forked from OSchip/llvm-project
334 lines
17 KiB
LLVM
334 lines
17 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-vsr-nums-as-vr -ppc-asm-full-reg-names < %s \
|
|
; RUN: | FileCheck %s
|
|
; RUN: llc -verify-machineinstrs -mtriple powerpc64le-unknown-linux-gnu \
|
|
; RUN: -mcpu=pwr10 -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names \
|
|
; RUN: -ppc-track-subreg-liveness < %s | FileCheck %s --check-prefix=TRACKLIVE
|
|
|
|
%0 = type <{ double }>
|
|
%1 = type <{ double }>
|
|
|
|
define void @acc_regalloc(i32* %arg, [0 x %0]* %arg1, [0 x %1]* %arg2) local_unnamed_addr {
|
|
; CHECK-LABEL: acc_regalloc:
|
|
; CHECK: # %bb.0: # %bb
|
|
; CHECK-NEXT: lwz r3, 0(r3)
|
|
; CHECK-NEXT: lxv v4, 0(0)
|
|
; CHECK-NEXT: xxlxor v0, v0, v0
|
|
; CHECK-NEXT: xxlxor v1, v1, v1
|
|
; CHECK-NEXT: stfd f14, -144(r1) # 8-byte Folded Spill
|
|
; CHECK-NEXT: stfd f15, -136(r1) # 8-byte Folded Spill
|
|
; CHECK-NEXT: xxlxor v2, v2, v2
|
|
; CHECK-NEXT: li r6, 1
|
|
; CHECK-NEXT: li r4, 16
|
|
; CHECK-NEXT: extswsli r3, r3, 3
|
|
; CHECK-NEXT: xvmaddadp v1, v4, v1
|
|
; CHECK-NEXT: lxvdsx v5, 0, r3
|
|
; CHECK-NEXT: xvmaddadp v0, v5, v0
|
|
; CHECK-NEXT: .p2align 4
|
|
; CHECK-NEXT: .LBB0_1: # %bb9
|
|
; CHECK-NEXT: #
|
|
; CHECK-NEXT: addi r6, r6, 2
|
|
; CHECK-NEXT: lxv vs1, -64(r5)
|
|
; CHECK-NEXT: lxv vs2, -16(r5)
|
|
; CHECK-NEXT: lxv vs0, 16(0)
|
|
; CHECK-NEXT: vmr v9, v0
|
|
; CHECK-NEXT: xxlxor v10, v10, v10
|
|
; CHECK-NEXT: xxlxor v7, v7, v7
|
|
; CHECK-NEXT: mulld r6, r6, r3
|
|
; CHECK-NEXT: xvmaddadp v9, vs1, v2
|
|
; CHECK-NEXT: xxlxor v8, v8, v8
|
|
; CHECK-NEXT: xvmaddadp v10, vs2, v10
|
|
; CHECK-NEXT: xvmaddadp v7, vs0, v5
|
|
; CHECK-NEXT: xvmuldp v6, vs0, v2
|
|
; CHECK-NEXT: xvmaddadp v7, v2, v2
|
|
; CHECK-NEXT: xvmaddadp v6, v2, v2
|
|
; CHECK-NEXT: lxvdsx v14, r6, r4
|
|
; CHECK-NEXT: xvmaddadp v8, vs1, v8
|
|
; CHECK-NEXT: li r6, 0
|
|
; CHECK-NEXT: xvmuldp v11, vs2, v14
|
|
; CHECK-NEXT: xvmuldp v3, vs1, v14
|
|
; CHECK-NEXT: xvmuldp vs5, v14, v2
|
|
; CHECK-NEXT: xvmuldp v13, v4, v14
|
|
; CHECK-NEXT: vmr v12, v2
|
|
; CHECK-NEXT: xxlor vs14, v10, v10
|
|
; CHECK-NEXT: xxlor vs0, v2, v2
|
|
; CHECK-NEXT: xxlor vs4, v2, v2
|
|
; CHECK-NEXT: # kill: def $vsrp2 killed $vsrp2 def $uacc1
|
|
; CHECK-NEXT: xxlor vs6, v6, v6
|
|
; CHECK-NEXT: xxlor vs7, v7, v7
|
|
; CHECK-NEXT: xxlor vs8, v12, v12
|
|
; CHECK-NEXT: xxlor vs9, v13, v13
|
|
; CHECK-NEXT: vmr v12, v1
|
|
; CHECK-NEXT: xxlor vs15, v11, v11
|
|
; CHECK-NEXT: vmr v10, v2
|
|
; CHECK-NEXT: xxlor vs1, v3, v3
|
|
; CHECK-NEXT: xxlor vs2, v8, v8
|
|
; CHECK-NEXT: xxlor vs3, v9, v9
|
|
; CHECK-NEXT: xxlor vs10, v12, v12
|
|
; CHECK-NEXT: xxlor vs11, v13, v13
|
|
; CHECK-NEXT: xxmtacc acc1
|
|
; CHECK-NEXT: xxlor vs12, v10, v10
|
|
; CHECK-NEXT: xxlor vs13, v11, v11
|
|
; CHECK-NEXT: xxmtacc acc0
|
|
; CHECK-NEXT: xxmtacc acc2
|
|
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; CHECK-NEXT: xxmtacc acc3
|
|
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; CHECK-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; CHECK-NEXT: xxmfacc acc0
|
|
; CHECK-NEXT: xxmfacc acc1
|
|
; CHECK-NEXT: xxmfacc acc2
|
|
; CHECK-NEXT: xxmfacc acc3
|
|
; CHECK-NEXT: stxv vs1, 0(r3)
|
|
; CHECK-NEXT: stxv vs9, 32(r3)
|
|
; CHECK-NEXT: stxv vs4, 16(0)
|
|
; CHECK-NEXT: stxv vs12, 48(0)
|
|
; CHECK-NEXT: b .LBB0_1
|
|
;
|
|
; TRACKLIVE-LABEL: acc_regalloc:
|
|
; TRACKLIVE: # %bb.0: # %bb
|
|
; TRACKLIVE-NEXT: lwz r3, 0(r3)
|
|
; TRACKLIVE-NEXT: lxv v4, 0(0)
|
|
; TRACKLIVE-NEXT: xxlxor v0, v0, v0
|
|
; TRACKLIVE-NEXT: xxlxor v1, v1, v1
|
|
; TRACKLIVE-NEXT: stfd f14, -144(r1) # 8-byte Folded Spill
|
|
; TRACKLIVE-NEXT: stfd f15, -136(r1) # 8-byte Folded Spill
|
|
; TRACKLIVE-NEXT: xxlxor v2, v2, v2
|
|
; TRACKLIVE-NEXT: li r6, 1
|
|
; TRACKLIVE-NEXT: li r4, 16
|
|
; TRACKLIVE-NEXT: extswsli r3, r3, 3
|
|
; TRACKLIVE-NEXT: xvmaddadp v1, v4, v1
|
|
; TRACKLIVE-NEXT: lxvdsx v5, 0, r3
|
|
; TRACKLIVE-NEXT: xvmaddadp v0, v5, v0
|
|
; TRACKLIVE-NEXT: .p2align 4
|
|
; TRACKLIVE-NEXT: .LBB0_1: # %bb9
|
|
; TRACKLIVE-NEXT: #
|
|
; TRACKLIVE-NEXT: addi r6, r6, 2
|
|
; TRACKLIVE-NEXT: lxv vs0, 16(0)
|
|
; TRACKLIVE-NEXT: xxlxor vs7, vs7, vs7
|
|
; TRACKLIVE-NEXT: lxv vs1, -64(r5)
|
|
; TRACKLIVE-NEXT: lxv vs4, -16(r5)
|
|
; TRACKLIVE-NEXT: xxlxor vs12, vs12, vs12
|
|
; TRACKLIVE-NEXT: xxlor vs3, v0, v0
|
|
; TRACKLIVE-NEXT: xxlxor vs2, vs2, vs2
|
|
; TRACKLIVE-NEXT: mulld r6, r6, r3
|
|
; TRACKLIVE-NEXT: xxlor vs10, v2, v2
|
|
; TRACKLIVE-NEXT: xxlor vs8, vs10, vs10
|
|
; TRACKLIVE-NEXT: xxlor vs10, v1, v1
|
|
; TRACKLIVE-NEXT: xvmaddadp vs7, vs0, v5
|
|
; TRACKLIVE-NEXT: xvmuldp vs6, vs0, v2
|
|
; TRACKLIVE-NEXT: xvmaddadp vs12, vs4, vs12
|
|
; TRACKLIVE-NEXT: xvmaddadp vs3, vs1, v2
|
|
; TRACKLIVE-NEXT: xvmaddadp vs2, vs1, vs2
|
|
; TRACKLIVE-NEXT: xxlor vs0, v2, v2
|
|
; TRACKLIVE-NEXT: lxvdsx v6, r6, r4
|
|
; TRACKLIVE-NEXT: li r6, 0
|
|
; TRACKLIVE-NEXT: xvmaddadp vs7, v2, v2
|
|
; TRACKLIVE-NEXT: xvmaddadp vs6, v2, v2
|
|
; TRACKLIVE-NEXT: xxlor vs14, vs12, vs12
|
|
; TRACKLIVE-NEXT: xxlor vs12, v2, v2
|
|
; TRACKLIVE-NEXT: xvmuldp v3, vs1, v6
|
|
; TRACKLIVE-NEXT: xvmuldp vs11, v4, v6
|
|
; TRACKLIVE-NEXT: xvmuldp vs13, vs4, v6
|
|
; TRACKLIVE-NEXT: xvmuldp vs5, v6, v2
|
|
; TRACKLIVE-NEXT: xxlor vs4, v2, v2
|
|
; TRACKLIVE-NEXT: xxlor vs1, v3, v3
|
|
; TRACKLIVE-NEXT: xxlor vs9, vs11, vs11
|
|
; TRACKLIVE-NEXT: xxlor vs15, vs13, vs13
|
|
; TRACKLIVE-NEXT: xxmtacc acc1
|
|
; TRACKLIVE-NEXT: xxmtacc acc0
|
|
; TRACKLIVE-NEXT: xxmtacc acc2
|
|
; TRACKLIVE-NEXT: xxmtacc acc3
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc0, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc1, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc2, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xvf64gerpp acc3, vsp34, vs0
|
|
; TRACKLIVE-NEXT: xxmfacc acc0
|
|
; TRACKLIVE-NEXT: xxmfacc acc1
|
|
; TRACKLIVE-NEXT: xxmfacc acc2
|
|
; TRACKLIVE-NEXT: xxmfacc acc3
|
|
; TRACKLIVE-NEXT: stxv vs1, 0(r3)
|
|
; TRACKLIVE-NEXT: stxv vs9, 32(r3)
|
|
; TRACKLIVE-NEXT: stxv vs4, 16(0)
|
|
; TRACKLIVE-NEXT: stxv vs12, 48(0)
|
|
; TRACKLIVE-NEXT: b .LBB0_1
|
|
bb:
|
|
%i = load i32, i32* %arg, align 4
|
|
%i3 = sext i32 %i to i64
|
|
%i4 = shl nsw i64 %i3, 3
|
|
%i5 = bitcast [0 x %0]* %arg1 to i8*
|
|
%i6 = getelementptr i8, i8* %i5, i64 undef
|
|
%i7 = getelementptr [0 x %1], [0 x %1]* %arg2, i64 0, i64 -8
|
|
%i8 = getelementptr i8, i8* %i6, i64 undef
|
|
br label %bb9
|
|
|
|
bb9: ; preds = %bb95, %bb
|
|
%i10 = phi i64 [ 1, %bb ], [ 0, %bb95 ]
|
|
%i11 = getelementptr %1, %1* null, i64 2
|
|
%i12 = bitcast %1* %i11 to <2 x double>*
|
|
%i13 = load <2 x double>, <2 x double>* %i12, align 1
|
|
%i14 = add nuw nsw i64 %i10, 2
|
|
%i15 = getelementptr inbounds %1, %1* %i7, i64 undef
|
|
%i16 = bitcast %1* %i15 to <2 x double>*
|
|
%i17 = load <2 x double>, <2 x double>* %i16, align 1
|
|
%i18 = load <2 x double>, <2 x double>* null, align 1
|
|
%i19 = getelementptr %1, %1* %i15, i64 6
|
|
%i20 = bitcast %1* %i19 to <2 x double>*
|
|
%i21 = load <2 x double>, <2 x double>* %i20, align 1
|
|
%i22 = load i64, i64* undef, align 8
|
|
%i23 = insertelement <2 x i64> poison, i64 %i22, i32 0
|
|
%i24 = bitcast <2 x i64> %i23 to <2 x double>
|
|
%i25 = shufflevector <2 x double> %i24, <2 x double> undef, <2 x i32> zeroinitializer
|
|
%i26 = mul i64 %i14, %i4
|
|
%i27 = getelementptr i8, i8* null, i64 %i26
|
|
%i28 = getelementptr inbounds i8, i8* %i27, i64 0
|
|
%i29 = getelementptr i8, i8* %i28, i64 16
|
|
%i30 = bitcast i8* %i29 to i64*
|
|
%i31 = load i64, i64* %i30, align 8
|
|
%i32 = insertelement <2 x i64> poison, i64 %i31, i32 0
|
|
%i33 = bitcast <2 x i64> %i32 to <2 x double>
|
|
%i34 = shufflevector <2 x double> %i33, <2 x double> undef, <2 x i32> zeroinitializer
|
|
%i35 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> zeroinitializer, <2 x double> %i25, <2 x double> zeroinitializer)
|
|
%i36 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> %i13, <2 x double> %i25, <2 x double> zeroinitializer)
|
|
%i37 = fmul contract <2 x double> %i13, zeroinitializer
|
|
%i38 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> %i17, <2 x double> zeroinitializer, <2 x double> %i35)
|
|
%i39 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> zeroinitializer, <2 x double> zeroinitializer, <2 x double> %i36)
|
|
%i40 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> %i17, <2 x double> zeroinitializer, <2 x double> zeroinitializer)
|
|
%i41 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> zeroinitializer, <2 x double> zeroinitializer, <2 x double> %i37)
|
|
%i42 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> %i18, <2 x double> zeroinitializer, <2 x double> zeroinitializer)
|
|
%i43 = tail call contract <2 x double> @llvm.fma.v2f64(<2 x double> %i21, <2 x double> zeroinitializer, <2 x double> zeroinitializer)
|
|
%i44 = fmul contract <2 x double> %i17, %i34
|
|
%i45 = fmul contract <2 x double> zeroinitializer, %i34
|
|
%i46 = fmul contract <2 x double> %i18, %i34
|
|
%i47 = fmul contract <2 x double> %i21, %i34
|
|
%i48 = bitcast <2 x double> %i44 to <16 x i8>
|
|
%i49 = bitcast <2 x double> %i40 to <16 x i8>
|
|
%i50 = bitcast <2 x double> %i38 to <16 x i8>
|
|
%i51 = tail call <512 x i1> @llvm.ppc.mma.assemble.acc(<16 x i8> zeroinitializer, <16 x i8> %i48, <16 x i8> %i49, <16 x i8> %i50)
|
|
%i52 = bitcast <2 x double> %i45 to <16 x i8>
|
|
%i53 = bitcast <2 x double> %i41 to <16 x i8>
|
|
%i54 = bitcast <2 x double> %i39 to <16 x i8>
|
|
%i55 = tail call <512 x i1> @llvm.ppc.mma.assemble.acc(<16 x i8> zeroinitializer, <16 x i8> %i52, <16 x i8> %i53, <16 x i8> %i54)
|
|
%i56 = bitcast <2 x double> %i46 to <16 x i8>
|
|
%i57 = bitcast <2 x double> %i42 to <16 x i8>
|
|
%i58 = tail call <512 x i1> @llvm.ppc.mma.assemble.acc(<16 x i8> zeroinitializer, <16 x i8> %i56, <16 x i8> %i57, <16 x i8> %i56)
|
|
%i59 = bitcast <2 x double> %i47 to <16 x i8>
|
|
%i60 = bitcast <2 x double> %i43 to <16 x i8>
|
|
%i61 = tail call <512 x i1> @llvm.ppc.mma.assemble.acc(<16 x i8> zeroinitializer, <16 x i8> %i59, <16 x i8> %i60, <16 x i8> %i59)
|
|
%i62 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i51, <256 x i1> undef, <16 x i8> undef)
|
|
%i63 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i55, <256 x i1> undef, <16 x i8> undef)
|
|
%i64 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i58, <256 x i1> undef, <16 x i8> undef)
|
|
%i65 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i61, <256 x i1> undef, <16 x i8> undef)
|
|
%i66 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i62, <256 x i1> undef, <16 x i8> undef)
|
|
%i67 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i63, <256 x i1> undef, <16 x i8> undef)
|
|
%i68 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i64, <256 x i1> undef, <16 x i8> undef)
|
|
%i69 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i65, <256 x i1> undef, <16 x i8> undef)
|
|
%i70 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i66, <256 x i1> undef, <16 x i8> undef)
|
|
%i71 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i67, <256 x i1> undef, <16 x i8> undef)
|
|
%i72 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i68, <256 x i1> undef, <16 x i8> undef)
|
|
%i73 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i69, <256 x i1> undef, <16 x i8> undef)
|
|
%i74 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i70, <256 x i1> undef, <16 x i8> undef)
|
|
%i75 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i71, <256 x i1> undef, <16 x i8> undef)
|
|
%i76 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i72, <256 x i1> undef, <16 x i8> undef)
|
|
%i77 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i73, <256 x i1> undef, <16 x i8> undef)
|
|
%i78 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i74, <256 x i1> undef, <16 x i8> undef)
|
|
%i79 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i75, <256 x i1> undef, <16 x i8> undef)
|
|
%i80 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i76, <256 x i1> undef, <16 x i8> undef)
|
|
%i81 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i77, <256 x i1> undef, <16 x i8> undef)
|
|
br label %bb82
|
|
|
|
bb82: ; preds = %bb82, %bb9
|
|
%i83 = phi <512 x i1> [ %i94, %bb82 ], [ %i81, %bb9 ]
|
|
%i84 = phi <512 x i1> [ %i93, %bb82 ], [ %i80, %bb9 ]
|
|
%i85 = phi <512 x i1> [ %i92, %bb82 ], [ %i79, %bb9 ]
|
|
%i86 = phi <512 x i1> [ %i91, %bb82 ], [ %i78, %bb9 ]
|
|
%i87 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i86, <256 x i1> undef, <16 x i8> undef)
|
|
%i88 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i85, <256 x i1> undef, <16 x i8> undef)
|
|
%i89 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i84, <256 x i1> undef, <16 x i8> undef)
|
|
%i90 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i83, <256 x i1> undef, <16 x i8> undef)
|
|
%i91 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i87, <256 x i1> undef, <16 x i8> undef)
|
|
%i92 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i88, <256 x i1> undef, <16 x i8> undef)
|
|
%i93 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i89, <256 x i1> undef, <16 x i8> undef)
|
|
%i94 = tail call <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1> %i90, <256 x i1> undef, <16 x i8> undef)
|
|
br i1 undef, label %bb95, label %bb82
|
|
|
|
bb95: ; preds = %bb82
|
|
%i96 = tail call { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.ppc.mma.disassemble.acc(<512 x i1> %i91)
|
|
%i97 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %i96, 2
|
|
%i98 = tail call { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.ppc.mma.disassemble.acc(<512 x i1> %i92)
|
|
%i99 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %i98, 3
|
|
%i100 = tail call { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.ppc.mma.disassemble.acc(<512 x i1> %i93)
|
|
%i101 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %i100, 2
|
|
%i102 = tail call { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.ppc.mma.disassemble.acc(<512 x i1> %i94)
|
|
%i103 = extractvalue { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } %i102, 3
|
|
%i104 = getelementptr inbounds i8, i8* %i8, i64 undef
|
|
%i105 = bitcast i8* %i104 to <16 x i8>*
|
|
store <16 x i8> %i97, <16 x i8>* %i105, align 1
|
|
%i106 = getelementptr i8, i8* %i104, i64 32
|
|
%i107 = bitcast i8* %i106 to <16 x i8>*
|
|
store <16 x i8> %i101, <16 x i8>* %i107, align 1
|
|
%i108 = getelementptr i8, i8* null, i64 16
|
|
%i109 = bitcast i8* %i108 to <16 x i8>*
|
|
store <16 x i8> %i99, <16 x i8>* %i109, align 1
|
|
%i110 = getelementptr i8, i8* null, i64 48
|
|
%i111 = bitcast i8* %i110 to <16 x i8>*
|
|
store <16 x i8> %i103, <16 x i8>* %i111, align 1
|
|
br label %bb9
|
|
}
|
|
|
|
declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>)
|
|
declare <512 x i1> @llvm.ppc.mma.assemble.acc(<16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>)
|
|
declare <512 x i1> @llvm.ppc.mma.xvf64gerpp(<512 x i1>, <256 x i1>, <16 x i8>)
|
|
declare { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> } @llvm.ppc.mma.disassemble.acc(<512 x i1>)
|
|
|