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
124 lines
6.7 KiB
LLVM
124 lines
6.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt -S -passes=instcombine < %s | FileCheck %s
|
|
; ARM64 AES intrinsic variants
|
|
|
|
define <16 x i8> @combineXorAeseZeroARM64(<16 x i8> %data, <16 x i8> %key) {
|
|
; CHECK-LABEL: define <16 x i8> @combineXorAeseZeroARM64(
|
|
; CHECK-SAME: <16 x i8> [[DATA:%.*]], <16 x i8> [[KEY:%.*]]) {
|
|
; CHECK-NEXT: [[DATA_AES:%.*]] = tail call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> [[DATA]], <16 x i8> [[KEY]])
|
|
; CHECK-NEXT: ret <16 x i8> [[DATA_AES]]
|
|
;
|
|
%data.xor = xor <16 x i8> %data, %key
|
|
%data.aes = tail call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %data.xor, <16 x i8> zeroinitializer)
|
|
ret <16 x i8> %data.aes
|
|
}
|
|
|
|
define <16 x i8> @combineXorAeseZeroLhsARM64(<16 x i8> %data, <16 x i8> %key) {
|
|
; CHECK-LABEL: define <16 x i8> @combineXorAeseZeroLhsARM64(
|
|
; CHECK-SAME: <16 x i8> [[DATA:%.*]], <16 x i8> [[KEY:%.*]]) {
|
|
; CHECK-NEXT: [[DATA_AES:%.*]] = tail call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> [[DATA]], <16 x i8> [[KEY]])
|
|
; CHECK-NEXT: ret <16 x i8> [[DATA_AES]]
|
|
;
|
|
%data.xor = xor <16 x i8> %data, %key
|
|
%data.aes = tail call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> zeroinitializer, <16 x i8> %data.xor)
|
|
ret <16 x i8> %data.aes
|
|
}
|
|
|
|
define <16 x i8> @combineXorAeseNonZeroARM64(<16 x i8> %data, <16 x i8> %key) {
|
|
; CHECK-LABEL: define <16 x i8> @combineXorAeseNonZeroARM64(
|
|
; CHECK-SAME: <16 x i8> [[DATA:%.*]], <16 x i8> [[KEY:%.*]]) {
|
|
; CHECK-NEXT: [[DATA_XOR:%.*]] = xor <16 x i8> [[DATA]], [[KEY]]
|
|
; CHECK-NEXT: [[DATA_AES:%.*]] = tail call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> [[DATA_XOR]], <16 x i8> splat (i8 -1))
|
|
; CHECK-NEXT: ret <16 x i8> [[DATA_AES]]
|
|
;
|
|
%data.xor = xor <16 x i8> %data, %key
|
|
%data.aes = tail call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %data.xor, <16 x i8> <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>)
|
|
ret <16 x i8> %data.aes
|
|
}
|
|
|
|
define <16 x i8> @combineXorAesdZeroARM64(<16 x i8> %data, <16 x i8> %key) {
|
|
; CHECK-LABEL: define <16 x i8> @combineXorAesdZeroARM64(
|
|
; CHECK-SAME: <16 x i8> [[DATA:%.*]], <16 x i8> [[KEY:%.*]]) {
|
|
; CHECK-NEXT: [[DATA_AES:%.*]] = tail call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> [[DATA]], <16 x i8> [[KEY]])
|
|
; CHECK-NEXT: ret <16 x i8> [[DATA_AES]]
|
|
;
|
|
%data.xor = xor <16 x i8> %data, %key
|
|
%data.aes = tail call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %data.xor, <16 x i8> zeroinitializer)
|
|
ret <16 x i8> %data.aes
|
|
}
|
|
|
|
define <16 x i8> @combineXorAesdZeroLhsARM64(<16 x i8> %data, <16 x i8> %key) {
|
|
; CHECK-LABEL: define <16 x i8> @combineXorAesdZeroLhsARM64(
|
|
; CHECK-SAME: <16 x i8> [[DATA:%.*]], <16 x i8> [[KEY:%.*]]) {
|
|
; CHECK-NEXT: [[DATA_AES:%.*]] = tail call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> [[DATA]], <16 x i8> [[KEY]])
|
|
; CHECK-NEXT: ret <16 x i8> [[DATA_AES]]
|
|
;
|
|
%data.xor = xor <16 x i8> %data, %key
|
|
%data.aes = tail call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> zeroinitializer, <16 x i8> %data.xor)
|
|
ret <16 x i8> %data.aes
|
|
}
|
|
|
|
define <16 x i8> @combineXorAesdNonZeroARM64(<16 x i8> %data, <16 x i8> %key) {
|
|
; CHECK-LABEL: define <16 x i8> @combineXorAesdNonZeroARM64(
|
|
; CHECK-SAME: <16 x i8> [[DATA:%.*]], <16 x i8> [[KEY:%.*]]) {
|
|
; CHECK-NEXT: [[DATA_XOR:%.*]] = xor <16 x i8> [[DATA]], [[KEY]]
|
|
; CHECK-NEXT: [[DATA_AES:%.*]] = tail call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> [[DATA_XOR]], <16 x i8> splat (i8 -1))
|
|
; CHECK-NEXT: ret <16 x i8> [[DATA_AES]]
|
|
;
|
|
%data.xor = xor <16 x i8> %data, %key
|
|
%data.aes = tail call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %data.xor, <16 x i8> <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>)
|
|
ret <16 x i8> %data.aes
|
|
}
|
|
|
|
declare <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8>, <16 x i8>) #0
|
|
declare <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8>, <16 x i8>) #0
|
|
|
|
; SVE
|
|
|
|
define <vscale x 16 x i8> @combineXorAeseZeroLhsSVE(<vscale x 16 x i8> %data, <vscale x 16 x i8> %key) {
|
|
; CHECK-LABEL: define <vscale x 16 x i8> @combineXorAeseZeroLhsSVE(
|
|
; CHECK-SAME: <vscale x 16 x i8> [[DATA:%.*]], <vscale x 16 x i8> [[KEY:%.*]]) {
|
|
; CHECK-NEXT: [[DATA_AES:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.aese(<vscale x 16 x i8> [[DATA]], <vscale x 16 x i8> [[KEY]])
|
|
; CHECK-NEXT: ret <vscale x 16 x i8> [[DATA_AES]]
|
|
;
|
|
%data.xor = xor <vscale x 16 x i8> %data, %key
|
|
%data.aes = tail call <vscale x 16 x i8> @llvm.aarch64.sve.aese(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> %data.xor)
|
|
ret <vscale x 16 x i8> %data.aes
|
|
}
|
|
|
|
define <vscale x 16 x i8> @combineXorAeseZeroRhsSVE(<vscale x 16 x i8> %data, <vscale x 16 x i8> %key) {
|
|
; CHECK-LABEL: define <vscale x 16 x i8> @combineXorAeseZeroRhsSVE(
|
|
; CHECK-SAME: <vscale x 16 x i8> [[DATA:%.*]], <vscale x 16 x i8> [[KEY:%.*]]) {
|
|
; CHECK-NEXT: [[DATA_AES:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.aese(<vscale x 16 x i8> [[DATA]], <vscale x 16 x i8> [[KEY]])
|
|
; CHECK-NEXT: ret <vscale x 16 x i8> [[DATA_AES]]
|
|
;
|
|
%data.xor = xor <vscale x 16 x i8> %data, %key
|
|
%data.aes = tail call <vscale x 16 x i8> @llvm.aarch64.sve.aese(<vscale x 16 x i8> %data.xor, <vscale x 16 x i8> zeroinitializer)
|
|
ret <vscale x 16 x i8> %data.aes
|
|
}
|
|
|
|
define <vscale x 16 x i8> @combineXorAesdZeroLhsSVE(<vscale x 16 x i8> %data, <vscale x 16 x i8> %key) {
|
|
; CHECK-LABEL: define <vscale x 16 x i8> @combineXorAesdZeroLhsSVE(
|
|
; CHECK-SAME: <vscale x 16 x i8> [[DATA:%.*]], <vscale x 16 x i8> [[KEY:%.*]]) {
|
|
; CHECK-NEXT: [[DATA_AES:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.aesd(<vscale x 16 x i8> [[DATA]], <vscale x 16 x i8> [[KEY]])
|
|
; CHECK-NEXT: ret <vscale x 16 x i8> [[DATA_AES]]
|
|
;
|
|
%data.xor = xor <vscale x 16 x i8> %data, %key
|
|
%data.aes = tail call <vscale x 16 x i8> @llvm.aarch64.sve.aesd(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> %data.xor)
|
|
ret <vscale x 16 x i8> %data.aes
|
|
}
|
|
|
|
define <vscale x 16 x i8> @combineXorAesdZeroRhsSVE(<vscale x 16 x i8> %data, <vscale x 16 x i8> %key) {
|
|
; CHECK-LABEL: define <vscale x 16 x i8> @combineXorAesdZeroRhsSVE(
|
|
; CHECK-SAME: <vscale x 16 x i8> [[DATA:%.*]], <vscale x 16 x i8> [[KEY:%.*]]) {
|
|
; CHECK-NEXT: [[DATA_AES:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.aesd(<vscale x 16 x i8> [[DATA]], <vscale x 16 x i8> [[KEY]])
|
|
; CHECK-NEXT: ret <vscale x 16 x i8> [[DATA_AES]]
|
|
;
|
|
%data.xor = xor <vscale x 16 x i8> %data, %key
|
|
%data.aes = tail call <vscale x 16 x i8> @llvm.aarch64.sve.aesd(<vscale x 16 x i8> %data.xor, <vscale x 16 x i8> zeroinitializer)
|
|
ret <vscale x 16 x i8> %data.aes
|
|
}
|
|
|
|
declare <vscale x 16 x i8> @llvm.aarch64.sve.aese(<vscale x 16 x i8>, <vscale x 16 x i8>) #0
|
|
declare <vscale x 16 x i8> @llvm.aarch64.sve.aesd(<vscale x 16 x i8>, <vscale x 16 x i8>) #0
|