; 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 ; Function Attrs: nofree nounwind writeonly define dso_local void @test1(i8* nocapture readnone %vqp, i8* nocapture readnone %vpp, <16 x i8> %vc, i8* 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 entry: %0 = tail call <512 x i1> @llvm.ppc.mma.xvi16ger2(<16 x i8> %vc, <16 x i8> %vc) %1 = bitcast i8* %resp to <512 x i1>* store <512 x i1> %0, <512 x i1>* %1, 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(i8* nocapture readnone %vqp, i8* nocapture readnone %vpp, <16 x i8> %vc, i8* 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 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) %1 = bitcast i8* %resp to <512 x i1>* store <512 x i1> %0, <512 x i1>* %1, 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(i8* nocapture readonly %vqp, i8* nocapture readnone %vpp, <16 x i8> %vc, i8* nocapture %resp) { ; CHECK-LABEL: test3: ; CHECK: # %bb.0: # %entry ; CHECK-NEXT: lxv vs1, 32(r3) ; CHECK-NEXT: lxv vs0, 48(r3) ; CHECK-NEXT: lxv vs3, 0(r3) ; CHECK-NEXT: lxv vs2, 16(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 vs1, 16(r3) ; CHECK-BE-NEXT: lxv vs0, 0(r3) ; CHECK-BE-NEXT: lxv vs3, 48(r3) ; CHECK-BE-NEXT: lxv vs2, 32(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 entry: %0 = bitcast i8* %vqp to <512 x i1>* %1 = load <512 x i1>, <512 x i1>* %0, align 64 %2 = tail call <512 x i1> @llvm.ppc.mma.xvi8ger4spp(<512 x i1> %1, <16 x i8> %vc, <16 x i8> %vc) %3 = bitcast i8* %resp to <512 x i1>* store <512 x i1> %2, <512 x i1>* %3, 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(i8* nocapture readonly %vqp, i8* nocapture readnone %vpp, <16 x i8> %vc, i8* nocapture %resp) { ; CHECK-LABEL: test4: ; CHECK: # %bb.0: # %entry ; CHECK-NEXT: lxv vs1, 32(r3) ; CHECK-NEXT: lxv vs0, 48(r3) ; CHECK-NEXT: lxv vs3, 0(r3) ; CHECK-NEXT: lxv vs2, 16(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 vs1, 16(r3) ; CHECK-BE-NEXT: lxv vs0, 0(r3) ; CHECK-BE-NEXT: lxv vs3, 48(r3) ; CHECK-BE-NEXT: lxv vs2, 32(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 entry: %0 = bitcast i8* %vqp to <512 x i1>* %1 = load <512 x i1>, <512 x i1>* %0, align 64 %2 = tail call <512 x i1> @llvm.ppc.mma.xvi16ger2pp(<512 x i1> %1, <16 x i8> %vc, <16 x i8> %vc) %3 = bitcast i8* %resp to <512 x i1>* store <512 x i1> %2, <512 x i1>* %3, 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(i8* nocapture readonly %vqp, i8* nocapture readnone %vpp, <16 x i8> %vc, i8* nocapture %resp) { ; CHECK-LABEL: test5: ; CHECK: # %bb.0: # %entry ; CHECK-NEXT: lxv vs1, 32(r3) ; CHECK-NEXT: lxv vs0, 48(r3) ; CHECK-NEXT: lxv vs3, 0(r3) ; CHECK-NEXT: lxv vs2, 16(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 vs1, 16(r3) ; CHECK-BE-NEXT: lxv vs0, 0(r3) ; CHECK-BE-NEXT: lxv vs3, 48(r3) ; CHECK-BE-NEXT: lxv vs2, 32(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 entry: %0 = bitcast i8* %vqp to <512 x i1>* %1 = load <512 x i1>, <512 x i1>* %0, align 64 %2 = tail call <512 x i1> @llvm.ppc.mma.pmxvi8ger4spp(<512 x i1> %1, <16 x i8> %vc, <16 x i8> %vc, i32 0, i32 0, i32 0) %3 = bitcast i8* %resp to <512 x i1>* store <512 x i1> %2, <512 x i1>* %3, 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(i8* nocapture readonly %vqp, i8* nocapture readnone %vpp, <16 x i8> %vc, i8* nocapture %resp) { ; CHECK-LABEL: test6: ; CHECK: # %bb.0: # %entry ; CHECK-NEXT: lxv vs1, 32(r3) ; CHECK-NEXT: lxv vs0, 48(r3) ; CHECK-NEXT: lxv vs3, 0(r3) ; CHECK-NEXT: lxv vs2, 16(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 vs1, 16(r3) ; CHECK-BE-NEXT: lxv vs0, 0(r3) ; CHECK-BE-NEXT: lxv vs3, 48(r3) ; CHECK-BE-NEXT: lxv vs2, 32(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 entry: %0 = bitcast i8* %vqp to <512 x i1>* %1 = load <512 x i1>, <512 x i1>* %0, align 64 %2 = tail call <512 x i1> @llvm.ppc.mma.pmxvi16ger2pp(<512 x i1> %1, <16 x i8> %vc, <16 x i8> %vc, i32 0, i32 0, i32 0) %3 = bitcast i8* %resp to <512 x i1>* store <512 x i1> %2, <512 x i1>* %3, 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)