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
133 lines
6.8 KiB
LLVM
133 lines
6.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -O3 -disable-peephole -mtriple=x86_64-unknown-unknown -mattr=+sha < %s | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-unknown"
|
|
|
|
; Stack reload folding tests.
|
|
;
|
|
; By including a nop call with sideeffects we can force a partial register spill of the
|
|
; relevant registers and check that the reload is correctly folded into the instruction.
|
|
|
|
define <4 x i32> @stack_fold_sha1msg1(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK-LABEL: stack_fold_sha1msg1:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: sha1msg1 {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
|
|
%2 = tail call <4 x i32> @llvm.x86.sha1msg1(<4 x i32> %a0, <4 x i32> %a1)
|
|
ret <4 x i32> %2
|
|
}
|
|
declare <4 x i32> @llvm.x86.sha1msg1(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
define <4 x i32> @stack_fold_sha1msg2(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK-LABEL: stack_fold_sha1msg2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: sha1msg2 {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
|
|
%2 = tail call <4 x i32> @llvm.x86.sha1msg2(<4 x i32> %a0, <4 x i32> %a1)
|
|
ret <4 x i32> %2
|
|
}
|
|
declare <4 x i32> @llvm.x86.sha1msg2(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
define <4 x i32> @stack_fold_sha1nexte(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK-LABEL: stack_fold_sha1nexte:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: sha1nexte {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
|
|
%2 = tail call <4 x i32> @llvm.x86.sha1nexte(<4 x i32> %a0, <4 x i32> %a1)
|
|
ret <4 x i32> %2
|
|
}
|
|
declare <4 x i32> @llvm.x86.sha1nexte(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
define <4 x i32> @stack_fold_sha1rnds4(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK-LABEL: stack_fold_sha1rnds4:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: sha1rnds4 $3, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
|
|
%2 = tail call <4 x i32> @llvm.x86.sha1rnds4(<4 x i32> %a0, <4 x i32> %a1, i8 3)
|
|
ret <4 x i32> %2
|
|
}
|
|
declare <4 x i32> @llvm.x86.sha1rnds4(<4 x i32>, <4 x i32>, i8) nounwind readnone
|
|
|
|
define <4 x i32> @stack_fold_sha256msg1(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK-LABEL: stack_fold_sha256msg1:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: sha256msg1 {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
|
|
%2 = tail call <4 x i32> @llvm.x86.sha256msg1(<4 x i32> %a0, <4 x i32> %a1)
|
|
ret <4 x i32> %2
|
|
}
|
|
declare <4 x i32> @llvm.x86.sha256msg1(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
define <4 x i32> @stack_fold_sha256msg2(<4 x i32> %a0, <4 x i32> %a1) {
|
|
; CHECK-LABEL: stack_fold_sha256msg2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: sha256msg2 {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
|
|
%2 = tail call <4 x i32> @llvm.x86.sha256msg2(<4 x i32> %a0, <4 x i32> %a1)
|
|
ret <4 x i32> %2
|
|
}
|
|
declare <4 x i32> @llvm.x86.sha256msg2(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
define <4 x i32> @stack_fold_sha256rnds2(<4 x i32> %a0, <4 x i32> %a1, <4 x i32> %a2) {
|
|
; CHECK-LABEL: stack_fold_sha256rnds2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
|
; CHECK-NEXT: sha256rnds2 %xmm0, {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
|
|
; CHECK-NEXT: movaps %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
|
|
%2 = tail call <4 x i32> @llvm.x86.sha256rnds2(<4 x i32> %a0, <4 x i32> %a1, <4 x i32> %a2)
|
|
ret <4 x i32> %2
|
|
}
|
|
declare <4 x i32> @llvm.x86.sha256rnds2(<4 x i32>, <4 x i32>, <4 x i32>) nounwind readnone
|