Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/PowerPC/mma-integer-based-outer-product.ll
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

398 lines
15 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
; RUN: -mcpu=pwr10 -ppc-asm-full-reg-names \
; RUN: -ppc-vsr-nums-as-vr < %s | FileCheck %s
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu \
; RUN: -mcpu=pwr10 -ppc-asm-full-reg-names \
; RUN: -ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=CHECK-BE
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
; RUN: -mcpu=future -ppc-asm-full-reg-names \
; RUN: -ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=CHECK-LE-WACC
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu \
; RUN: -mcpu=future -ppc-asm-full-reg-names \
; RUN: -ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=CHECK-BE-WACC
; Function Attrs: nofree nounwind writeonly
define dso_local void @test1(ptr nocapture readnone %vqp, ptr nocapture readnone %vpp, <16 x i8> %vc, ptr nocapture %resp) {
; CHECK-LABEL: test1:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xvi16ger2 acc0, v2, v2
; CHECK-NEXT: xxmfacc acc0
; CHECK-NEXT: stxv vs0, 48(r7)
; CHECK-NEXT: stxv vs1, 32(r7)
; CHECK-NEXT: stxv vs2, 16(r7)
; CHECK-NEXT: stxv vs3, 0(r7)
; CHECK-NEXT: blr
;
; CHECK-BE-LABEL: test1:
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: xvi16ger2 acc0, v2, v2
; CHECK-BE-NEXT: xxmfacc acc0
; CHECK-BE-NEXT: stxv vs1, 16(r7)
; CHECK-BE-NEXT: stxv vs0, 0(r7)
; CHECK-BE-NEXT: stxv vs3, 48(r7)
; CHECK-BE-NEXT: stxv vs2, 32(r7)
; CHECK-BE-NEXT: blr
;
; CHECK-LE-WACC-LABEL: test1:
; CHECK-LE-WACC: # %bb.0: # %entry
; CHECK-LE-WACC-NEXT: xvi16ger2 wacc0, v2, v2
; CHECK-LE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-LE-WACC-NEXT: stxv v4, 48(r7)
; CHECK-LE-WACC-NEXT: stxv v5, 32(r7)
; CHECK-LE-WACC-NEXT: stxv v2, 16(r7)
; CHECK-LE-WACC-NEXT: stxv v3, 0(r7)
; CHECK-LE-WACC-NEXT: blr
;
; CHECK-BE-WACC-LABEL: test1:
; CHECK-BE-WACC: # %bb.0: # %entry
; CHECK-BE-WACC-NEXT: xvi16ger2 wacc0, v2, v2
; CHECK-BE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-BE-WACC-NEXT: stxv v5, 48(r7)
; CHECK-BE-WACC-NEXT: stxv v4, 32(r7)
; CHECK-BE-WACC-NEXT: stxv v3, 16(r7)
; CHECK-BE-WACC-NEXT: stxv v2, 0(r7)
; CHECK-BE-WACC-NEXT: blr
entry:
%0 = tail call <512 x i1> @llvm.ppc.mma.xvi16ger2(<16 x i8> %vc, <16 x i8> %vc)
store <512 x i1> %0, ptr %resp, align 64
ret void
}
; Function Attrs: nounwind readnone
declare <512 x i1> @llvm.ppc.mma.xvi16ger2(<16 x i8>, <16 x i8>)
; Function Attrs: nofree nounwind writeonly
define dso_local void @test2(ptr nocapture readnone %vqp, ptr nocapture readnone %vpp, <16 x i8> %vc, ptr nocapture %resp) {
; CHECK-LABEL: test2:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: pmxvi16ger2 acc0, v2, v2, 0, 0, 0
; CHECK-NEXT: xxmfacc acc0
; CHECK-NEXT: stxv vs0, 48(r7)
; CHECK-NEXT: stxv vs1, 32(r7)
; CHECK-NEXT: stxv vs2, 16(r7)
; CHECK-NEXT: stxv vs3, 0(r7)
; CHECK-NEXT: blr
;
; CHECK-BE-LABEL: test2:
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: pmxvi16ger2 acc0, v2, v2, 0, 0, 0
; CHECK-BE-NEXT: xxmfacc acc0
; CHECK-BE-NEXT: stxv vs1, 16(r7)
; CHECK-BE-NEXT: stxv vs0, 0(r7)
; CHECK-BE-NEXT: stxv vs3, 48(r7)
; CHECK-BE-NEXT: stxv vs2, 32(r7)
; CHECK-BE-NEXT: blr
;
; CHECK-LE-WACC-LABEL: test2:
; CHECK-LE-WACC: # %bb.0: # %entry
; CHECK-LE-WACC-NEXT: pmxvi16ger2 wacc0, v2, v2, 0, 0, 0
; CHECK-LE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-LE-WACC-NEXT: stxv v4, 48(r7)
; CHECK-LE-WACC-NEXT: stxv v5, 32(r7)
; CHECK-LE-WACC-NEXT: stxv v2, 16(r7)
; CHECK-LE-WACC-NEXT: stxv v3, 0(r7)
; CHECK-LE-WACC-NEXT: blr
;
; CHECK-BE-WACC-LABEL: test2:
; CHECK-BE-WACC: # %bb.0: # %entry
; CHECK-BE-WACC-NEXT: pmxvi16ger2 wacc0, v2, v2, 0, 0, 0
; CHECK-BE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-BE-WACC-NEXT: stxv v5, 48(r7)
; CHECK-BE-WACC-NEXT: stxv v4, 32(r7)
; CHECK-BE-WACC-NEXT: stxv v3, 16(r7)
; CHECK-BE-WACC-NEXT: stxv v2, 0(r7)
; CHECK-BE-WACC-NEXT: blr
entry:
%0 = tail call <512 x i1> @llvm.ppc.mma.pmxvi16ger2(<16 x i8> %vc, <16 x i8> %vc, i32 0, i32 0, i32 0)
store <512 x i1> %0, ptr %resp, align 64
ret void
}
; Function Attrs: nounwind readnone
declare <512 x i1> @llvm.ppc.mma.pmxvi16ger2(<16 x i8>, <16 x i8>, i32, i32, i32)
; Function Attrs: nofree nounwind
define dso_local void @test3(ptr nocapture readonly %vqp, ptr nocapture readnone %vpp, <16 x i8> %vc, ptr nocapture %resp) {
; CHECK-LABEL: test3:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv vs3, 0(r3)
; CHECK-NEXT: lxv vs2, 16(r3)
; CHECK-NEXT: lxv vs1, 32(r3)
; CHECK-NEXT: lxv vs0, 48(r3)
; CHECK-NEXT: xxmtacc acc0
; CHECK-NEXT: xvi8ger4spp acc0, v2, v2
; CHECK-NEXT: xxmfacc acc0
; CHECK-NEXT: stxv vs0, 48(r7)
; CHECK-NEXT: stxv vs1, 32(r7)
; CHECK-NEXT: stxv vs2, 16(r7)
; CHECK-NEXT: stxv vs3, 0(r7)
; CHECK-NEXT: blr
;
; CHECK-BE-LABEL: test3:
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: lxv vs3, 48(r3)
; CHECK-BE-NEXT: lxv vs2, 32(r3)
; CHECK-BE-NEXT: lxv vs1, 16(r3)
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: xxmtacc acc0
; CHECK-BE-NEXT: xvi8ger4spp acc0, v2, v2
; CHECK-BE-NEXT: xxmfacc acc0
; CHECK-BE-NEXT: stxv vs1, 16(r7)
; CHECK-BE-NEXT: stxv vs0, 0(r7)
; CHECK-BE-NEXT: stxv vs3, 48(r7)
; CHECK-BE-NEXT: stxv vs2, 32(r7)
; CHECK-BE-NEXT: blr
;
; CHECK-LE-WACC-LABEL: test3:
; CHECK-LE-WACC: # %bb.0: # %entry
; CHECK-LE-WACC-NEXT: lxv v5, 0(r3)
; CHECK-LE-WACC-NEXT: lxv v1, 32(r3)
; CHECK-LE-WACC-NEXT: lxv v4, 16(r3)
; CHECK-LE-WACC-NEXT: lxv v0, 48(r3)
; CHECK-LE-WACC-NEXT: dmxxinstdmr512 wacc0, vsp32, vsp36, 0
; CHECK-LE-WACC-NEXT: xvi8ger4spp wacc0, v2, v2
; CHECK-LE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-LE-WACC-NEXT: stxv v4, 48(r7)
; CHECK-LE-WACC-NEXT: stxv v5, 32(r7)
; CHECK-LE-WACC-NEXT: stxv v2, 16(r7)
; CHECK-LE-WACC-NEXT: stxv v3, 0(r7)
; CHECK-LE-WACC-NEXT: blr
;
; CHECK-BE-WACC-LABEL: test3:
; CHECK-BE-WACC: # %bb.0: # %entry
; CHECK-BE-WACC-NEXT: lxv v5, 48(r3)
; CHECK-BE-WACC-NEXT: lxv v1, 16(r3)
; CHECK-BE-WACC-NEXT: lxv v4, 32(r3)
; CHECK-BE-WACC-NEXT: lxv v0, 0(r3)
; CHECK-BE-WACC-NEXT: dmxxinstdmr512 wacc0, vsp32, vsp36, 0
; CHECK-BE-WACC-NEXT: xvi8ger4spp wacc0, v2, v2
; CHECK-BE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-BE-WACC-NEXT: stxv v5, 48(r7)
; CHECK-BE-WACC-NEXT: stxv v4, 32(r7)
; CHECK-BE-WACC-NEXT: stxv v3, 16(r7)
; CHECK-BE-WACC-NEXT: stxv v2, 0(r7)
; CHECK-BE-WACC-NEXT: blr
entry:
%0 = load <512 x i1>, ptr %vqp, align 64
%1 = tail call <512 x i1> @llvm.ppc.mma.xvi8ger4spp(<512 x i1> %0, <16 x i8> %vc, <16 x i8> %vc)
store <512 x i1> %1, ptr %resp, align 64
ret void
}
; Function Attrs: nounwind readnone
declare <512 x i1> @llvm.ppc.mma.xvi8ger4spp(<512 x i1>, <16 x i8>, <16 x i8>)
; Function Attrs: nofree nounwind
define dso_local void @test4(ptr nocapture readonly %vqp, ptr nocapture readnone %vpp, <16 x i8> %vc, ptr nocapture %resp) {
; CHECK-LABEL: test4:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv vs3, 0(r3)
; CHECK-NEXT: lxv vs2, 16(r3)
; CHECK-NEXT: lxv vs1, 32(r3)
; CHECK-NEXT: lxv vs0, 48(r3)
; CHECK-NEXT: xxmtacc acc0
; CHECK-NEXT: xvi16ger2pp acc0, v2, v2
; CHECK-NEXT: xxmfacc acc0
; CHECK-NEXT: stxv vs0, 48(r7)
; CHECK-NEXT: stxv vs1, 32(r7)
; CHECK-NEXT: stxv vs2, 16(r7)
; CHECK-NEXT: stxv vs3, 0(r7)
; CHECK-NEXT: blr
;
; CHECK-BE-LABEL: test4:
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: lxv vs3, 48(r3)
; CHECK-BE-NEXT: lxv vs2, 32(r3)
; CHECK-BE-NEXT: lxv vs1, 16(r3)
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: xxmtacc acc0
; CHECK-BE-NEXT: xvi16ger2pp acc0, v2, v2
; CHECK-BE-NEXT: xxmfacc acc0
; CHECK-BE-NEXT: stxv vs1, 16(r7)
; CHECK-BE-NEXT: stxv vs0, 0(r7)
; CHECK-BE-NEXT: stxv vs3, 48(r7)
; CHECK-BE-NEXT: stxv vs2, 32(r7)
; CHECK-BE-NEXT: blr
;
; CHECK-LE-WACC-LABEL: test4:
; CHECK-LE-WACC: # %bb.0: # %entry
; CHECK-LE-WACC-NEXT: lxv v5, 0(r3)
; CHECK-LE-WACC-NEXT: lxv v1, 32(r3)
; CHECK-LE-WACC-NEXT: lxv v4, 16(r3)
; CHECK-LE-WACC-NEXT: lxv v0, 48(r3)
; CHECK-LE-WACC-NEXT: dmxxinstdmr512 wacc0, vsp32, vsp36, 0
; CHECK-LE-WACC-NEXT: xvi16ger2pp wacc0, v2, v2
; CHECK-LE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-LE-WACC-NEXT: stxv v4, 48(r7)
; CHECK-LE-WACC-NEXT: stxv v5, 32(r7)
; CHECK-LE-WACC-NEXT: stxv v2, 16(r7)
; CHECK-LE-WACC-NEXT: stxv v3, 0(r7)
; CHECK-LE-WACC-NEXT: blr
;
; CHECK-BE-WACC-LABEL: test4:
; CHECK-BE-WACC: # %bb.0: # %entry
; CHECK-BE-WACC-NEXT: lxv v5, 48(r3)
; CHECK-BE-WACC-NEXT: lxv v1, 16(r3)
; CHECK-BE-WACC-NEXT: lxv v4, 32(r3)
; CHECK-BE-WACC-NEXT: lxv v0, 0(r3)
; CHECK-BE-WACC-NEXT: dmxxinstdmr512 wacc0, vsp32, vsp36, 0
; CHECK-BE-WACC-NEXT: xvi16ger2pp wacc0, v2, v2
; CHECK-BE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-BE-WACC-NEXT: stxv v5, 48(r7)
; CHECK-BE-WACC-NEXT: stxv v4, 32(r7)
; CHECK-BE-WACC-NEXT: stxv v3, 16(r7)
; CHECK-BE-WACC-NEXT: stxv v2, 0(r7)
; CHECK-BE-WACC-NEXT: blr
entry:
%0 = load <512 x i1>, ptr %vqp, align 64
%1 = tail call <512 x i1> @llvm.ppc.mma.xvi16ger2pp(<512 x i1> %0, <16 x i8> %vc, <16 x i8> %vc)
store <512 x i1> %1, ptr %resp, align 64
ret void
}
; Function Attrs: nounwind readnone
declare <512 x i1> @llvm.ppc.mma.xvi16ger2pp(<512 x i1>, <16 x i8>, <16 x i8>)
; Function Attrs: nofree nounwind
define dso_local void @test5(ptr nocapture readonly %vqp, ptr nocapture readnone %vpp, <16 x i8> %vc, ptr nocapture %resp) {
; CHECK-LABEL: test5:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv vs3, 0(r3)
; CHECK-NEXT: lxv vs2, 16(r3)
; CHECK-NEXT: lxv vs1, 32(r3)
; CHECK-NEXT: lxv vs0, 48(r3)
; CHECK-NEXT: xxmtacc acc0
; CHECK-NEXT: pmxvi8ger4spp acc0, v2, v2, 0, 0, 0
; CHECK-NEXT: xxmfacc acc0
; CHECK-NEXT: stxv vs0, 48(r7)
; CHECK-NEXT: stxv vs1, 32(r7)
; CHECK-NEXT: stxv vs2, 16(r7)
; CHECK-NEXT: stxv vs3, 0(r7)
; CHECK-NEXT: blr
;
; CHECK-BE-LABEL: test5:
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: lxv vs3, 48(r3)
; CHECK-BE-NEXT: lxv vs2, 32(r3)
; CHECK-BE-NEXT: lxv vs1, 16(r3)
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: xxmtacc acc0
; CHECK-BE-NEXT: pmxvi8ger4spp acc0, v2, v2, 0, 0, 0
; CHECK-BE-NEXT: xxmfacc acc0
; CHECK-BE-NEXT: stxv vs1, 16(r7)
; CHECK-BE-NEXT: stxv vs0, 0(r7)
; CHECK-BE-NEXT: stxv vs3, 48(r7)
; CHECK-BE-NEXT: stxv vs2, 32(r7)
; CHECK-BE-NEXT: blr
;
; CHECK-LE-WACC-LABEL: test5:
; CHECK-LE-WACC: # %bb.0: # %entry
; CHECK-LE-WACC-NEXT: lxv v5, 0(r3)
; CHECK-LE-WACC-NEXT: lxv v1, 32(r3)
; CHECK-LE-WACC-NEXT: lxv v4, 16(r3)
; CHECK-LE-WACC-NEXT: lxv v0, 48(r3)
; CHECK-LE-WACC-NEXT: dmxxinstdmr512 wacc0, vsp32, vsp36, 0
; CHECK-LE-WACC-NEXT: pmxvi8ger4spp wacc0, v2, v2, 0, 0, 0
; CHECK-LE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-LE-WACC-NEXT: stxv v4, 48(r7)
; CHECK-LE-WACC-NEXT: stxv v5, 32(r7)
; CHECK-LE-WACC-NEXT: stxv v2, 16(r7)
; CHECK-LE-WACC-NEXT: stxv v3, 0(r7)
; CHECK-LE-WACC-NEXT: blr
;
; CHECK-BE-WACC-LABEL: test5:
; CHECK-BE-WACC: # %bb.0: # %entry
; CHECK-BE-WACC-NEXT: lxv v5, 48(r3)
; CHECK-BE-WACC-NEXT: lxv v1, 16(r3)
; CHECK-BE-WACC-NEXT: lxv v4, 32(r3)
; CHECK-BE-WACC-NEXT: lxv v0, 0(r3)
; CHECK-BE-WACC-NEXT: dmxxinstdmr512 wacc0, vsp32, vsp36, 0
; CHECK-BE-WACC-NEXT: pmxvi8ger4spp wacc0, v2, v2, 0, 0, 0
; CHECK-BE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-BE-WACC-NEXT: stxv v5, 48(r7)
; CHECK-BE-WACC-NEXT: stxv v4, 32(r7)
; CHECK-BE-WACC-NEXT: stxv v3, 16(r7)
; CHECK-BE-WACC-NEXT: stxv v2, 0(r7)
; CHECK-BE-WACC-NEXT: blr
entry:
%0 = load <512 x i1>, ptr %vqp, align 64
%1 = tail call <512 x i1> @llvm.ppc.mma.pmxvi8ger4spp(<512 x i1> %0, <16 x i8> %vc, <16 x i8> %vc, i32 0, i32 0, i32 0)
store <512 x i1> %1, ptr %resp, align 64
ret void
}
; Function Attrs: nounwind readnone
declare <512 x i1> @llvm.ppc.mma.pmxvi8ger4spp(<512 x i1>, <16 x i8>, <16 x i8>, i32, i32, i32)
; Function Attrs: nofree nounwind
define dso_local void @test6(ptr nocapture readonly %vqp, ptr nocapture readnone %vpp, <16 x i8> %vc, ptr nocapture %resp) {
; CHECK-LABEL: test6:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lxv vs3, 0(r3)
; CHECK-NEXT: lxv vs2, 16(r3)
; CHECK-NEXT: lxv vs1, 32(r3)
; CHECK-NEXT: lxv vs0, 48(r3)
; CHECK-NEXT: xxmtacc acc0
; CHECK-NEXT: pmxvi16ger2pp acc0, v2, v2, 0, 0, 0
; CHECK-NEXT: xxmfacc acc0
; CHECK-NEXT: stxv vs0, 48(r7)
; CHECK-NEXT: stxv vs1, 32(r7)
; CHECK-NEXT: stxv vs2, 16(r7)
; CHECK-NEXT: stxv vs3, 0(r7)
; CHECK-NEXT: blr
;
; CHECK-BE-LABEL: test6:
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: lxv vs3, 48(r3)
; CHECK-BE-NEXT: lxv vs2, 32(r3)
; CHECK-BE-NEXT: lxv vs1, 16(r3)
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: xxmtacc acc0
; CHECK-BE-NEXT: pmxvi16ger2pp acc0, v2, v2, 0, 0, 0
; CHECK-BE-NEXT: xxmfacc acc0
; CHECK-BE-NEXT: stxv vs1, 16(r7)
; CHECK-BE-NEXT: stxv vs0, 0(r7)
; CHECK-BE-NEXT: stxv vs3, 48(r7)
; CHECK-BE-NEXT: stxv vs2, 32(r7)
; CHECK-BE-NEXT: blr
;
; CHECK-LE-WACC-LABEL: test6:
; CHECK-LE-WACC: # %bb.0: # %entry
; CHECK-LE-WACC-NEXT: lxv v5, 0(r3)
; CHECK-LE-WACC-NEXT: lxv v1, 32(r3)
; CHECK-LE-WACC-NEXT: lxv v4, 16(r3)
; CHECK-LE-WACC-NEXT: lxv v0, 48(r3)
; CHECK-LE-WACC-NEXT: dmxxinstdmr512 wacc0, vsp32, vsp36, 0
; CHECK-LE-WACC-NEXT: pmxvi16ger2pp wacc0, v2, v2, 0, 0, 0
; CHECK-LE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-LE-WACC-NEXT: stxv v4, 48(r7)
; CHECK-LE-WACC-NEXT: stxv v5, 32(r7)
; CHECK-LE-WACC-NEXT: stxv v2, 16(r7)
; CHECK-LE-WACC-NEXT: stxv v3, 0(r7)
; CHECK-LE-WACC-NEXT: blr
;
; CHECK-BE-WACC-LABEL: test6:
; CHECK-BE-WACC: # %bb.0: # %entry
; CHECK-BE-WACC-NEXT: lxv v5, 48(r3)
; CHECK-BE-WACC-NEXT: lxv v1, 16(r3)
; CHECK-BE-WACC-NEXT: lxv v4, 32(r3)
; CHECK-BE-WACC-NEXT: lxv v0, 0(r3)
; CHECK-BE-WACC-NEXT: dmxxinstdmr512 wacc0, vsp32, vsp36, 0
; CHECK-BE-WACC-NEXT: pmxvi16ger2pp wacc0, v2, v2, 0, 0, 0
; CHECK-BE-WACC-NEXT: dmxxextfdmr512 vsp34, vsp36, wacc0, 0
; CHECK-BE-WACC-NEXT: stxv v5, 48(r7)
; CHECK-BE-WACC-NEXT: stxv v4, 32(r7)
; CHECK-BE-WACC-NEXT: stxv v3, 16(r7)
; CHECK-BE-WACC-NEXT: stxv v2, 0(r7)
; CHECK-BE-WACC-NEXT: blr
entry:
%0 = load <512 x i1>, ptr %vqp, align 64
%1 = tail call <512 x i1> @llvm.ppc.mma.pmxvi16ger2pp(<512 x i1> %0, <16 x i8> %vc, <16 x i8> %vc, i32 0, i32 0, i32 0)
store <512 x i1> %1, ptr %resp, align 64
ret void
}
; Function Attrs: nounwind readnone
declare <512 x i1> @llvm.ppc.mma.pmxvi16ger2pp(<512 x i1>, <16 x i8>, <16 x i8>, i32, i32, i32)