
|
ret { <vscale x 16 x i8>, <vscale x 16 x i8> } %out
|
|
}
|
|
|
|
define { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @aese_x4(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c, <vscale x 16 x i8> %d) {
|
|
; CHECK-LABEL: aese_x4:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: aese { z0.b - z3.b }, { z0.b - z3.b }, z2.q[0]
|
|
; CHECK-NEXT: ret
|
|
%out= call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.aese.lane.x4(<vscale x 16 x i8> %a,
|
|
<vscale x 16 x i8> %b, <vscale x 16 x i8> %c,
|
|
<vscale x 16 x i8> %d, <vscale x 16 x i8> %c , i32 0)
|
|
ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } %out
|
|
}
|
|
|
|
;
|
|
; AESD
|
|
;
|
|
|
|
define { <vscale x 16 x i8>, <vscale x 16 x i8> } @aesd_x2(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
|
|
; CHECK-LABEL: aesd_x2:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: aesd { z0.b, z1.b }, { z0.b, z1.b }, z2.q[0]
|
|
; CHECK-NEXT: ret
|
|
%out= call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.aesd.lane.x2(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c, i32 0)
|
|
ret { <vscale x 16 x i8>, <vscale x 16 x i8> } %out
|
|
}
|
|
|
|
define { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @aesd_x4(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c, <vscale x 16 x i8> %d) {
|
|
; CHECK-LABEL: aesd_x4:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: aesd { z0.b - z3.b }, { z0.b - z3.b }, z2.q[0]
|
|
; CHECK-NEXT: ret
|
|
%out= call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.aesd.lane.x4(<vscale x 16 x i8> %a,
|
|
<vscale x 16 x i8> %b, <vscale x 16 x i8> %c,
|
|
<vscale x 16 x i8> %d, <vscale x 16 x i8> %c , i32 0)
|
|
ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } %out
|
|
}
|
|
|
|
|
|
;
|
|
; AESEMC
|
|
;
|
|
|
|
define { <vscale x 16 x i8>, <vscale x 16 x i8> } @aesemc_x2(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
|
|
; CHECK-LABEL: aesemc_x2:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: aesemc { z0.b, z1.b }, { z0.b, z1.b }, z2.q[0]
|
|
; CHECK-NEXT: ret
|
|
%out= call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.aesemc.lane.x2(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c, i32 0)
|
|
ret { <vscale x 16 x i8>, <vscale x 16 x i8> } %out
|
|
}
|
|
|
|
define { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @aesemc_x4(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c, <vscale x 16 x i8> %d) {
|
|
; CHECK-LABEL: aesemc_x4:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: aesemc { z0.b - z3.b }, { z0.b - z3.b }, z2.q[0]
|
|
; CHECK-NEXT: ret
|
|
%out= call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.aesemc.lane.x4(<vscale x 16 x i8> %a,
|
|
<vscale x 16 x i8> %b, <vscale x 16 x i8> %c,
|
|
<vscale x 16 x i8> %d, <vscale x 16 x i8> %c , i32 0)
|
|
ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } %out
|
|
}
|
|
|
|
;
|
|
; AESDIMC
|
|
;
|
|
|
|
define { <vscale x 16 x i8>, <vscale x 16 x i8> } @aesdimc_x2(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
|
|
; CHECK-LABEL: aesdimc_x2:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: aesdimc { z0.b, z1.b }, { z0.b, z1.b }, z2.q[0]
|
|
; CHECK-NEXT: ret
|
|
%out= call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.aesdimc.lane.x2(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c, i32 0)
|
|
ret { <vscale x 16 x i8>, <vscale x 16 x i8> } %out
|
|
}
|
|
|
|
define { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @aesdimc_x4(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c, <vscale x 16 x i8> %d) {
|
|
; CHECK-LABEL: aesdimc_x4:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: aesdimc { z0.b - z3.b }, { z0.b - z3.b }, z2.q[0]
|
|
; CHECK-NEXT: ret
|
|
%out= call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.aarch64.sve.aesdimc.lane.x4(<vscale x 16 x i8> %a,
|
|
<vscale x 16 x i8> %b, <vscale x 16 x i8> %c,
|
|
<vscale x 16 x i8> %d, <vscale x 16 x i8> %c , i32 0)
|
|
ret { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } %out
|
|
}
|
|
|
|
;
|
|
; PMULL
|
|
;
|
|
|
|
define { <vscale x 2 x i64>, <vscale x 2 x i64> } @pmull_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
|
|
; CHECK-LABEL: pmull_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: pmull { z0.q, z1.q }, z0.d, z1.d
|
|
; CHECK-NEXT: ret
|
|
%out = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sve.pmull.pair.x2(<vscale x 2 x i64> %a,
|
|
<vscale x 2 x i64> %b)
|
|
ret { <vscale x 2 x i64>, <vscale x 2 x i64> } %out
|
|
}
|
|
|
|
|
|
;
|
|
; PMLAL
|
|
;
|
|
|
|
define { <vscale x 2 x i64>, <vscale x 2 x i64> } @pmlal_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c, <vscale x 2 x i64> %d) {
|
|
; CHECK-LABEL: pmlal_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: pmlal { z0.q, z1.q }, z2.d, z3.d
|
|
; CHECK-NEXT: ret
|
|
%out = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.aarch64.sve.pmlal.pair.x2(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c,
|
|
<vscale x 2 x i64> %d)
|
|
ret { <vscale x 2 x i64>, <vscale x 2 x i64> } %out
|
|
}
|