forked from OSchip/llvm-project
Revert r373172 "[X86] Add custom isel logic to match VPTERNLOG from 2 logic ops."
This seems to be causing some performance regresions that I'm trying to investigate. One thing that stands out is that this transform can increase the live range of the operands of the earlier logic op. This can be bad for register allocation. If there are two logic op inputs we should really combine the one that is closest, but SelectionDAG doesn't have a good way to do that. Maybe we need to do this as a basic block transform in Machine IR. llvm-svn: 373401
This commit is contained in:
Craig Topper
parent
5269091dc7
commit
0da163a2cf
|
|
@ -514,7 +514,6 @@ namespace {
|
|||
bool tryShiftAmountMod(SDNode *N);
|
||||
bool combineIncDecVector(SDNode *Node);
|
||||
bool tryShrinkShlLogicImm(SDNode *N);
|
||||
bool tryVPTERNLOG(SDNode *N);
|
||||
bool tryVPTESTM(SDNode *Root, SDValue Setcc, SDValue Mask);
|
||||
bool tryMatchBitSelect(SDNode *N);
|
||||
|
||||
|
|
@ -3833,82 +3832,6 @@ bool X86DAGToDAGISel::tryShrinkShlLogicImm(SDNode *N) {
|
|||
return true;
|
||||
}
|
||||
|
||||
// Try to match two logic ops to a VPTERNLOG.
|
||||
// FIXME: Handle inverted inputs?
|
||||
// FIXME: Handle more complex patterns that use an operand more than once?
|
||||
// FIXME: Support X86ISD::ANDNP
|
||||
bool X86DAGToDAGISel::tryVPTERNLOG(SDNode *N) {
|
||||
MVT NVT = N->getSimpleValueType(0);
|
||||
|
||||
// Make sure we support VPTERNLOG.
|
||||
if (!NVT.isVector() || !Subtarget->hasAVX512() ||
|
||||
NVT.getVectorElementType() == MVT::i1)
|
||||
return false;
|
||||
|
||||
// We need VLX for 128/256-bit.
|
||||
if (!(Subtarget->hasVLX() || NVT.is512BitVector()))
|
||||
return false;
|
||||
|
||||
unsigned Opc1 = N->getOpcode();
|
||||
SDValue N0 = N->getOperand(0);
|
||||
SDValue N1 = N->getOperand(1);
|
||||
|
||||
auto isLogicOp = [](unsigned Opc) {
|
||||
return Opc == ISD::AND || Opc == ISD::OR || Opc == ISD::XOR;
|
||||
};
|
||||
|
||||
SDValue A, B, C;
|
||||
unsigned Opc2;
|
||||
if (isLogicOp(N1.getOpcode()) && N1.hasOneUse()) {
|
||||
Opc2 = N1.getOpcode();
|
||||
A = N0;
|
||||
B = N1.getOperand(0);
|
||||
C = N1.getOperand(1);
|
||||
} else if (isLogicOp(N0.getOpcode()) && N0.hasOneUse()) {
|
||||
Opc2 = N0.getOpcode();
|
||||
A = N1;
|
||||
B = N0.getOperand(0);
|
||||
C = N0.getOperand(1);
|
||||
} else
|
||||
return false;
|
||||
|
||||
uint64_t Imm;
|
||||
switch (Opc1) {
|
||||
default: llvm_unreachable("Unexpected opcode!");
|
||||
case ISD::AND:
|
||||
switch (Opc2) {
|
||||
default: llvm_unreachable("Unexpected opcode!");
|
||||
case ISD::AND: Imm = 0x80; break;
|
||||
case ISD::OR: Imm = 0xe0; break;
|
||||
case ISD::XOR: Imm = 0x60; break;
|
||||
}
|
||||
break;
|
||||
case ISD::OR:
|
||||
switch (Opc2) {
|
||||
default: llvm_unreachable("Unexpected opcode!");
|
||||
case ISD::AND: Imm = 0xf8; break;
|
||||
case ISD::OR: Imm = 0xfe; break;
|
||||
case ISD::XOR: Imm = 0xf6; break;
|
||||
}
|
||||
break;
|
||||
case ISD::XOR:
|
||||
switch (Opc2) {
|
||||
default: llvm_unreachable("Unexpected opcode!");
|
||||
case ISD::AND: Imm = 0x78; break;
|
||||
case ISD::OR: Imm = 0x1e; break;
|
||||
case ISD::XOR: Imm = 0x96; break;
|
||||
}
|
||||
break;
|
||||
}
|
||||
|
||||
SDLoc DL(N);
|
||||
SDValue New = CurDAG->getNode(X86ISD::VPTERNLOG, DL, NVT, A, B, C,
|
||||
CurDAG->getTargetConstant(Imm, DL, MVT::i8));
|
||||
ReplaceNode(N, New.getNode());
|
||||
SelectCode(New.getNode());
|
||||
return true;
|
||||
}
|
||||
|
||||
/// Convert vector increment or decrement to sub/add with an all-ones constant:
|
||||
/// add X, <1, 1...> --> sub X, <-1, -1...>
|
||||
/// sub X, <1, 1...> --> add X, <-1, -1...>
|
||||
|
|
@ -4580,10 +4503,9 @@ void X86DAGToDAGISel::Select(SDNode *Node) {
|
|||
case ISD::XOR:
|
||||
if (tryShrinkShlLogicImm(Node))
|
||||
return;
|
||||
|
||||
if (Opcode == ISD::OR && tryMatchBitSelect(Node))
|
||||
return;
|
||||
if (tryVPTERNLOG(Node))
|
||||
return;
|
||||
|
||||
LLVM_FALLTHROUGH;
|
||||
case ISD::ADD:
|
||||
|
|
|
|||
|
|
@ -331,8 +331,8 @@ define <4 x float> @ulto4f32(<4 x i64> %a) {
|
|||
define <8 x double> @ulto8f64(<8 x i64> %a) {
|
||||
; NODQ-LABEL: ulto8f64:
|
||||
; NODQ: # %bb.0:
|
||||
; NODQ-NEXT: vpbroadcastq {{.*#+}} zmm1 = [4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200]
|
||||
; NODQ-NEXT: vpternlogq $248, {{.*}}(%rip){1to8}, %zmm0, %zmm1
|
||||
; NODQ-NEXT: vpandq {{.*}}(%rip){1to8}, %zmm0, %zmm1
|
||||
; NODQ-NEXT: vporq {{.*}}(%rip){1to8}, %zmm1, %zmm1
|
||||
; NODQ-NEXT: vpsrlq $32, %zmm0, %zmm0
|
||||
; NODQ-NEXT: vporq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; NODQ-NEXT: vsubpd {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
|
|
@ -356,20 +356,21 @@ define <16 x double> @ulto16f64(<16 x i64> %a) {
|
|||
; NODQ-LABEL: ulto16f64:
|
||||
; NODQ: # %bb.0:
|
||||
; NODQ-NEXT: vpbroadcastq {{.*#+}} zmm2 = [4294967295,4294967295,4294967295,4294967295,4294967295,4294967295,4294967295,4294967295]
|
||||
; NODQ-NEXT: vpbroadcastq {{.*#+}} zmm3 = [4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200]
|
||||
; NODQ-NEXT: vmovdqa64 %zmm3, %zmm4
|
||||
; NODQ-NEXT: vpternlogq $248, %zmm2, %zmm0, %zmm4
|
||||
; NODQ-NEXT: vpandq %zmm2, %zmm0, %zmm3
|
||||
; NODQ-NEXT: vpbroadcastq {{.*#+}} zmm4 = [4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200]
|
||||
; NODQ-NEXT: vporq %zmm4, %zmm3, %zmm3
|
||||
; NODQ-NEXT: vpsrlq $32, %zmm0, %zmm0
|
||||
; NODQ-NEXT: vpbroadcastq {{.*#+}} zmm5 = [4985484787499139072,4985484787499139072,4985484787499139072,4985484787499139072,4985484787499139072,4985484787499139072,4985484787499139072,4985484787499139072]
|
||||
; NODQ-NEXT: vporq %zmm5, %zmm0, %zmm0
|
||||
; NODQ-NEXT: vbroadcastsd {{.*#+}} zmm6 = [1.9342813118337666E+25,1.9342813118337666E+25,1.9342813118337666E+25,1.9342813118337666E+25,1.9342813118337666E+25,1.9342813118337666E+25,1.9342813118337666E+25,1.9342813118337666E+25]
|
||||
; NODQ-NEXT: vsubpd %zmm6, %zmm0, %zmm0
|
||||
; NODQ-NEXT: vaddpd %zmm0, %zmm4, %zmm0
|
||||
; NODQ-NEXT: vpternlogq $248, %zmm2, %zmm1, %zmm3
|
||||
; NODQ-NEXT: vaddpd %zmm0, %zmm3, %zmm0
|
||||
; NODQ-NEXT: vpandq %zmm2, %zmm1, %zmm2
|
||||
; NODQ-NEXT: vporq %zmm4, %zmm2, %zmm2
|
||||
; NODQ-NEXT: vpsrlq $32, %zmm1, %zmm1
|
||||
; NODQ-NEXT: vporq %zmm5, %zmm1, %zmm1
|
||||
; NODQ-NEXT: vsubpd %zmm6, %zmm1, %zmm1
|
||||
; NODQ-NEXT: vaddpd %zmm1, %zmm3, %zmm1
|
||||
; NODQ-NEXT: vaddpd %zmm1, %zmm2, %zmm1
|
||||
; NODQ-NEXT: retq
|
||||
;
|
||||
; VLDQ-LABEL: ulto16f64:
|
||||
|
|
|
|||
|
|
@ -7,21 +7,21 @@ define <16 x i8> @test_vgf2p8affineinvqb_128(<16 x i8> %src1, <16 x i8> %src2, <
|
|||
; X86-LABEL: test_vgf2p8affineinvqb_128:
|
||||
; X86: # %bb.0:
|
||||
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %xmm1, %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xf9,0xcf,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %xmm1, %xmm0, %xmm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0x89,0xcf,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xf9,0xcf,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %xmm1, %xmm0, %xmm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0x89,0xcf,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0xcf,0xd1,0x03]
|
||||
; X86-NEXT: vpternlogq $150, %xmm2, %xmm4, %xmm3 # encoding: [0x62,0xf3,0xdd,0x08,0x25,0xda,0x96]
|
||||
; X86-NEXT: vmovdqa %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc3]
|
||||
; X86-NEXT: vpxor %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xef,0xc3]
|
||||
; X86-NEXT: vpxor %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xef,0xc0]
|
||||
; X86-NEXT: retl # encoding: [0xc3]
|
||||
;
|
||||
; X64-LABEL: test_vgf2p8affineinvqb_128:
|
||||
; X64: # %bb.0:
|
||||
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %xmm1, %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xf9,0xcf,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %xmm1, %xmm0, %xmm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0x89,0xcf,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xf9,0xcf,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %xmm1, %xmm0, %xmm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0x89,0xcf,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0xcf,0xd1,0x03]
|
||||
; X64-NEXT: vpternlogq $150, %xmm2, %xmm4, %xmm3 # encoding: [0x62,0xf3,0xdd,0x08,0x25,0xda,0x96]
|
||||
; X64-NEXT: vmovdqa %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc3]
|
||||
; X64-NEXT: vpxor %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xef,0xc3]
|
||||
; X64-NEXT: vpxor %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xef,0xc0]
|
||||
; X64-NEXT: retq # encoding: [0xc3]
|
||||
%1 = bitcast i16 %mask to <16 x i1>
|
||||
%2 = call <16 x i8> @llvm.x86.vgf2p8affineinvqb.128(<16 x i8> %src1, <16 x i8> %src2, i8 3)
|
||||
|
|
@ -37,21 +37,21 @@ define <32 x i8> @test_vgf2p8affineinvqb_256(<32 x i8> %src1, <32 x i8> %src2, <
|
|||
; X86-LABEL: test_vgf2p8affineinvqb_256:
|
||||
; X86: # %bb.0:
|
||||
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %ymm1, %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xfd,0xcf,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %ymm1, %ymm0, %ymm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xa9,0xcf,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xfd,0xcf,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %ymm1, %ymm0, %ymm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xa9,0xcf,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0xcf,0xd1,0x03]
|
||||
; X86-NEXT: vpternlogq $150, %ymm2, %ymm4, %ymm3 # encoding: [0x62,0xf3,0xdd,0x28,0x25,0xda,0x96]
|
||||
; X86-NEXT: vmovdqa %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc3]
|
||||
; X86-NEXT: vpxor %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xef,0xc3]
|
||||
; X86-NEXT: vpxor %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xef,0xc0]
|
||||
; X86-NEXT: retl # encoding: [0xc3]
|
||||
;
|
||||
; X64-LABEL: test_vgf2p8affineinvqb_256:
|
||||
; X64: # %bb.0:
|
||||
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %ymm1, %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xfd,0xcf,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %ymm1, %ymm0, %ymm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xa9,0xcf,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xfd,0xcf,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %ymm1, %ymm0, %ymm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xa9,0xcf,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0xcf,0xd1,0x03]
|
||||
; X64-NEXT: vpternlogq $150, %ymm2, %ymm4, %ymm3 # encoding: [0x62,0xf3,0xdd,0x28,0x25,0xda,0x96]
|
||||
; X64-NEXT: vmovdqa %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc3]
|
||||
; X64-NEXT: vpxor %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xef,0xc3]
|
||||
; X64-NEXT: vpxor %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xef,0xc0]
|
||||
; X64-NEXT: retq # encoding: [0xc3]
|
||||
%1 = bitcast i32 %mask to <32 x i1>
|
||||
%2 = call <32 x i8> @llvm.x86.vgf2p8affineinvqb.256(<32 x i8> %src1, <32 x i8> %src2, i8 3)
|
||||
|
|
@ -67,21 +67,21 @@ define <64 x i8> @test_vgf2p8affineinvqb_512(<64 x i8> %src1, <64 x i8> %src2, <
|
|||
; X86-LABEL: test_vgf2p8affineinvqb_512:
|
||||
; X86: # %bb.0:
|
||||
; X86-NEXT: kmovq {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf8,0x90,0x4c,0x24,0x04]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %zmm1, %zmm0, %zmm4 # encoding: [0x62,0xf3,0xfd,0x48,0xcf,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %zmm1, %zmm0, %zmm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xc9,0xcf,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %zmm1, %zmm0, %zmm3 # encoding: [0x62,0xf3,0xfd,0x48,0xcf,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %zmm1, %zmm0, %zmm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xc9,0xcf,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineinvqb $3, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0xcf,0xd1,0x03]
|
||||
; X86-NEXT: vpternlogq $150, %zmm2, %zmm4, %zmm3 # encoding: [0x62,0xf3,0xdd,0x48,0x25,0xda,0x96]
|
||||
; X86-NEXT: vmovdqa64 %zmm3, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc3]
|
||||
; X86-NEXT: vpxorq %zmm3, %zmm2, %zmm0 # encoding: [0x62,0xf1,0xed,0x48,0xef,0xc3]
|
||||
; X86-NEXT: vpxorq %zmm0, %zmm4, %zmm0 # encoding: [0x62,0xf1,0xdd,0x48,0xef,0xc0]
|
||||
; X86-NEXT: retl # encoding: [0xc3]
|
||||
;
|
||||
; X64-LABEL: test_vgf2p8affineinvqb_512:
|
||||
; X64: # %bb.0:
|
||||
; X64-NEXT: kmovq %rdi, %k1 # encoding: [0xc4,0xe1,0xfb,0x92,0xcf]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %zmm1, %zmm0, %zmm4 # encoding: [0x62,0xf3,0xfd,0x48,0xcf,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %zmm1, %zmm0, %zmm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xc9,0xcf,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %zmm1, %zmm0, %zmm3 # encoding: [0x62,0xf3,0xfd,0x48,0xcf,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %zmm1, %zmm0, %zmm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xc9,0xcf,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineinvqb $3, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0xcf,0xd1,0x03]
|
||||
; X64-NEXT: vpternlogq $150, %zmm2, %zmm4, %zmm3 # encoding: [0x62,0xf3,0xdd,0x48,0x25,0xda,0x96]
|
||||
; X64-NEXT: vmovdqa64 %zmm3, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc3]
|
||||
; X64-NEXT: vpxorq %zmm3, %zmm2, %zmm0 # encoding: [0x62,0xf1,0xed,0x48,0xef,0xc3]
|
||||
; X64-NEXT: vpxorq %zmm0, %zmm4, %zmm0 # encoding: [0x62,0xf1,0xdd,0x48,0xef,0xc0]
|
||||
; X64-NEXT: retq # encoding: [0xc3]
|
||||
%1 = bitcast i64 %mask to <64 x i1>
|
||||
%2 = call <64 x i8> @llvm.x86.vgf2p8affineinvqb.512(<64 x i8> %src1, <64 x i8> %src2, i8 3)
|
||||
|
|
@ -97,21 +97,21 @@ define <16 x i8> @test_vgf2p8affineqb_128(<16 x i8> %src1, <16 x i8> %src2, <16
|
|||
; X86-LABEL: test_vgf2p8affineqb_128:
|
||||
; X86: # %bb.0:
|
||||
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %xmm1, %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xf9,0xce,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %xmm1, %xmm0, %xmm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0x89,0xce,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xf9,0xce,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %xmm1, %xmm0, %xmm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0x89,0xce,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0xce,0xd1,0x03]
|
||||
; X86-NEXT: vpternlogq $150, %xmm2, %xmm4, %xmm3 # encoding: [0x62,0xf3,0xdd,0x08,0x25,0xda,0x96]
|
||||
; X86-NEXT: vmovdqa %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc3]
|
||||
; X86-NEXT: vpxor %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xef,0xc3]
|
||||
; X86-NEXT: vpxor %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xef,0xc0]
|
||||
; X86-NEXT: retl # encoding: [0xc3]
|
||||
;
|
||||
; X64-LABEL: test_vgf2p8affineqb_128:
|
||||
; X64: # %bb.0:
|
||||
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %xmm1, %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xf9,0xce,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %xmm1, %xmm0, %xmm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0x89,0xce,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xf9,0xce,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %xmm1, %xmm0, %xmm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0x89,0xce,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0xce,0xd1,0x03]
|
||||
; X64-NEXT: vpternlogq $150, %xmm2, %xmm4, %xmm3 # encoding: [0x62,0xf3,0xdd,0x08,0x25,0xda,0x96]
|
||||
; X64-NEXT: vmovdqa %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc3]
|
||||
; X64-NEXT: vpxor %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xef,0xc3]
|
||||
; X64-NEXT: vpxor %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xef,0xc0]
|
||||
; X64-NEXT: retq # encoding: [0xc3]
|
||||
%1 = bitcast i16 %mask to <16 x i1>
|
||||
%2 = call <16 x i8> @llvm.x86.vgf2p8affineqb.128(<16 x i8> %src1, <16 x i8> %src2, i8 3)
|
||||
|
|
@ -127,21 +127,21 @@ define <32 x i8> @test_vgf2p8affineqb_256(<32 x i8> %src1, <32 x i8> %src2, <32
|
|||
; X86-LABEL: test_vgf2p8affineqb_256:
|
||||
; X86: # %bb.0:
|
||||
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %ymm1, %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xfd,0xce,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %ymm1, %ymm0, %ymm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xa9,0xce,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xfd,0xce,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %ymm1, %ymm0, %ymm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xa9,0xce,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0xce,0xd1,0x03]
|
||||
; X86-NEXT: vpternlogq $150, %ymm2, %ymm4, %ymm3 # encoding: [0x62,0xf3,0xdd,0x28,0x25,0xda,0x96]
|
||||
; X86-NEXT: vmovdqa %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc3]
|
||||
; X86-NEXT: vpxor %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xef,0xc3]
|
||||
; X86-NEXT: vpxor %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xef,0xc0]
|
||||
; X86-NEXT: retl # encoding: [0xc3]
|
||||
;
|
||||
; X64-LABEL: test_vgf2p8affineqb_256:
|
||||
; X64: # %bb.0:
|
||||
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %ymm1, %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xfd,0xce,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %ymm1, %ymm0, %ymm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xa9,0xce,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc4,0xe3,0xfd,0xce,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %ymm1, %ymm0, %ymm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xa9,0xce,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0xce,0xd1,0x03]
|
||||
; X64-NEXT: vpternlogq $150, %ymm2, %ymm4, %ymm3 # encoding: [0x62,0xf3,0xdd,0x28,0x25,0xda,0x96]
|
||||
; X64-NEXT: vmovdqa %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc3]
|
||||
; X64-NEXT: vpxor %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xef,0xc3]
|
||||
; X64-NEXT: vpxor %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xef,0xc0]
|
||||
; X64-NEXT: retq # encoding: [0xc3]
|
||||
%1 = bitcast i32 %mask to <32 x i1>
|
||||
%2 = call <32 x i8> @llvm.x86.vgf2p8affineqb.256(<32 x i8> %src1, <32 x i8> %src2, i8 3)
|
||||
|
|
@ -157,21 +157,21 @@ define <64 x i8> @test_vgf2p8affineqb_512(<64 x i8> %src1, <64 x i8> %src2, <64
|
|||
; X86-LABEL: test_vgf2p8affineqb_512:
|
||||
; X86: # %bb.0:
|
||||
; X86-NEXT: kmovq {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf8,0x90,0x4c,0x24,0x04]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %zmm1, %zmm0, %zmm4 # encoding: [0x62,0xf3,0xfd,0x48,0xce,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %zmm1, %zmm0, %zmm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xc9,0xce,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %zmm1, %zmm0, %zmm3 # encoding: [0x62,0xf3,0xfd,0x48,0xce,0xd9,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %zmm1, %zmm0, %zmm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xc9,0xce,0xe1,0x03]
|
||||
; X86-NEXT: vgf2p8affineqb $3, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0xce,0xd1,0x03]
|
||||
; X86-NEXT: vpternlogq $150, %zmm2, %zmm4, %zmm3 # encoding: [0x62,0xf3,0xdd,0x48,0x25,0xda,0x96]
|
||||
; X86-NEXT: vmovdqa64 %zmm3, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc3]
|
||||
; X86-NEXT: vpxorq %zmm3, %zmm2, %zmm0 # encoding: [0x62,0xf1,0xed,0x48,0xef,0xc3]
|
||||
; X86-NEXT: vpxorq %zmm0, %zmm4, %zmm0 # encoding: [0x62,0xf1,0xdd,0x48,0xef,0xc0]
|
||||
; X86-NEXT: retl # encoding: [0xc3]
|
||||
;
|
||||
; X64-LABEL: test_vgf2p8affineqb_512:
|
||||
; X64: # %bb.0:
|
||||
; X64-NEXT: kmovq %rdi, %k1 # encoding: [0xc4,0xe1,0xfb,0x92,0xcf]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %zmm1, %zmm0, %zmm4 # encoding: [0x62,0xf3,0xfd,0x48,0xce,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %zmm1, %zmm0, %zmm3 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xc9,0xce,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %zmm1, %zmm0, %zmm3 # encoding: [0x62,0xf3,0xfd,0x48,0xce,0xd9,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %zmm1, %zmm0, %zmm4 {%k1} {z} # encoding: [0x62,0xf3,0xfd,0xc9,0xce,0xe1,0x03]
|
||||
; X64-NEXT: vgf2p8affineqb $3, %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x49,0xce,0xd1,0x03]
|
||||
; X64-NEXT: vpternlogq $150, %zmm2, %zmm4, %zmm3 # encoding: [0x62,0xf3,0xdd,0x48,0x25,0xda,0x96]
|
||||
; X64-NEXT: vmovdqa64 %zmm3, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc3]
|
||||
; X64-NEXT: vpxorq %zmm3, %zmm2, %zmm0 # encoding: [0x62,0xf1,0xed,0x48,0xef,0xc3]
|
||||
; X64-NEXT: vpxorq %zmm0, %zmm4, %zmm0 # encoding: [0x62,0xf1,0xdd,0x48,0xef,0xc0]
|
||||
; X64-NEXT: retq # encoding: [0xc3]
|
||||
%1 = bitcast i64 %mask to <64 x i1>
|
||||
%2 = call <64 x i8> @llvm.x86.vgf2p8affineqb.512(<64 x i8> %src1, <64 x i8> %src2, i8 3)
|
||||
|
|
@ -187,21 +187,21 @@ define <16 x i8> @test_vgf2p8mulb_128(<16 x i8> %src1, <16 x i8> %src2, <16 x i8
|
|||
; X86-LABEL: test_vgf2p8mulb_128:
|
||||
; X86: # %bb.0:
|
||||
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
|
||||
; X86-NEXT: vgf2p8mulb %xmm1, %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0xcf,0xe1]
|
||||
; X86-NEXT: vgf2p8mulb %xmm1, %xmm0, %xmm3 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0xcf,0xd9]
|
||||
; X86-NEXT: vgf2p8mulb %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0xcf,0xd9]
|
||||
; X86-NEXT: vgf2p8mulb %xmm1, %xmm0, %xmm4 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0xcf,0xe1]
|
||||
; X86-NEXT: vgf2p8mulb %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0xcf,0xd1]
|
||||
; X86-NEXT: vpternlogq $150, %xmm2, %xmm4, %xmm3 # encoding: [0x62,0xf3,0xdd,0x08,0x25,0xda,0x96]
|
||||
; X86-NEXT: vmovdqa %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc3]
|
||||
; X86-NEXT: vpxor %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xef,0xc3]
|
||||
; X86-NEXT: vpxor %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xef,0xc0]
|
||||
; X86-NEXT: retl # encoding: [0xc3]
|
||||
;
|
||||
; X64-LABEL: test_vgf2p8mulb_128:
|
||||
; X64: # %bb.0:
|
||||
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
|
||||
; X64-NEXT: vgf2p8mulb %xmm1, %xmm0, %xmm4 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0xcf,0xe1]
|
||||
; X64-NEXT: vgf2p8mulb %xmm1, %xmm0, %xmm3 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0xcf,0xd9]
|
||||
; X64-NEXT: vgf2p8mulb %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0xcf,0xd9]
|
||||
; X64-NEXT: vgf2p8mulb %xmm1, %xmm0, %xmm4 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0xcf,0xe1]
|
||||
; X64-NEXT: vgf2p8mulb %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0xcf,0xd1]
|
||||
; X64-NEXT: vpternlogq $150, %xmm2, %xmm4, %xmm3 # encoding: [0x62,0xf3,0xdd,0x08,0x25,0xda,0x96]
|
||||
; X64-NEXT: vmovdqa %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc3]
|
||||
; X64-NEXT: vpxor %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xef,0xc3]
|
||||
; X64-NEXT: vpxor %xmm0, %xmm4, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xd9,0xef,0xc0]
|
||||
; X64-NEXT: retq # encoding: [0xc3]
|
||||
%1 = bitcast i16 %mask to <16 x i1>
|
||||
%2 = call <16 x i8> @llvm.x86.vgf2p8mulb.128(<16 x i8> %src1, <16 x i8> %src2)
|
||||
|
|
@ -217,21 +217,21 @@ define <32 x i8> @test_vgf2p8mulb_256(<32 x i8> %src1, <32 x i8> %src2, <32 x i8
|
|||
; X86-LABEL: test_vgf2p8mulb_256:
|
||||
; X86: # %bb.0:
|
||||
; X86-NEXT: kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
|
||||
; X86-NEXT: vgf2p8mulb %ymm1, %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0xcf,0xe1]
|
||||
; X86-NEXT: vgf2p8mulb %ymm1, %ymm0, %ymm3 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0xcf,0xd9]
|
||||
; X86-NEXT: vgf2p8mulb %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0xcf,0xd9]
|
||||
; X86-NEXT: vgf2p8mulb %ymm1, %ymm0, %ymm4 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0xcf,0xe1]
|
||||
; X86-NEXT: vgf2p8mulb %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0xcf,0xd1]
|
||||
; X86-NEXT: vpternlogq $150, %ymm2, %ymm4, %ymm3 # encoding: [0x62,0xf3,0xdd,0x28,0x25,0xda,0x96]
|
||||
; X86-NEXT: vmovdqa %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc3]
|
||||
; X86-NEXT: vpxor %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xef,0xc3]
|
||||
; X86-NEXT: vpxor %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xef,0xc0]
|
||||
; X86-NEXT: retl # encoding: [0xc3]
|
||||
;
|
||||
; X64-LABEL: test_vgf2p8mulb_256:
|
||||
; X64: # %bb.0:
|
||||
; X64-NEXT: kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
|
||||
; X64-NEXT: vgf2p8mulb %ymm1, %ymm0, %ymm4 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0xcf,0xe1]
|
||||
; X64-NEXT: vgf2p8mulb %ymm1, %ymm0, %ymm3 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0xcf,0xd9]
|
||||
; X64-NEXT: vgf2p8mulb %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0xcf,0xd9]
|
||||
; X64-NEXT: vgf2p8mulb %ymm1, %ymm0, %ymm4 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0xcf,0xe1]
|
||||
; X64-NEXT: vgf2p8mulb %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0xcf,0xd1]
|
||||
; X64-NEXT: vpternlogq $150, %ymm2, %ymm4, %ymm3 # encoding: [0x62,0xf3,0xdd,0x28,0x25,0xda,0x96]
|
||||
; X64-NEXT: vmovdqa %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc3]
|
||||
; X64-NEXT: vpxor %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xef,0xc3]
|
||||
; X64-NEXT: vpxor %ymm0, %ymm4, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xdd,0xef,0xc0]
|
||||
; X64-NEXT: retq # encoding: [0xc3]
|
||||
%1 = bitcast i32 %mask to <32 x i1>
|
||||
%2 = call <32 x i8> @llvm.x86.vgf2p8mulb.256(<32 x i8> %src1, <32 x i8> %src2)
|
||||
|
|
@ -247,21 +247,21 @@ define <64 x i8> @test_vgf2p8mulb_512(<64 x i8> %src1, <64 x i8> %src2, <64 x i8
|
|||
; X86-LABEL: test_vgf2p8mulb_512:
|
||||
; X86: # %bb.0:
|
||||
; X86-NEXT: kmovq {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf8,0x90,0x4c,0x24,0x04]
|
||||
; X86-NEXT: vgf2p8mulb %zmm1, %zmm0, %zmm4 # encoding: [0x62,0xf2,0x7d,0x48,0xcf,0xe1]
|
||||
; X86-NEXT: vgf2p8mulb %zmm1, %zmm0, %zmm3 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0xcf,0xd9]
|
||||
; X86-NEXT: vgf2p8mulb %zmm1, %zmm0, %zmm3 # encoding: [0x62,0xf2,0x7d,0x48,0xcf,0xd9]
|
||||
; X86-NEXT: vgf2p8mulb %zmm1, %zmm0, %zmm4 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0xcf,0xe1]
|
||||
; X86-NEXT: vgf2p8mulb %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0xcf,0xd1]
|
||||
; X86-NEXT: vpternlogq $150, %zmm2, %zmm4, %zmm3 # encoding: [0x62,0xf3,0xdd,0x48,0x25,0xda,0x96]
|
||||
; X86-NEXT: vmovdqa64 %zmm3, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc3]
|
||||
; X86-NEXT: vpxorq %zmm3, %zmm2, %zmm0 # encoding: [0x62,0xf1,0xed,0x48,0xef,0xc3]
|
||||
; X86-NEXT: vpxorq %zmm0, %zmm4, %zmm0 # encoding: [0x62,0xf1,0xdd,0x48,0xef,0xc0]
|
||||
; X86-NEXT: retl # encoding: [0xc3]
|
||||
;
|
||||
; X64-LABEL: test_vgf2p8mulb_512:
|
||||
; X64: # %bb.0:
|
||||
; X64-NEXT: kmovq %rdi, %k1 # encoding: [0xc4,0xe1,0xfb,0x92,0xcf]
|
||||
; X64-NEXT: vgf2p8mulb %zmm1, %zmm0, %zmm4 # encoding: [0x62,0xf2,0x7d,0x48,0xcf,0xe1]
|
||||
; X64-NEXT: vgf2p8mulb %zmm1, %zmm0, %zmm3 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0xcf,0xd9]
|
||||
; X64-NEXT: vgf2p8mulb %zmm1, %zmm0, %zmm3 # encoding: [0x62,0xf2,0x7d,0x48,0xcf,0xd9]
|
||||
; X64-NEXT: vgf2p8mulb %zmm1, %zmm0, %zmm4 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xc9,0xcf,0xe1]
|
||||
; X64-NEXT: vgf2p8mulb %zmm1, %zmm0, %zmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x49,0xcf,0xd1]
|
||||
; X64-NEXT: vpternlogq $150, %zmm2, %zmm4, %zmm3 # encoding: [0x62,0xf3,0xdd,0x48,0x25,0xda,0x96]
|
||||
; X64-NEXT: vmovdqa64 %zmm3, %zmm0 # encoding: [0x62,0xf1,0xfd,0x48,0x6f,0xc3]
|
||||
; X64-NEXT: vpxorq %zmm3, %zmm2, %zmm0 # encoding: [0x62,0xf1,0xed,0x48,0xef,0xc3]
|
||||
; X64-NEXT: vpxorq %zmm0, %zmm4, %zmm0 # encoding: [0x62,0xf1,0xdd,0x48,0xef,0xc0]
|
||||
; X64-NEXT: retq # encoding: [0xc3]
|
||||
%1 = bitcast i64 %mask to <64 x i1>
|
||||
%2 = call <64 x i8> @llvm.x86.vgf2p8mulb.512(<64 x i8> %src1, <64 x i8> %src2)
|
||||
|
|
|
|||
|
|
@ -13,18 +13,12 @@ define <4 x i32> @reassociate_and_v4i32(<4 x i32> %x0, <4 x i32> %x1, <4 x i32>
|
|||
; SSE-NEXT: pand %xmm2, %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: reassociate_and_v4i32:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpaddd %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpand %xmm3, %xmm2, %xmm1
|
||||
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: reassociate_and_v4i32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpaddd %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpternlogd $128, %xmm2, %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
; AVX-LABEL: reassociate_and_v4i32:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vpaddd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpand %xmm3, %xmm2, %xmm1
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
|
||||
%t0 = add <4 x i32> %x0, %x1
|
||||
%t1 = and <4 x i32> %x2, %t0
|
||||
|
|
@ -40,18 +34,12 @@ define <4 x i32> @reassociate_or_v4i32(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %
|
|||
; SSE-NEXT: por %xmm2, %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: reassociate_or_v4i32:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpaddd %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpor %xmm3, %xmm2, %xmm1
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: reassociate_or_v4i32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpaddd %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpternlogd $254, %xmm2, %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
; AVX-LABEL: reassociate_or_v4i32:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vpaddd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpor %xmm3, %xmm2, %xmm1
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
|
||||
%t0 = add <4 x i32> %x0, %x1
|
||||
%t1 = or <4 x i32> %x2, %t0
|
||||
|
|
@ -67,18 +55,12 @@ define <4 x i32> @reassociate_xor_v4i32(<4 x i32> %x0, <4 x i32> %x1, <4 x i32>
|
|||
; SSE-NEXT: pxor %xmm2, %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: reassociate_xor_v4i32:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpaddd %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpxor %xmm3, %xmm2, %xmm1
|
||||
; AVX2-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: reassociate_xor_v4i32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpaddd %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpternlogd $150, %xmm2, %xmm3, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
; AVX-LABEL: reassociate_xor_v4i32:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vpaddd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpxor %xmm3, %xmm2, %xmm1
|
||||
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
|
||||
%t0 = add <4 x i32> %x0, %x1
|
||||
%t1 = xor <4 x i32> %x2, %t0
|
||||
|
|
@ -99,18 +81,12 @@ define <8 x i32> @reassociate_and_v8i32(<8 x i32> %x0, <8 x i32> %x1, <8 x i32>
|
|||
; SSE-NEXT: pand %xmm5, %xmm1
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: reassociate_and_v8i32:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpand %ymm3, %ymm2, %ymm1
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: reassociate_and_v8i32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
||||
; AVX512-NEXT: vpternlogd $128, %ymm2, %ymm3, %ymm0
|
||||
; AVX512-NEXT: retq
|
||||
; AVX-LABEL: reassociate_and_v8i32:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
||||
; AVX-NEXT: vpand %ymm3, %ymm2, %ymm1
|
||||
; AVX-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX-NEXT: retq
|
||||
|
||||
%t0 = add <8 x i32> %x0, %x1
|
||||
%t1 = and <8 x i32> %x2, %t0
|
||||
|
|
@ -129,18 +105,12 @@ define <8 x i32> @reassociate_or_v8i32(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %
|
|||
; SSE-NEXT: por %xmm5, %xmm1
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: reassociate_or_v8i32:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpor %ymm3, %ymm2, %ymm1
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: reassociate_or_v8i32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
||||
; AVX512-NEXT: vpternlogd $254, %ymm2, %ymm3, %ymm0
|
||||
; AVX512-NEXT: retq
|
||||
; AVX-LABEL: reassociate_or_v8i32:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
||||
; AVX-NEXT: vpor %ymm3, %ymm2, %ymm1
|
||||
; AVX-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX-NEXT: retq
|
||||
|
||||
%t0 = add <8 x i32> %x0, %x1
|
||||
%t1 = or <8 x i32> %x2, %t0
|
||||
|
|
@ -159,18 +129,12 @@ define <8 x i32> @reassociate_xor_v8i32(<8 x i32> %x0, <8 x i32> %x1, <8 x i32>
|
|||
; SSE-NEXT: pxor %xmm5, %xmm1
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: reassociate_xor_v8i32:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpxor %ymm3, %ymm2, %ymm1
|
||||
; AVX2-NEXT: vpxor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: reassociate_xor_v8i32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
||||
; AVX512-NEXT: vpternlogd $150, %ymm2, %ymm3, %ymm0
|
||||
; AVX512-NEXT: retq
|
||||
; AVX-LABEL: reassociate_xor_v8i32:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vpaddd %ymm1, %ymm0, %ymm0
|
||||
; AVX-NEXT: vpxor %ymm3, %ymm2, %ymm1
|
||||
; AVX-NEXT: vpxor %ymm1, %ymm0, %ymm0
|
||||
; AVX-NEXT: retq
|
||||
|
||||
%t0 = add <8 x i32> %x0, %x1
|
||||
%t1 = xor <8 x i32> %x2, %t0
|
||||
|
|
@ -211,7 +175,8 @@ define <16 x i32> @reassociate_and_v16i32(<16 x i32> %x0, <16 x i32> %x1, <16 x
|
|||
; AVX512-LABEL: reassociate_and_v16i32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpaddd %zmm1, %zmm0, %zmm0
|
||||
; AVX512-NEXT: vpternlogd $128, %zmm2, %zmm3, %zmm0
|
||||
; AVX512-NEXT: vpandd %zmm3, %zmm2, %zmm1
|
||||
; AVX512-NEXT: vpandd %zmm1, %zmm0, %zmm0
|
||||
; AVX512-NEXT: retq
|
||||
|
||||
%t0 = add <16 x i32> %x0, %x1
|
||||
|
|
@ -250,7 +215,8 @@ define <16 x i32> @reassociate_or_v16i32(<16 x i32> %x0, <16 x i32> %x1, <16 x i
|
|||
; AVX512-LABEL: reassociate_or_v16i32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpaddd %zmm1, %zmm0, %zmm0
|
||||
; AVX512-NEXT: vpternlogd $254, %zmm2, %zmm3, %zmm0
|
||||
; AVX512-NEXT: vpord %zmm3, %zmm2, %zmm1
|
||||
; AVX512-NEXT: vpord %zmm1, %zmm0, %zmm0
|
||||
; AVX512-NEXT: retq
|
||||
|
||||
%t0 = add <16 x i32> %x0, %x1
|
||||
|
|
@ -289,7 +255,8 @@ define <16 x i32> @reassociate_xor_v16i32(<16 x i32> %x0, <16 x i32> %x1, <16 x
|
|||
; AVX512-LABEL: reassociate_xor_v16i32:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpaddd %zmm1, %zmm0, %zmm0
|
||||
; AVX512-NEXT: vpternlogd $150, %zmm2, %zmm3, %zmm0
|
||||
; AVX512-NEXT: vpxord %zmm3, %zmm2, %zmm1
|
||||
; AVX512-NEXT: vpxord %zmm1, %zmm0, %zmm0
|
||||
; AVX512-NEXT: retq
|
||||
|
||||
%t0 = add <16 x i32> %x0, %x1
|
||||
|
|
|
|||
|
|
@ -2263,12 +2263,12 @@ define <8 x i16> @vec128_i16_unsigned_reg_reg(<8 x i16> %a1, <8 x i16> %a2) noun
|
|||
; AVX512VL-FALLBACK: # %bb.0:
|
||||
; AVX512VL-FALLBACK-NEXT: vpminuw %xmm1, %xmm0, %xmm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqw %xmm2, %xmm0, %xmm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $190, {{.*}}(%rip), %xmm3, %xmm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $15, %xmm3, %xmm3, %xmm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpor {{.*}}(%rip), %xmm3, %xmm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpmaxuw %xmm1, %xmm0, %xmm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsubw %xmm2, %xmm1, %xmm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsrlw $1, %xmm1, %xmm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %xmm4, %xmm1, %xmm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %xmm3, %xmm1, %xmm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpaddw %xmm0, %xmm1, %xmm0
|
||||
; AVX512VL-FALLBACK-NEXT: retq
|
||||
;
|
||||
|
|
@ -3123,14 +3123,14 @@ define <16 x i8> @vec128_i8_unsigned_reg_reg(<16 x i8> %a1, <16 x i8> %a2) nounw
|
|||
; AVX512VL-FALLBACK: # %bb.0:
|
||||
; AVX512VL-FALLBACK-NEXT: vpminub %xmm1, %xmm0, %xmm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqb %xmm2, %xmm0, %xmm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $190, {{.*}}(%rip), %xmm3, %xmm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $15, %xmm3, %xmm3, %xmm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpor {{.*}}(%rip), %xmm3, %xmm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpmaxub %xmm1, %xmm0, %xmm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsubb %xmm2, %xmm1, %xmm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsrlw $1, %xmm1, %xmm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpmovzxbw {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero,xmm1[8],zero,xmm1[9],zero,xmm1[10],zero,xmm1[11],zero,xmm1[12],zero,xmm1[13],zero,xmm1[14],zero,xmm1[15],zero
|
||||
; AVX512VL-FALLBACK-NEXT: vpmovzxbw {{.*#+}} ymm2 = xmm4[0],zero,xmm4[1],zero,xmm4[2],zero,xmm4[3],zero,xmm4[4],zero,xmm4[5],zero,xmm4[6],zero,xmm4[7],zero,xmm4[8],zero,xmm4[9],zero,xmm4[10],zero,xmm4[11],zero,xmm4[12],zero,xmm4[13],zero,xmm4[14],zero,xmm4[15],zero
|
||||
; AVX512VL-FALLBACK-NEXT: vpmovzxbw {{.*#+}} ymm2 = xmm3[0],zero,xmm3[1],zero,xmm3[2],zero,xmm3[3],zero,xmm3[4],zero,xmm3[5],zero,xmm3[6],zero,xmm3[7],zero,xmm3[8],zero,xmm3[9],zero,xmm3[10],zero,xmm3[11],zero,xmm3[12],zero,xmm3[13],zero,xmm3[14],zero,xmm3[15],zero
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm2, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
|
||||
; AVX512VL-FALLBACK-NEXT: vpmovdb %zmm1, %xmm1
|
||||
|
|
|
|||
|
|
@ -1855,12 +1855,12 @@ define <16 x i16> @vec256_i16_unsigned_reg_reg(<16 x i16> %a1, <16 x i16> %a2) n
|
|||
; AVX512VL-FALLBACK: # %bb.0:
|
||||
; AVX512VL-FALLBACK-NEXT: vpminuw %ymm1, %ymm0, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqw %ymm2, %ymm0, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqd %ymm4, %ymm4, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $190, {{.*}}(%rip), %ymm3, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $15, %ymm3, %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpor {{.*}}(%rip), %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpmaxuw %ymm1, %ymm0, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsubw %ymm2, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsrlw $1, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm4, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm3, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpaddw %ymm0, %ymm1, %ymm0
|
||||
; AVX512VL-FALLBACK-NEXT: retq
|
||||
;
|
||||
|
|
@ -2789,21 +2789,21 @@ define <32 x i8> @vec256_i8_unsigned_reg_reg(<32 x i8> %a1, <32 x i8> %a2) nounw
|
|||
; AVX512VL-FALLBACK: # %bb.0:
|
||||
; AVX512VL-FALLBACK-NEXT: vpminub %ymm1, %ymm0, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqb %ymm2, %ymm0, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqd %ymm4, %ymm4, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $190, {{.*}}(%rip), %ymm3, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $15, %ymm3, %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpor {{.*}}(%rip), %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpmaxub %ymm1, %ymm0, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsubb %ymm2, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsrlw $1, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpand {{.*}}(%rip), %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpckhbw {{.*#+}} ymm2 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31]
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpckhbw {{.*#+}} ymm3 = ymm4[8],ymm0[8],ymm4[9],ymm0[9],ymm4[10],ymm0[10],ymm4[11],ymm0[11],ymm4[12],ymm0[12],ymm4[13],ymm0[13],ymm4[14],ymm0[14],ymm4[15],ymm0[15],ymm4[24],ymm0[24],ymm4[25],ymm0[25],ymm4[26],ymm0[26],ymm4[27],ymm0[27],ymm4[28],ymm0[28],ymm4[29],ymm0[29],ymm4[30],ymm0[30],ymm4[31],ymm0[31]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm3, %ymm2, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vmovdqa {{.*#+}} ymm3 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm3, %ymm2, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpckhbw {{.*#+}} ymm4 = ymm3[8],ymm0[8],ymm3[9],ymm0[9],ymm3[10],ymm0[10],ymm3[11],ymm0[11],ymm3[12],ymm0[12],ymm3[13],ymm0[13],ymm3[14],ymm0[14],ymm3[15],ymm0[15],ymm3[24],ymm0[24],ymm3[25],ymm0[25],ymm3[26],ymm0[26],ymm3[27],ymm0[27],ymm3[28],ymm0[28],ymm3[29],ymm0[29],ymm3[30],ymm0[30],ymm3[31],ymm0[31]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm4, %ymm2, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vmovdqa {{.*#+}} ymm4 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm4, %ymm2, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpcklbw {{.*#+}} ymm1 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23]
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpcklbw {{.*#+}} ymm4 = ymm4[0],ymm0[0],ymm4[1],ymm0[1],ymm4[2],ymm0[2],ymm4[3],ymm0[3],ymm4[4],ymm0[4],ymm4[5],ymm0[5],ymm4[6],ymm0[6],ymm4[7],ymm0[7],ymm4[16],ymm0[16],ymm4[17],ymm0[17],ymm4[18],ymm0[18],ymm4[19],ymm0[19],ymm4[20],ymm0[20],ymm4[21],ymm0[21],ymm4[22],ymm0[22],ymm4[23],ymm0[23]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm4, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm3, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpcklbw {{.*#+}} ymm3 = ymm3[0],ymm0[0],ymm3[1],ymm0[1],ymm3[2],ymm0[2],ymm3[3],ymm0[3],ymm3[4],ymm0[4],ymm3[5],ymm0[5],ymm3[6],ymm0[6],ymm3[7],ymm0[7],ymm3[16],ymm0[16],ymm3[17],ymm0[17],ymm3[18],ymm0[18],ymm3[19],ymm0[19],ymm3[20],ymm0[20],ymm3[21],ymm0[21],ymm3[22],ymm0[22],ymm3[23],ymm0[23]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm3, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm4, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpackuswb %ymm2, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpaddb %ymm0, %ymm1, %ymm0
|
||||
; AVX512VL-FALLBACK-NEXT: retq
|
||||
|
|
|
|||
|
|
@ -418,20 +418,21 @@ define <32 x i16> @vec512_i16_unsigned_reg_reg(<32 x i16> %a1, <32 x i16> %a2) n
|
|||
; AVX512VL-FALLBACK-NEXT: vextracti64x4 $1, %zmm0, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpminuw %ymm2, %ymm3, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqw %ymm4, %ymm3, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqd %ymm6, %ymm6, %ymm6
|
||||
; AVX512VL-FALLBACK-NEXT: vmovdqa {{.*#+}} ymm7 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $222, %ymm6, %ymm7, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vpminuw %ymm1, %ymm0, %ymm8
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqw %ymm8, %ymm0, %ymm9
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $222, %ymm6, %ymm7, %ymm9
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $15, %ymm5, %ymm5, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vmovdqa {{.*#+}} ymm6 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
|
||||
; AVX512VL-FALLBACK-NEXT: vpor %ymm6, %ymm5, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vpminuw %ymm1, %ymm0, %ymm7
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqw %ymm7, %ymm0, %ymm8
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $15, %ymm8, %ymm8, %ymm8
|
||||
; AVX512VL-FALLBACK-NEXT: vpor %ymm6, %ymm8, %ymm6
|
||||
; AVX512VL-FALLBACK-NEXT: vpmaxuw %ymm2, %ymm3, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpmaxuw %ymm1, %ymm0, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsubw %ymm8, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsubw %ymm7, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsubw %ymm4, %ymm2, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpsrlw $1, %ymm2, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm5, %ymm2, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpsrlw $1, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm9, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm6, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpaddw %ymm3, %ymm2, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpaddw %ymm0, %ymm1, %ymm0
|
||||
; AVX512VL-FALLBACK-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
|
|
@ -876,44 +877,45 @@ define <64 x i8> @vec512_i8_unsigned_reg_reg(<64 x i8> %a1, <64 x i8> %a2) nounw
|
|||
;
|
||||
; AVX512VL-FALLBACK-LABEL: vec512_i8_unsigned_reg_reg:
|
||||
; AVX512VL-FALLBACK: # %bb.0:
|
||||
; AVX512VL-FALLBACK-NEXT: vextracti64x4 $1, %zmm1, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vextracti64x4 $1, %zmm1, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vextracti64x4 $1, %zmm0, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpminub %ymm4, %ymm2, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqb %ymm5, %ymm2, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqd %ymm6, %ymm6, %ymm6
|
||||
; AVX512VL-FALLBACK-NEXT: vmovdqa {{.*#+}} ymm7 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $222, %ymm6, %ymm7, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpminub %ymm1, %ymm0, %ymm8
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqb %ymm8, %ymm0, %ymm9
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $222, %ymm6, %ymm7, %ymm9
|
||||
; AVX512VL-FALLBACK-NEXT: vpmaxub %ymm4, %ymm2, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpminub %ymm3, %ymm2, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqb %ymm4, %ymm2, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $15, %ymm5, %ymm5, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vmovdqa {{.*#+}} ymm6 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
|
||||
; AVX512VL-FALLBACK-NEXT: vpor %ymm6, %ymm5, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vpminub %ymm1, %ymm0, %ymm7
|
||||
; AVX512VL-FALLBACK-NEXT: vpcmpeqb %ymm7, %ymm0, %ymm8
|
||||
; AVX512VL-FALLBACK-NEXT: vpternlogq $15, %ymm8, %ymm8, %ymm8
|
||||
; AVX512VL-FALLBACK-NEXT: vpor %ymm6, %ymm8, %ymm6
|
||||
; AVX512VL-FALLBACK-NEXT: vpmaxub %ymm3, %ymm2, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpmaxub %ymm1, %ymm0, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsubb %ymm8, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsubb %ymm5, %ymm4, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpsrlw $1, %ymm4, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vmovdqa {{.*#+}} ymm5 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm5, %ymm4, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpsubb %ymm7, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpsubb %ymm4, %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpsrlw $1, %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vmovdqa {{.*#+}} ymm4 = [127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127,127]
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm4, %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpsrlw $1, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm5, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpckhbw {{.*#+}} ymm5 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31]
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpckhbw {{.*#+}} ymm6 = ymm9[8],ymm0[8],ymm9[9],ymm0[9],ymm9[10],ymm0[10],ymm9[11],ymm0[11],ymm9[12],ymm0[12],ymm9[13],ymm0[13],ymm9[14],ymm0[14],ymm9[15],ymm0[15],ymm9[24],ymm0[24],ymm9[25],ymm0[25],ymm9[26],ymm0[26],ymm9[27],ymm0[27],ymm9[28],ymm0[28],ymm9[29],ymm0[29],ymm9[30],ymm0[30],ymm9[31],ymm0[31]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm6, %ymm5, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vmovdqa {{.*#+}} ymm6 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm6, %ymm5, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm4, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpckhbw {{.*#+}} ymm4 = ymm1[8],ymm0[8],ymm1[9],ymm0[9],ymm1[10],ymm0[10],ymm1[11],ymm0[11],ymm1[12],ymm0[12],ymm1[13],ymm0[13],ymm1[14],ymm0[14],ymm1[15],ymm0[15],ymm1[24],ymm0[24],ymm1[25],ymm0[25],ymm1[26],ymm0[26],ymm1[27],ymm0[27],ymm1[28],ymm0[28],ymm1[29],ymm0[29],ymm1[30],ymm0[30],ymm1[31],ymm0[31]
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpckhbw {{.*#+}} ymm7 = ymm6[8],ymm0[8],ymm6[9],ymm0[9],ymm6[10],ymm0[10],ymm6[11],ymm0[11],ymm6[12],ymm0[12],ymm6[13],ymm0[13],ymm6[14],ymm0[14],ymm6[15],ymm0[15],ymm6[24],ymm0[24],ymm6[25],ymm0[25],ymm6[26],ymm0[26],ymm6[27],ymm0[27],ymm6[28],ymm0[28],ymm6[29],ymm0[29],ymm6[30],ymm0[30],ymm6[31],ymm0[31]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm7, %ymm4, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vmovdqa {{.*#+}} ymm7 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm7, %ymm4, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpcklbw {{.*#+}} ymm1 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[4],ymm0[4],ymm1[5],ymm0[5],ymm1[6],ymm0[6],ymm1[7],ymm0[7],ymm1[16],ymm0[16],ymm1[17],ymm0[17],ymm1[18],ymm0[18],ymm1[19],ymm0[19],ymm1[20],ymm0[20],ymm1[21],ymm0[21],ymm1[22],ymm0[22],ymm1[23],ymm0[23]
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpcklbw {{.*#+}} ymm7 = ymm9[0],ymm0[0],ymm9[1],ymm0[1],ymm9[2],ymm0[2],ymm9[3],ymm0[3],ymm9[4],ymm0[4],ymm9[5],ymm0[5],ymm9[6],ymm0[6],ymm9[7],ymm0[7],ymm9[16],ymm0[16],ymm9[17],ymm0[17],ymm9[18],ymm0[18],ymm9[19],ymm0[19],ymm9[20],ymm0[20],ymm9[21],ymm0[21],ymm9[22],ymm0[22],ymm9[23],ymm0[23]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm7, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm6, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpackuswb %ymm5, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpckhbw {{.*#+}} ymm5 = ymm4[8],ymm0[8],ymm4[9],ymm0[9],ymm4[10],ymm0[10],ymm4[11],ymm0[11],ymm4[12],ymm0[12],ymm4[13],ymm0[13],ymm4[14],ymm0[14],ymm4[15],ymm0[15],ymm4[24],ymm0[24],ymm4[25],ymm0[25],ymm4[26],ymm0[26],ymm4[27],ymm0[27],ymm4[28],ymm0[28],ymm4[29],ymm0[29],ymm4[30],ymm0[30],ymm4[31],ymm0[31]
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpckhbw {{.*#+}} ymm7 = ymm3[8],ymm0[8],ymm3[9],ymm0[9],ymm3[10],ymm0[10],ymm3[11],ymm0[11],ymm3[12],ymm0[12],ymm3[13],ymm0[13],ymm3[14],ymm0[14],ymm3[15],ymm0[15],ymm3[24],ymm0[24],ymm3[25],ymm0[25],ymm3[26],ymm0[26],ymm3[27],ymm0[27],ymm3[28],ymm0[28],ymm3[29],ymm0[29],ymm3[30],ymm0[30],ymm3[31],ymm0[31]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm7, %ymm5, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm6, %ymm5, %ymm5
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpcklbw {{.*#+}} ymm4 = ymm4[0],ymm0[0],ymm4[1],ymm0[1],ymm4[2],ymm0[2],ymm4[3],ymm0[3],ymm4[4],ymm0[4],ymm4[5],ymm0[5],ymm4[6],ymm0[6],ymm4[7],ymm0[7],ymm4[16],ymm0[16],ymm4[17],ymm0[17],ymm4[18],ymm0[18],ymm4[19],ymm0[19],ymm4[20],ymm0[20],ymm4[21],ymm0[21],ymm4[22],ymm0[22],ymm4[23],ymm0[23]
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpcklbw {{.*#+}} ymm6 = ymm6[0],ymm0[0],ymm6[1],ymm0[1],ymm6[2],ymm0[2],ymm6[3],ymm0[3],ymm6[4],ymm0[4],ymm6[5],ymm0[5],ymm6[6],ymm0[6],ymm6[7],ymm0[7],ymm6[16],ymm0[16],ymm6[17],ymm0[17],ymm6[18],ymm0[18],ymm6[19],ymm0[19],ymm6[20],ymm0[20],ymm6[21],ymm0[21],ymm6[22],ymm0[22],ymm6[23],ymm0[23]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm6, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm7, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpackuswb %ymm4, %ymm1, %ymm1
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpckhbw {{.*#+}} ymm4 = ymm3[8],ymm0[8],ymm3[9],ymm0[9],ymm3[10],ymm0[10],ymm3[11],ymm0[11],ymm3[12],ymm0[12],ymm3[13],ymm0[13],ymm3[14],ymm0[14],ymm3[15],ymm0[15],ymm3[24],ymm0[24],ymm3[25],ymm0[25],ymm3[26],ymm0[26],ymm3[27],ymm0[27],ymm3[28],ymm0[28],ymm3[29],ymm0[29],ymm3[30],ymm0[30],ymm3[31],ymm0[31]
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpckhbw {{.*#+}} ymm6 = ymm5[8],ymm0[8],ymm5[9],ymm0[9],ymm5[10],ymm0[10],ymm5[11],ymm0[11],ymm5[12],ymm0[12],ymm5[13],ymm0[13],ymm5[14],ymm0[14],ymm5[15],ymm0[15],ymm5[24],ymm0[24],ymm5[25],ymm0[25],ymm5[26],ymm0[26],ymm5[27],ymm0[27],ymm5[28],ymm0[28],ymm5[29],ymm0[29],ymm5[30],ymm0[30],ymm5[31],ymm0[31]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm6, %ymm4, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm7, %ymm4, %ymm4
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpcklbw {{.*#+}} ymm3 = ymm3[0],ymm0[0],ymm3[1],ymm0[1],ymm3[2],ymm0[2],ymm3[3],ymm0[3],ymm3[4],ymm0[4],ymm3[5],ymm0[5],ymm3[6],ymm0[6],ymm3[7],ymm0[7],ymm3[16],ymm0[16],ymm3[17],ymm0[17],ymm3[18],ymm0[18],ymm3[19],ymm0[19],ymm3[20],ymm0[20],ymm3[21],ymm0[21],ymm3[22],ymm0[22],ymm3[23],ymm0[23]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm3, %ymm4, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm6, %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpackuswb %ymm5, %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpunpcklbw {{.*#+}} ymm5 = ymm5[0],ymm0[0],ymm5[1],ymm0[1],ymm5[2],ymm0[2],ymm5[3],ymm0[3],ymm5[4],ymm0[4],ymm5[5],ymm0[5],ymm5[6],ymm0[6],ymm5[7],ymm0[7],ymm5[16],ymm0[16],ymm5[17],ymm0[17],ymm5[18],ymm0[18],ymm5[19],ymm0[19],ymm5[20],ymm0[20],ymm5[21],ymm0[21],ymm5[22],ymm0[22],ymm5[23],ymm0[23]
|
||||
; AVX512VL-FALLBACK-NEXT: vpmullw %ymm5, %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpand %ymm7, %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpackuswb %ymm4, %ymm3, %ymm3
|
||||
; AVX512VL-FALLBACK-NEXT: vpaddb %ymm2, %ymm3, %ymm2
|
||||
; AVX512VL-FALLBACK-NEXT: vpaddb %ymm0, %ymm1, %ymm0
|
||||
; AVX512VL-FALLBACK-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
|
|
|
|||
|
|
@ -495,49 +495,20 @@ define <16 x i4> @v16i4(<16 x i4> %x, <16 x i4> %y) nounwind {
|
|||
; SSE-NEXT: psubb %xmm1, %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: v16i4:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vpsllw $4, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
||||
; AVX1-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpsllw $4, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpand %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpaddsb %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsrlw $4, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX1-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: v16i4:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpsllw $4, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
||||
; AVX2-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpsllw $4, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpand %xmm2, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpaddsb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsrlw $4, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX2-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: v16i4:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpsllw $4, %xmm1, %xmm1
|
||||
; AVX512-NEXT: vmovdqa {{.*#+}} xmm2 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
||||
; AVX512-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX512-NEXT: vpsllw $4, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpand %xmm2, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpaddsb %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpsrlw $4, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vmovdqa {{.*#+}} xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512-NEXT: vpternlogq $108, {{.*}}(%rip), %xmm1, %xmm0
|
||||
; AVX512-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
; AVX-LABEL: v16i4:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vpsllw $4, %xmm1, %xmm1
|
||||
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
||||
; AVX-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX-NEXT: vpsllw $4, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpand %xmm2, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpaddsb %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsrlw $4, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovdqa {{.*#+}} xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
%z = call <16 x i4> @llvm.sadd.sat.v16i4(<16 x i4> %x, <16 x i4> %y)
|
||||
ret <16 x i4> %z
|
||||
}
|
||||
|
|
|
|||
|
|
@ -495,49 +495,20 @@ define <16 x i4> @v16i4(<16 x i4> %x, <16 x i4> %y) nounwind {
|
|||
; SSE-NEXT: psubb %xmm1, %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: v16i4:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vpsllw $4, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
||||
; AVX1-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpsllw $4, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpand %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsrlw $4, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX1-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: v16i4:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpsllw $4, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
||||
; AVX2-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpsllw $4, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpand %xmm2, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsrlw $4, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX2-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: v16i4:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpsllw $4, %xmm1, %xmm1
|
||||
; AVX512-NEXT: vmovdqa {{.*#+}} xmm2 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
||||
; AVX512-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX512-NEXT: vpsllw $4, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpand %xmm2, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpsrlw $4, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vmovdqa {{.*#+}} xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512-NEXT: vpternlogq $108, {{.*}}(%rip), %xmm1, %xmm0
|
||||
; AVX512-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
; AVX-LABEL: v16i4:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vpsllw $4, %xmm1, %xmm1
|
||||
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
||||
; AVX-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX-NEXT: vpsllw $4, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpand %xmm2, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsubsb %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsrlw $4, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovdqa {{.*#+}} xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
%z = call <16 x i4> @llvm.ssub.sat.v16i4(<16 x i4> %x, <16 x i4> %y)
|
||||
ret <16 x i4> %z
|
||||
}
|
||||
|
|
|
|||
|
|
@ -552,8 +552,8 @@ define <2 x double> @uitofp_2i64_to_2f64(<2 x i64> %a) {
|
|||
;
|
||||
; AVX512VL-LABEL: uitofp_2i64_to_2f64:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm1 = [4841369599423283200,4841369599423283200]
|
||||
; AVX512VL-NEXT: vpternlogq $248, {{.*}}(%rip), %xmm0, %xmm1
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm1
|
||||
; AVX512VL-NEXT: vpor {{.*}}(%rip), %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpsrlq $32, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpor {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vsubpd {{.*}}(%rip), %xmm0, %xmm0
|
||||
|
|
@ -905,8 +905,8 @@ define <4 x double> @uitofp_4i64_to_4f64(<4 x i64> %a) {
|
|||
;
|
||||
; AVX512VL-LABEL: uitofp_4i64_to_4f64:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpbroadcastq {{.*#+}} ymm1 = [4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200]
|
||||
; AVX512VL-NEXT: vpternlogq $248, {{.*}}(%rip){1to4}, %ymm0, %ymm1
|
||||
; AVX512VL-NEXT: vpandq {{.*}}(%rip){1to4}, %ymm0, %ymm1
|
||||
; AVX512VL-NEXT: vporq {{.*}}(%rip){1to4}, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpsrlq $32, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vporq {{.*}}(%rip){1to4}, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vsubpd {{.*}}(%rip){1to4}, %ymm0, %ymm0
|
||||
|
|
@ -3464,8 +3464,8 @@ define <2 x double> @uitofp_load_2i64_to_2f64(<2 x i64> *%a) {
|
|||
; AVX512VL-LABEL: uitofp_load_2i64_to_2f64:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm1 = [4841369599423283200,4841369599423283200]
|
||||
; AVX512VL-NEXT: vpternlogq $248, {{.*}}(%rip), %xmm0, %xmm1
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm1
|
||||
; AVX512VL-NEXT: vpor {{.*}}(%rip), %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpsrlq $32, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpor {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vsubpd {{.*}}(%rip), %xmm0, %xmm0
|
||||
|
|
@ -3847,8 +3847,8 @@ define <4 x double> @uitofp_load_4i64_to_4f64(<4 x i64> *%a) {
|
|||
; AVX512VL-LABEL: uitofp_load_4i64_to_4f64:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
|
||||
; AVX512VL-NEXT: vpbroadcastq {{.*#+}} ymm1 = [4841369599423283200,4841369599423283200,4841369599423283200,4841369599423283200]
|
||||
; AVX512VL-NEXT: vpternlogq $248, {{.*}}(%rip){1to4}, %ymm0, %ymm1
|
||||
; AVX512VL-NEXT: vpandq {{.*}}(%rip){1to4}, %ymm0, %ymm1
|
||||
; AVX512VL-NEXT: vporq {{.*}}(%rip){1to4}, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpsrlq $32, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vporq {{.*}}(%rip){1to4}, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vsubpd {{.*}}(%rip){1to4}, %ymm0, %ymm0
|
||||
|
|
|
|||
|
|
@ -1550,10 +1550,11 @@ define <32 x i8> @splatvar_funnnel_v32i8(<32 x i8> %x, <32 x i8> %y, <32 x i8> %
|
|||
; AVX512VL-NEXT: vpsrlw %xmm4, %xmm5, %xmm4
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm4, %xmm4
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm4, %ymm4
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm1, %ymm3, %ymm4
|
||||
; AVX512VL-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpcmpeqb %ymm1, %ymm2, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm0, %ymm4, %ymm0
|
||||
; AVX512VL-NEXT: vpand %ymm4, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpor %ymm1, %ymm3, %ymm1
|
||||
; AVX512VL-NEXT: vpxor %xmm3, %xmm3, %xmm3
|
||||
; AVX512VL-NEXT: vpcmpeqb %ymm3, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatvar_funnnel_v32i8:
|
||||
|
|
|
|||
|
|
@ -867,14 +867,16 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %y, <64 x i8> %
|
|||
; AVX512VL-NEXT: vpsrlw %xmm3, %xmm8, %xmm6
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm6, %xmm6
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm6, %ymm6
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm6, %ymm10, %ymm9
|
||||
; AVX512VL-NEXT: vpxor %xmm8, %xmm8, %xmm8
|
||||
; AVX512VL-NEXT: vpcmpeqb %ymm8, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm4, %ymm9, %ymm4
|
||||
; AVX512VL-NEXT: vpand %ymm6, %ymm9, %ymm8
|
||||
; AVX512VL-NEXT: vpor %ymm8, %ymm10, %ymm8
|
||||
; AVX512VL-NEXT: vpxor %xmm9, %xmm9, %xmm9
|
||||
; AVX512VL-NEXT: vpcmpeqb %ymm9, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm4, %ymm8, %ymm4
|
||||
; AVX512VL-NEXT: vpsllw %xmm5, %ymm0, %ymm5
|
||||
; AVX512VL-NEXT: vpand %ymm7, %ymm5, %ymm5
|
||||
; AVX512VL-NEXT: vpsrlw %xmm3, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm6, %ymm5, %ymm1
|
||||
; AVX512VL-NEXT: vpand %ymm6, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpor %ymm1, %ymm5, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
|
||||
; AVX512VL-NEXT: vinserti64x4 $1, %ymm4, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
|
|
@ -892,11 +894,12 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %y, <64 x i8> %
|
|||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512BW-NEXT: vpsubb %xmm2, %xmm4, %xmm4
|
||||
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm4 = xmm4[0],zero,zero,zero,zero,zero,zero,zero,xmm4[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vpsrlw %xmm4, %zmm1, %zmm6
|
||||
; AVX512BW-NEXT: vpsrlw %xmm4, %xmm5, %xmm1
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpternlogq $236, %zmm6, %zmm3, %zmm1
|
||||
; AVX512BW-NEXT: vpsrlw %xmm4, %zmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpsrlw %xmm4, %xmm5, %xmm4
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm4, %xmm4
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm4, %zmm4
|
||||
; AVX512BW-NEXT: vpandq %zmm4, %zmm1, %zmm1
|
||||
; AVX512BW-NEXT: vporq %zmm1, %zmm3, %zmm1
|
||||
; AVX512BW-NEXT: vptestnmb %zmm2, %zmm2, %k1
|
||||
; AVX512BW-NEXT: vmovdqu8 %zmm0, %zmm1 {%k1}
|
||||
; AVX512BW-NEXT: vmovdqa64 %zmm1, %zmm0
|
||||
|
|
@ -915,11 +918,12 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %y, <64 x i8> %
|
|||
; AVX512VBMI2-NEXT: vmovdqa {{.*#+}} xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VBMI2-NEXT: vpsubb %xmm2, %xmm4, %xmm4
|
||||
; AVX512VBMI2-NEXT: vpmovzxbq {{.*#+}} xmm4 = xmm4[0],zero,zero,zero,zero,zero,zero,zero,xmm4[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMI2-NEXT: vpsrlw %xmm4, %zmm1, %zmm6
|
||||
; AVX512VBMI2-NEXT: vpsrlw %xmm4, %xmm5, %xmm1
|
||||
; AVX512VBMI2-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512VBMI2-NEXT: vpbroadcastb %xmm1, %zmm1
|
||||
; AVX512VBMI2-NEXT: vpternlogq $236, %zmm6, %zmm3, %zmm1
|
||||
; AVX512VBMI2-NEXT: vpsrlw %xmm4, %zmm1, %zmm1
|
||||
; AVX512VBMI2-NEXT: vpsrlw %xmm4, %xmm5, %xmm4
|
||||
; AVX512VBMI2-NEXT: vpsrlw $8, %xmm4, %xmm4
|
||||
; AVX512VBMI2-NEXT: vpbroadcastb %xmm4, %zmm4
|
||||
; AVX512VBMI2-NEXT: vpandq %zmm4, %zmm1, %zmm1
|
||||
; AVX512VBMI2-NEXT: vporq %zmm1, %zmm3, %zmm1
|
||||
; AVX512VBMI2-NEXT: vptestnmb %zmm2, %zmm2, %k1
|
||||
; AVX512VBMI2-NEXT: vmovdqu8 %zmm0, %zmm1 {%k1}
|
||||
; AVX512VBMI2-NEXT: vmovdqa64 %zmm1, %zmm0
|
||||
|
|
@ -938,11 +942,12 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %y, <64 x i8> %
|
|||
; AVX512VLBW-NEXT: vmovdqa {{.*#+}} xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VLBW-NEXT: vpsubb %xmm2, %xmm4, %xmm4
|
||||
; AVX512VLBW-NEXT: vpmovzxbq {{.*#+}} xmm4 = xmm4[0],zero,zero,zero,zero,zero,zero,zero,xmm4[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm4, %zmm1, %zmm6
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm4, %xmm5, %xmm1
|
||||
; AVX512VLBW-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm1, %zmm1
|
||||
; AVX512VLBW-NEXT: vpternlogq $236, %zmm6, %zmm3, %zmm1
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm4, %zmm1, %zmm1
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm4, %xmm5, %xmm4
|
||||
; AVX512VLBW-NEXT: vpsrlw $8, %xmm4, %xmm4
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm4, %zmm4
|
||||
; AVX512VLBW-NEXT: vpandq %zmm4, %zmm1, %zmm1
|
||||
; AVX512VLBW-NEXT: vporq %zmm1, %zmm3, %zmm1
|
||||
; AVX512VLBW-NEXT: vptestnmb %zmm2, %zmm2, %k1
|
||||
; AVX512VLBW-NEXT: vmovdqu8 %zmm0, %zmm1 {%k1}
|
||||
; AVX512VLBW-NEXT: vmovdqa64 %zmm1, %zmm0
|
||||
|
|
@ -961,11 +966,12 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %y, <64 x i8> %
|
|||
; AVX512VLVBMI2-NEXT: vmovdqa {{.*#+}} xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VLVBMI2-NEXT: vpsubb %xmm2, %xmm4, %xmm4
|
||||
; AVX512VLVBMI2-NEXT: vpmovzxbq {{.*#+}} xmm4 = xmm4[0],zero,zero,zero,zero,zero,zero,zero,xmm4[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw %xmm4, %zmm1, %zmm6
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw %xmm4, %xmm5, %xmm1
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512VLVBMI2-NEXT: vpbroadcastb %xmm1, %zmm1
|
||||
; AVX512VLVBMI2-NEXT: vpternlogq $236, %zmm6, %zmm3, %zmm1
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw %xmm4, %zmm1, %zmm1
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw %xmm4, %xmm5, %xmm4
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw $8, %xmm4, %xmm4
|
||||
; AVX512VLVBMI2-NEXT: vpbroadcastb %xmm4, %zmm4
|
||||
; AVX512VLVBMI2-NEXT: vpandq %zmm4, %zmm1, %zmm1
|
||||
; AVX512VLVBMI2-NEXT: vporq %zmm1, %zmm3, %zmm1
|
||||
; AVX512VLVBMI2-NEXT: vptestnmb %zmm2, %zmm2, %k1
|
||||
; AVX512VLVBMI2-NEXT: vmovdqu8 %zmm0, %zmm1 {%k1}
|
||||
; AVX512VLVBMI2-NEXT: vmovdqa64 %zmm1, %zmm0
|
||||
|
|
|
|||
|
|
@ -446,11 +446,12 @@ define <32 x i8> @var_funnnel_v32i8(<32 x i8> %x, <32 x i8> %amt) nounwind {
|
|||
; AVX512VL-NEXT: vpternlogq $216, {{.*}}(%rip), %ymm2, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm0, %ymm2
|
||||
; AVX512VL-NEXT: vpaddb %ymm0, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpternlogq $248, {{.*}}(%rip), %ymm2, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm0, %ymm0, %ymm2
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpor %ymm3, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm2, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: var_funnnel_v32i8:
|
||||
|
|
@ -836,11 +837,12 @@ define <32 x i8> @splatvar_funnnel_v32i8(<32 x i8> %x, <32 x i8> %amt) nounwind
|
|||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VL-NEXT: vpsubb %xmm1, %xmm3, %xmm1
|
||||
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %xmm4, %xmm0
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm0, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm3, %ymm2, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %xmm4, %xmm1
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm1, %ymm1
|
||||
; AVX512VL-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpor %ymm0, %ymm2, %ymm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatvar_funnnel_v32i8:
|
||||
|
|
|
|||
|
|
@ -186,11 +186,12 @@ define <64 x i8> @var_funnnel_v64i8(<64 x i8> %x, <64 x i8> %amt) nounwind {
|
|||
; AVX512VL-NEXT: vpaddb %ymm2, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm7, %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm3, %ymm5
|
||||
; AVX512VL-NEXT: vpaddb %ymm3, %ymm3, %ymm7
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm9 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
|
||||
; AVX512VL-NEXT: vpternlogq $248, %ymm9, %ymm5, %ymm7
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm7 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
|
||||
; AVX512VL-NEXT: vpand %ymm7, %ymm5, %ymm5
|
||||
; AVX512VL-NEXT: vpaddb %ymm3, %ymm3, %ymm9
|
||||
; AVX512VL-NEXT: vpor %ymm5, %ymm9, %ymm5
|
||||
; AVX512VL-NEXT: vpaddb %ymm2, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm7, %ymm3, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm5, %ymm3, %ymm2
|
||||
; AVX512VL-NEXT: vpsrlw $4, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpsllw $4, %ymm0, %ymm5
|
||||
; AVX512VL-NEXT: vpternlogq $226, %ymm3, %ymm6, %ymm5
|
||||
|
|
@ -203,10 +204,11 @@ define <64 x i8> @var_funnnel_v64i8(<64 x i8> %x, <64 x i8> %amt) nounwind {
|
|||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm4, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpand %ymm7, %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm0, %ymm0, %ymm4
|
||||
; AVX512VL-NEXT: vpternlogq $248, %ymm9, %ymm3, %ymm4
|
||||
; AVX512VL-NEXT: vpor %ymm3, %ymm4, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm4, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
@ -433,11 +435,13 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %amt) nounwind
|
|||
; AVX512VL-NEXT: vpsrlw %xmm1, %xmm5, %xmm5
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm5, %xmm5
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm5, %ymm5
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm5, %ymm4, %ymm2
|
||||
; AVX512VL-NEXT: vpand %ymm5, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpor %ymm2, %ymm4, %ymm2
|
||||
; AVX512VL-NEXT: vpsllw %xmm3, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpand %ymm6, %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm5, %ymm3, %ymm0
|
||||
; AVX512VL-NEXT: vpand %ymm5, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpor %ymm0, %ymm3, %ymm0
|
||||
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
@ -456,11 +460,12 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %amt) nounwind
|
|||
; AVX512BW-NEXT: vpsubb %xmm1, %xmm4, %xmm1
|
||||
; AVX512BW-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %zmm0, %zmm2
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %xmm5, %xmm0
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpternlogq $236, %zmm2, %zmm3, %zmm0
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %xmm5, %xmm1
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpandq %zmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vporq %zmm0, %zmm3, %zmm0
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512VLBW-LABEL: splatvar_funnnel_v64i8:
|
||||
|
|
@ -478,11 +483,12 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %amt) nounwind
|
|||
; AVX512VLBW-NEXT: vpsubb %xmm1, %xmm4, %xmm1
|
||||
; AVX512VLBW-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX512VLBW-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm1, %zmm0, %zmm2
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm1, %xmm5, %xmm0
|
||||
; AVX512VLBW-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpternlogq $236, %zmm2, %zmm3, %zmm0
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm1, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm1, %xmm5, %xmm1
|
||||
; AVX512VLBW-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm1, %zmm1
|
||||
; AVX512VLBW-NEXT: vpandq %zmm1, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vporq %zmm0, %zmm3, %zmm0
|
||||
; AVX512VLBW-NEXT: retq
|
||||
%splat = shufflevector <64 x i8> %amt, <64 x i8> undef, <64 x i32> zeroinitializer
|
||||
%res = call <64 x i8> @llvm.fshl.v64i8(<64 x i8> %x, <64 x i8> %x, <64 x i8> %splat)
|
||||
|
|
|
|||
|
|
@ -1538,23 +1538,24 @@ define <32 x i8> @splatvar_funnnel_v32i8(<32 x i8> %x, <32 x i8> %y, <32 x i8> %
|
|||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm2, %ymm2
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VL-NEXT: vpsubb %xmm2, %xmm3, %xmm3
|
||||
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm3[0],zero,zero,zero,zero,zero,zero,zero,xmm3[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vpsllw %xmm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
||||
; AVX512VL-NEXT: vpsllw %xmm3, %xmm4, %xmm3
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm3, %ymm3
|
||||
; AVX512VL-NEXT: vpand %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vpsrlw %xmm3, %ymm1, %ymm5
|
||||
; AVX512VL-NEXT: vpsrlw %xmm3, %xmm4, %xmm3
|
||||
; AVX512VL-NEXT: vpsrlw %xmm3, %ymm1, %ymm4
|
||||
; AVX512VL-NEXT: vpcmpeqd %xmm5, %xmm5, %xmm5
|
||||
; AVX512VL-NEXT: vpsrlw %xmm3, %xmm5, %xmm3
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm3, %xmm3
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm3, %ymm3
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm5, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpxor %xmm0, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpcmpeqb %ymm0, %ymm2, %ymm0
|
||||
; AVX512VL-NEXT: vpblendvb %ymm0, %ymm1, %ymm3, %ymm0
|
||||
; AVX512VL-NEXT: vpand %ymm3, %ymm4, %ymm3
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VL-NEXT: vpsubb %xmm2, %xmm4, %xmm4
|
||||
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm4 = xmm4[0],zero,zero,zero,zero,zero,zero,zero,xmm4[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vpsllw %xmm4, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsllw %xmm4, %xmm5, %xmm4
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm4, %ymm4
|
||||
; AVX512VL-NEXT: vpand %ymm4, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpor %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpxor %xmm3, %xmm3, %xmm3
|
||||
; AVX512VL-NEXT: vpcmpeqb %ymm3, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatvar_funnnel_v32i8:
|
||||
|
|
|
|||
|
|
@ -838,32 +838,34 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %y, <64 x i8> %
|
|||
;
|
||||
; AVX512VL-LABEL: splatvar_funnnel_v64i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vextracti64x4 $1, %zmm1, %ymm10
|
||||
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm4
|
||||
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm9
|
||||
; AVX512VL-NEXT: vextracti64x4 $1, %zmm1, %ymm4
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm2, %ymm2
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VL-NEXT: vpsubb %xmm2, %xmm5, %xmm5
|
||||
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm5 = xmm5[0],zero,zero,zero,zero,zero,zero,zero,xmm5[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vpsllw %xmm5, %ymm4, %ymm4
|
||||
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm5 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vpsrlw %xmm5, %ymm4, %ymm6
|
||||
; AVX512VL-NEXT: vpcmpeqd %xmm8, %xmm8, %xmm8
|
||||
; AVX512VL-NEXT: vpsllw %xmm5, %xmm8, %xmm7
|
||||
; AVX512VL-NEXT: vpsrlw %xmm5, %xmm8, %xmm7
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm7, %xmm7
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm7, %ymm7
|
||||
; AVX512VL-NEXT: vpand %ymm7, %ymm4, %ymm4
|
||||
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm6 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vpsrlw %xmm6, %ymm10, %ymm9
|
||||
; AVX512VL-NEXT: vpsrlw %xmm6, %xmm8, %xmm3
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm3, %xmm3
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm3, %ymm3
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm3, %ymm4, %ymm9
|
||||
; AVX512VL-NEXT: vpxor %xmm4, %xmm4, %xmm4
|
||||
; AVX512VL-NEXT: vpcmpeqb %ymm4, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm10, %ymm9, %ymm4
|
||||
; AVX512VL-NEXT: vpsllw %xmm5, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpand %ymm7, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw %xmm6, %ymm1, %ymm5
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm3, %ymm0, %ymm5
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm1, %ymm5, %ymm0
|
||||
; AVX512VL-NEXT: vpand %ymm7, %ymm6, %ymm10
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VL-NEXT: vpsubb %xmm2, %xmm3, %xmm3
|
||||
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm3[0],zero,zero,zero,zero,zero,zero,zero,xmm3[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vpsllw %xmm3, %ymm9, %ymm9
|
||||
; AVX512VL-NEXT: vpsllw %xmm3, %xmm8, %xmm6
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm6, %ymm6
|
||||
; AVX512VL-NEXT: vpand %ymm6, %ymm9, %ymm8
|
||||
; AVX512VL-NEXT: vpor %ymm10, %ymm8, %ymm8
|
||||
; AVX512VL-NEXT: vpxor %xmm9, %xmm9, %xmm9
|
||||
; AVX512VL-NEXT: vpcmpeqb %ymm9, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm4, %ymm8, %ymm4
|
||||
; AVX512VL-NEXT: vpsrlw %xmm5, %ymm1, %ymm5
|
||||
; AVX512VL-NEXT: vpand %ymm7, %ymm5, %ymm5
|
||||
; AVX512VL-NEXT: vpsllw %xmm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpand %ymm6, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpor %ymm5, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vinserti64x4 $1, %ymm4, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
@ -871,20 +873,21 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %y, <64 x i8> %
|
|||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm2, %zmm2
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm2, %zmm2
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512BW-NEXT: vpsubb %xmm2, %xmm3, %xmm3
|
||||
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm3[0],zero,zero,zero,zero,zero,zero,zero,xmm3[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vpsllw %xmm3, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
||||
; AVX512BW-NEXT: vpsllw %xmm3, %xmm4, %xmm3
|
||||
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vpsrlw %xmm3, %zmm1, %zmm4
|
||||
; AVX512BW-NEXT: vpcmpeqd %xmm5, %xmm5, %xmm5
|
||||
; AVX512BW-NEXT: vpsrlw %xmm3, %xmm5, %xmm3
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm3, %xmm3
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm3, %zmm3
|
||||
; AVX512BW-NEXT: vpandq %zmm3, %zmm0, %zmm3
|
||||
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm0 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vpsrlw %xmm0, %zmm1, %zmm5
|
||||
; AVX512BW-NEXT: vpsrlw %xmm0, %xmm4, %xmm0
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpternlogq $236, %zmm5, %zmm3, %zmm0
|
||||
; AVX512BW-NEXT: vpandq %zmm3, %zmm4, %zmm3
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512BW-NEXT: vpsubb %xmm2, %xmm4, %xmm4
|
||||
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm4 = xmm4[0],zero,zero,zero,zero,zero,zero,zero,xmm4[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vpsllw %xmm4, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpsllw %xmm4, %xmm5, %xmm4
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm4, %zmm4
|
||||
; AVX512BW-NEXT: vpandq %zmm4, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vporq %zmm3, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vptestnmb %zmm2, %zmm2, %k1
|
||||
; AVX512BW-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
||||
; AVX512BW-NEXT: retq
|
||||
|
|
@ -893,20 +896,21 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %y, <64 x i8> %
|
|||
; AVX512VBMI2: # %bb.0:
|
||||
; AVX512VBMI2-NEXT: vpbroadcastb %xmm2, %zmm2
|
||||
; AVX512VBMI2-NEXT: vpandq {{.*}}(%rip), %zmm2, %zmm2
|
||||
; AVX512VBMI2-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VBMI2-NEXT: vpsubb %xmm2, %xmm3, %xmm3
|
||||
; AVX512VBMI2-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm3[0],zero,zero,zero,zero,zero,zero,zero,xmm3[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMI2-NEXT: vpsllw %xmm3, %zmm0, %zmm0
|
||||
; AVX512VBMI2-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
||||
; AVX512VBMI2-NEXT: vpsllw %xmm3, %xmm4, %xmm3
|
||||
; AVX512VBMI2-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMI2-NEXT: vpsrlw %xmm3, %zmm1, %zmm4
|
||||
; AVX512VBMI2-NEXT: vpcmpeqd %xmm5, %xmm5, %xmm5
|
||||
; AVX512VBMI2-NEXT: vpsrlw %xmm3, %xmm5, %xmm3
|
||||
; AVX512VBMI2-NEXT: vpsrlw $8, %xmm3, %xmm3
|
||||
; AVX512VBMI2-NEXT: vpbroadcastb %xmm3, %zmm3
|
||||
; AVX512VBMI2-NEXT: vpandq %zmm3, %zmm0, %zmm3
|
||||
; AVX512VBMI2-NEXT: vpmovzxbq {{.*#+}} xmm0 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMI2-NEXT: vpsrlw %xmm0, %zmm1, %zmm5
|
||||
; AVX512VBMI2-NEXT: vpsrlw %xmm0, %xmm4, %xmm0
|
||||
; AVX512VBMI2-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512VBMI2-NEXT: vpbroadcastb %xmm0, %zmm0
|
||||
; AVX512VBMI2-NEXT: vpternlogq $236, %zmm5, %zmm3, %zmm0
|
||||
; AVX512VBMI2-NEXT: vpandq %zmm3, %zmm4, %zmm3
|
||||
; AVX512VBMI2-NEXT: vmovdqa {{.*#+}} xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VBMI2-NEXT: vpsubb %xmm2, %xmm4, %xmm4
|
||||
; AVX512VBMI2-NEXT: vpmovzxbq {{.*#+}} xmm4 = xmm4[0],zero,zero,zero,zero,zero,zero,zero,xmm4[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VBMI2-NEXT: vpsllw %xmm4, %zmm0, %zmm0
|
||||
; AVX512VBMI2-NEXT: vpsllw %xmm4, %xmm5, %xmm4
|
||||
; AVX512VBMI2-NEXT: vpbroadcastb %xmm4, %zmm4
|
||||
; AVX512VBMI2-NEXT: vpandq %zmm4, %zmm0, %zmm0
|
||||
; AVX512VBMI2-NEXT: vporq %zmm3, %zmm0, %zmm0
|
||||
; AVX512VBMI2-NEXT: vptestnmb %zmm2, %zmm2, %k1
|
||||
; AVX512VBMI2-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
||||
; AVX512VBMI2-NEXT: retq
|
||||
|
|
@ -915,20 +919,21 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %y, <64 x i8> %
|
|||
; AVX512VLBW: # %bb.0:
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm2, %zmm2
|
||||
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm2, %zmm2
|
||||
; AVX512VLBW-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VLBW-NEXT: vpsubb %xmm2, %xmm3, %xmm3
|
||||
; AVX512VLBW-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm3[0],zero,zero,zero,zero,zero,zero,zero,xmm3[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLBW-NEXT: vpsllw %xmm3, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
||||
; AVX512VLBW-NEXT: vpsllw %xmm3, %xmm4, %xmm3
|
||||
; AVX512VLBW-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm3, %zmm1, %zmm4
|
||||
; AVX512VLBW-NEXT: vpcmpeqd %xmm5, %xmm5, %xmm5
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm3, %xmm5, %xmm3
|
||||
; AVX512VLBW-NEXT: vpsrlw $8, %xmm3, %xmm3
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm3, %zmm3
|
||||
; AVX512VLBW-NEXT: vpandq %zmm3, %zmm0, %zmm3
|
||||
; AVX512VLBW-NEXT: vpmovzxbq {{.*#+}} xmm0 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm0, %zmm1, %zmm5
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm0, %xmm4, %xmm0
|
||||
; AVX512VLBW-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpternlogq $236, %zmm5, %zmm3, %zmm0
|
||||
; AVX512VLBW-NEXT: vpandq %zmm3, %zmm4, %zmm3
|
||||
; AVX512VLBW-NEXT: vmovdqa {{.*#+}} xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VLBW-NEXT: vpsubb %xmm2, %xmm4, %xmm4
|
||||
; AVX512VLBW-NEXT: vpmovzxbq {{.*#+}} xmm4 = xmm4[0],zero,zero,zero,zero,zero,zero,zero,xmm4[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLBW-NEXT: vpsllw %xmm4, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpsllw %xmm4, %xmm5, %xmm4
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm4, %zmm4
|
||||
; AVX512VLBW-NEXT: vpandq %zmm4, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vporq %zmm3, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vptestnmb %zmm2, %zmm2, %k1
|
||||
; AVX512VLBW-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
||||
; AVX512VLBW-NEXT: retq
|
||||
|
|
@ -937,20 +942,21 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %y, <64 x i8> %
|
|||
; AVX512VLVBMI2: # %bb.0:
|
||||
; AVX512VLVBMI2-NEXT: vpbroadcastb %xmm2, %zmm2
|
||||
; AVX512VLVBMI2-NEXT: vpandq {{.*}}(%rip), %zmm2, %zmm2
|
||||
; AVX512VLVBMI2-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VLVBMI2-NEXT: vpsubb %xmm2, %xmm3, %xmm3
|
||||
; AVX512VLVBMI2-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm3[0],zero,zero,zero,zero,zero,zero,zero,xmm3[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLVBMI2-NEXT: vpsllw %xmm3, %zmm0, %zmm0
|
||||
; AVX512VLVBMI2-NEXT: vpcmpeqd %xmm4, %xmm4, %xmm4
|
||||
; AVX512VLVBMI2-NEXT: vpsllw %xmm3, %xmm4, %xmm3
|
||||
; AVX512VLVBMI2-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw %xmm3, %zmm1, %zmm4
|
||||
; AVX512VLVBMI2-NEXT: vpcmpeqd %xmm5, %xmm5, %xmm5
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw %xmm3, %xmm5, %xmm3
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw $8, %xmm3, %xmm3
|
||||
; AVX512VLVBMI2-NEXT: vpbroadcastb %xmm3, %zmm3
|
||||
; AVX512VLVBMI2-NEXT: vpandq %zmm3, %zmm0, %zmm3
|
||||
; AVX512VLVBMI2-NEXT: vpmovzxbq {{.*#+}} xmm0 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw %xmm0, %zmm1, %zmm5
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw %xmm0, %xmm4, %xmm0
|
||||
; AVX512VLVBMI2-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512VLVBMI2-NEXT: vpbroadcastb %xmm0, %zmm0
|
||||
; AVX512VLVBMI2-NEXT: vpternlogq $236, %zmm5, %zmm3, %zmm0
|
||||
; AVX512VLVBMI2-NEXT: vpandq %zmm3, %zmm4, %zmm3
|
||||
; AVX512VLVBMI2-NEXT: vmovdqa {{.*#+}} xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VLVBMI2-NEXT: vpsubb %xmm2, %xmm4, %xmm4
|
||||
; AVX512VLVBMI2-NEXT: vpmovzxbq {{.*#+}} xmm4 = xmm4[0],zero,zero,zero,zero,zero,zero,zero,xmm4[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLVBMI2-NEXT: vpsllw %xmm4, %zmm0, %zmm0
|
||||
; AVX512VLVBMI2-NEXT: vpsllw %xmm4, %xmm5, %xmm4
|
||||
; AVX512VLVBMI2-NEXT: vpbroadcastb %xmm4, %zmm4
|
||||
; AVX512VLVBMI2-NEXT: vpandq %zmm4, %zmm0, %zmm0
|
||||
; AVX512VLVBMI2-NEXT: vporq %zmm3, %zmm0, %zmm0
|
||||
; AVX512VLVBMI2-NEXT: vptestnmb %zmm2, %zmm2, %k1
|
||||
; AVX512VLVBMI2-NEXT: vmovdqu8 %zmm1, %zmm0 {%k1}
|
||||
; AVX512VLVBMI2-NEXT: retq
|
||||
|
|
|
|||
|
|
@ -487,11 +487,12 @@ define <32 x i8> @var_funnnel_v32i8(<32 x i8> %x, <32 x i8> %amt) nounwind {
|
|||
; AVX512VL-NEXT: vpternlogq $216, {{.*}}(%rip), %ymm2, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm0, %ymm2
|
||||
; AVX512VL-NEXT: vpaddb %ymm0, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpternlogq $248, {{.*}}(%rip), %ymm2, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm0, %ymm0, %ymm2
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpor %ymm3, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm2, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: var_funnnel_v32i8:
|
||||
|
|
@ -911,11 +912,12 @@ define <32 x i8> @splatvar_funnnel_v32i8(<32 x i8> %x, <32 x i8> %amt) nounwind
|
|||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VL-NEXT: vpsubb %xmm1, %xmm3, %xmm1
|
||||
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %xmm4, %xmm0
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm0, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm3, %ymm2, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %xmm4, %xmm1
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm1, %ymm1
|
||||
; AVX512VL-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpor %ymm0, %ymm2, %ymm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatvar_funnnel_v32i8:
|
||||
|
|
|
|||
|
|
@ -197,11 +197,12 @@ define <64 x i8> @var_funnnel_v64i8(<64 x i8> %x, <64 x i8> %amt) nounwind {
|
|||
; AVX512VL-NEXT: vpaddb %ymm2, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm8, %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm3, %ymm5
|
||||
; AVX512VL-NEXT: vpaddb %ymm3, %ymm3, %ymm8
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm10 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
|
||||
; AVX512VL-NEXT: vpternlogq $248, %ymm10, %ymm5, %ymm8
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm8 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
|
||||
; AVX512VL-NEXT: vpand %ymm8, %ymm5, %ymm5
|
||||
; AVX512VL-NEXT: vpaddb %ymm3, %ymm3, %ymm10
|
||||
; AVX512VL-NEXT: vpor %ymm5, %ymm10, %ymm5
|
||||
; AVX512VL-NEXT: vpaddb %ymm2, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm8, %ymm3, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm5, %ymm3, %ymm2
|
||||
; AVX512VL-NEXT: vpsrlw $4, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpsllw $4, %ymm0, %ymm5
|
||||
; AVX512VL-NEXT: vpternlogq $226, %ymm3, %ymm6, %ymm5
|
||||
|
|
@ -215,10 +216,11 @@ define <64 x i8> @var_funnnel_v64i8(<64 x i8> %x, <64 x i8> %amt) nounwind {
|
|||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm4, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpand %ymm8, %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm0, %ymm0, %ymm4
|
||||
; AVX512VL-NEXT: vpternlogq $248, %ymm10, %ymm3, %ymm4
|
||||
; AVX512VL-NEXT: vpor %ymm3, %ymm4, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm4, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
@ -453,56 +455,60 @@ define <64 x i8> @splatvar_funnnel_v64i8(<64 x i8> %x, <64 x i8> %amt) nounwind
|
|||
; AVX512VL-NEXT: vpsrlw %xmm1, %xmm5, %xmm5
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm5, %xmm5
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm5, %ymm5
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm5, %ymm4, %ymm2
|
||||
; AVX512VL-NEXT: vpand %ymm5, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpor %ymm2, %ymm4, %ymm2
|
||||
; AVX512VL-NEXT: vpsllw %xmm3, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpand %ymm6, %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm5, %ymm3, %ymm0
|
||||
; AVX512VL-NEXT: vpand %ymm5, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpor %ymm0, %ymm3, %ymm0
|
||||
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatvar_funnnel_v64i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpsubb %xmm1, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = [7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7]
|
||||
; AVX512BW-NEXT: vpand %xmm3, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm2 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vpsllw %xmm2, %zmm0, %zmm4
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = [7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7]
|
||||
; AVX512BW-NEXT: vpand %xmm2, %xmm1, %xmm3
|
||||
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm3[0],zero,zero,zero,zero,zero,zero,zero,xmm3[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vpsrlw %xmm3, %zmm0, %zmm4
|
||||
; AVX512BW-NEXT: vpcmpeqd %xmm5, %xmm5, %xmm5
|
||||
; AVX512BW-NEXT: vpsllw %xmm2, %xmm5, %xmm2
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm2, %zmm2
|
||||
; AVX512BW-NEXT: vpandq %zmm2, %zmm4, %zmm2
|
||||
; AVX512BW-NEXT: vpand %xmm3, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpsrlw %xmm3, %xmm5, %xmm3
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm3, %xmm3
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm3, %zmm3
|
||||
; AVX512BW-NEXT: vpandq %zmm3, %zmm4, %zmm3
|
||||
; AVX512BW-NEXT: vpxor %xmm4, %xmm4, %xmm4
|
||||
; AVX512BW-NEXT: vpsubb %xmm1, %xmm4, %xmm1
|
||||
; AVX512BW-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %zmm0, %zmm3
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %xmm5, %xmm0
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpternlogq $236, %zmm3, %zmm2, %zmm0
|
||||
; AVX512BW-NEXT: vpsllw %xmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpsllw %xmm1, %xmm5, %xmm1
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpandq %zmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vporq %zmm3, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512VLBW-LABEL: splatvar_funnnel_v64i8:
|
||||
; AVX512VLBW: # %bb.0:
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm1, %xmm1
|
||||
; AVX512VLBW-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
||||
; AVX512VLBW-NEXT: vpsubb %xmm1, %xmm2, %xmm2
|
||||
; AVX512VLBW-NEXT: vmovdqa {{.*#+}} xmm3 = [7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7]
|
||||
; AVX512VLBW-NEXT: vpand %xmm3, %xmm2, %xmm2
|
||||
; AVX512VLBW-NEXT: vpmovzxbq {{.*#+}} xmm2 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLBW-NEXT: vpsllw %xmm2, %zmm0, %zmm4
|
||||
; AVX512VLBW-NEXT: vmovdqa {{.*#+}} xmm2 = [7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7]
|
||||
; AVX512VLBW-NEXT: vpand %xmm2, %xmm1, %xmm3
|
||||
; AVX512VLBW-NEXT: vpmovzxbq {{.*#+}} xmm3 = xmm3[0],zero,zero,zero,zero,zero,zero,zero,xmm3[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm3, %zmm0, %zmm4
|
||||
; AVX512VLBW-NEXT: vpcmpeqd %xmm5, %xmm5, %xmm5
|
||||
; AVX512VLBW-NEXT: vpsllw %xmm2, %xmm5, %xmm2
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm2, %zmm2
|
||||
; AVX512VLBW-NEXT: vpandq %zmm2, %zmm4, %zmm2
|
||||
; AVX512VLBW-NEXT: vpand %xmm3, %xmm1, %xmm1
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm3, %xmm5, %xmm3
|
||||
; AVX512VLBW-NEXT: vpsrlw $8, %xmm3, %xmm3
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm3, %zmm3
|
||||
; AVX512VLBW-NEXT: vpandq %zmm3, %zmm4, %zmm3
|
||||
; AVX512VLBW-NEXT: vpxor %xmm4, %xmm4, %xmm4
|
||||
; AVX512VLBW-NEXT: vpsubb %xmm1, %xmm4, %xmm1
|
||||
; AVX512VLBW-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX512VLBW-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm1, %zmm0, %zmm3
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm1, %xmm5, %xmm0
|
||||
; AVX512VLBW-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpternlogq $236, %zmm3, %zmm2, %zmm0
|
||||
; AVX512VLBW-NEXT: vpsllw %xmm1, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpsllw %xmm1, %xmm5, %xmm1
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm1, %zmm1
|
||||
; AVX512VLBW-NEXT: vpandq %zmm1, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vporq %zmm3, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: retq
|
||||
%splat = shufflevector <64 x i8> %amt, <64 x i8> undef, <64 x i32> zeroinitializer
|
||||
%res = call <64 x i8> @llvm.fshr.v64i8(<64 x i8> %x, <64 x i8> %x, <64 x i8> %splat)
|
||||
|
|
|
|||
|
|
@ -186,8 +186,9 @@ define <64 x i8> @test_div7_64i8(<64 x i8> %a) nounwind {
|
|||
; AVX512BW-NEXT: vinserti64x4 $1, %ymm2, %zmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpaddb %zmm0, %zmm1, %zmm0
|
||||
; AVX512BW-NEXT: vpsrlw $2, %zmm0, %zmm1
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
||||
; AVX512BW-NEXT: vmovdqa64 {{.*#+}} zmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32]
|
||||
; AVX512BW-NEXT: vpternlogq $108, {{.*}}(%rip), %zmm2, %zmm1
|
||||
; AVX512BW-NEXT: vpxorq %zmm2, %zmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpsrlw $7, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpaddb %zmm0, %zmm1, %zmm0
|
||||
|
|
@ -540,8 +541,9 @@ define <64 x i8> @test_rem7_64i8(<64 x i8> %a) nounwind {
|
|||
; AVX512BW-NEXT: vinserti64x4 $1, %ymm2, %zmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpaddb %zmm0, %zmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpsrlw $2, %zmm1, %zmm2
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm2, %zmm2
|
||||
; AVX512BW-NEXT: vmovdqa64 {{.*#+}} zmm3 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32]
|
||||
; AVX512BW-NEXT: vpternlogq $108, {{.*}}(%rip), %zmm3, %zmm2
|
||||
; AVX512BW-NEXT: vpxorq %zmm3, %zmm2, %zmm2
|
||||
; AVX512BW-NEXT: vpsrlw $7, %zmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpaddb %zmm1, %zmm2, %zmm1
|
||||
|
|
|
|||
|
|
@ -2003,35 +2003,13 @@ define <8 x i16> @splatconstant_rotate_mask_v8i16(<8 x i16> %a) nounwind {
|
|||
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: splatconstant_rotate_mask_v8i16:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vpsrlw $11, %xmm0, %xmm1
|
||||
; AVX512F-NEXT: vpsllw $5, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: splatconstant_rotate_mask_v8i16:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpsllw $5, %xmm0, %xmm1
|
||||
; AVX512VL-NEXT: vpsrlw $11, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpternlogq $168, {{.*}}(%rip), %xmm1, %xmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatconstant_rotate_mask_v8i16:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpsrlw $11, %xmm0, %xmm1
|
||||
; AVX512BW-NEXT: vpsllw $5, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512VLBW-LABEL: splatconstant_rotate_mask_v8i16:
|
||||
; AVX512VLBW: # %bb.0:
|
||||
; AVX512VLBW-NEXT: vpsllw $5, %xmm0, %xmm1
|
||||
; AVX512VLBW-NEXT: vpsrlw $11, %xmm0, %xmm0
|
||||
; AVX512VLBW-NEXT: vpternlogq $168, {{.*}}(%rip), %xmm1, %xmm0
|
||||
; AVX512VLBW-NEXT: retq
|
||||
; AVX512-LABEL: splatconstant_rotate_mask_v8i16:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpsrlw $11, %xmm0, %xmm1
|
||||
; AVX512-NEXT: vpsllw $5, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
; XOP-LABEL: splatconstant_rotate_mask_v8i16:
|
||||
; XOP: # %bb.0:
|
||||
|
|
@ -2077,39 +2055,14 @@ define <16 x i8> @splatconstant_rotate_mask_v16i8(<16 x i8> %a) nounwind {
|
|||
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: splatconstant_rotate_mask_v16i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vpsllw $4, %xmm0, %xmm1
|
||||
; AVX512F-NEXT: vpsrlw $4, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpor %xmm0, %xmm1, %xmm0
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: splatconstant_rotate_mask_v16i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpsllw $4, %xmm0, %xmm1
|
||||
; AVX512VL-NEXT: vpsrlw $4, %xmm0, %xmm2
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm0
|
||||
; AVX512VL-NEXT: vpternlogq $248, {{.*}}(%rip), %xmm2, %xmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatconstant_rotate_mask_v16i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpsllw $4, %xmm0, %xmm1
|
||||
; AVX512BW-NEXT: vpsrlw $4, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpor %xmm0, %xmm1, %xmm0
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512VLBW-LABEL: splatconstant_rotate_mask_v16i8:
|
||||
; AVX512VLBW: # %bb.0:
|
||||
; AVX512VLBW-NEXT: vpsllw $4, %xmm0, %xmm1
|
||||
; AVX512VLBW-NEXT: vpsrlw $4, %xmm0, %xmm2
|
||||
; AVX512VLBW-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm0
|
||||
; AVX512VLBW-NEXT: vpternlogq $248, {{.*}}(%rip), %xmm2, %xmm0
|
||||
; AVX512VLBW-NEXT: retq
|
||||
; AVX512-LABEL: splatconstant_rotate_mask_v16i8:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpsllw $4, %xmm0, %xmm1
|
||||
; AVX512-NEXT: vpsrlw $4, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
|
||||
; AVX512-NEXT: vpor %xmm0, %xmm1, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
; XOP-LABEL: splatconstant_rotate_mask_v16i8:
|
||||
; XOP: # %bb.0:
|
||||
|
|
|
|||
|
|
@ -442,11 +442,12 @@ define <32 x i8> @var_rotate_v32i8(<32 x i8> %a, <32 x i8> %b) nounwind {
|
|||
; AVX512VL-NEXT: vpternlogq $216, {{.*}}(%rip), %ymm2, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm0, %ymm2
|
||||
; AVX512VL-NEXT: vpaddb %ymm0, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpternlogq $248, {{.*}}(%rip), %ymm2, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm0, %ymm0, %ymm2
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpor %ymm3, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm2, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: var_rotate_v32i8:
|
||||
|
|
@ -826,11 +827,12 @@ define <32 x i8> @splatvar_rotate_v32i8(<32 x i8> %a, <32 x i8> %b) nounwind {
|
|||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8]
|
||||
; AVX512VL-NEXT: vpsubb %xmm1, %xmm3, %xmm1
|
||||
; AVX512VL-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %xmm4, %xmm0
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm0, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm3, %ymm2, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %xmm4, %xmm1
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm1, %ymm1
|
||||
; AVX512VL-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpor %ymm0, %ymm2, %ymm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatvar_rotate_v32i8:
|
||||
|
|
@ -1711,35 +1713,13 @@ define <16 x i16> @splatconstant_rotate_mask_v16i16(<16 x i16> %a) nounwind {
|
|||
; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: splatconstant_rotate_mask_v16i16:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vpsrlw $11, %ymm0, %ymm1
|
||||
; AVX512F-NEXT: vpsllw $5, %ymm0, %ymm0
|
||||
; AVX512F-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX512F-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: splatconstant_rotate_mask_v16i16:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpsllw $5, %ymm0, %ymm1
|
||||
; AVX512VL-NEXT: vpsrlw $11, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $168, {{.*}}(%rip), %ymm1, %ymm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatconstant_rotate_mask_v16i16:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpsrlw $11, %ymm0, %ymm1
|
||||
; AVX512BW-NEXT: vpsllw $5, %ymm0, %ymm0
|
||||
; AVX512BW-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX512BW-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512VLBW-LABEL: splatconstant_rotate_mask_v16i16:
|
||||
; AVX512VLBW: # %bb.0:
|
||||
; AVX512VLBW-NEXT: vpsllw $5, %ymm0, %ymm1
|
||||
; AVX512VLBW-NEXT: vpsrlw $11, %ymm0, %ymm0
|
||||
; AVX512VLBW-NEXT: vpternlogq $168, {{.*}}(%rip), %ymm1, %ymm0
|
||||
; AVX512VLBW-NEXT: retq
|
||||
; AVX512-LABEL: splatconstant_rotate_mask_v16i16:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpsrlw $11, %ymm0, %ymm1
|
||||
; AVX512-NEXT: vpsllw $5, %ymm0, %ymm0
|
||||
; AVX512-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX512-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX512-NEXT: retq
|
||||
;
|
||||
; XOPAVX1-LABEL: splatconstant_rotate_mask_v16i16:
|
||||
; XOPAVX1: # %bb.0:
|
||||
|
|
@ -1808,11 +1788,9 @@ define <32 x i8> @splatconstant_rotate_mask_v32i8(<32 x i8> %a) nounwind {
|
|||
; AVX512VL-LABEL: splatconstant_rotate_mask_v32i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpsllw $4, %ymm0, %ymm1
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm2 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
||||
; AVX512VL-NEXT: vpand %ymm2, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpsrlw $4, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpandn %ymm0, %ymm2, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $168, {{.*}}(%rip), %ymm1, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $216, {{.*}}(%rip), %ymm1, %ymm0
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatconstant_rotate_mask_v32i8:
|
||||
|
|
@ -1827,9 +1805,10 @@ define <32 x i8> @splatconstant_rotate_mask_v32i8(<32 x i8> %a) nounwind {
|
|||
; AVX512VLBW-LABEL: splatconstant_rotate_mask_v32i8:
|
||||
; AVX512VLBW: # %bb.0:
|
||||
; AVX512VLBW-NEXT: vpsllw $4, %ymm0, %ymm1
|
||||
; AVX512VLBW-NEXT: vpsrlw $4, %ymm0, %ymm2
|
||||
; AVX512VLBW-NEXT: vpand {{.*}}(%rip), %ymm1, %ymm0
|
||||
; AVX512VLBW-NEXT: vpternlogq $248, {{.*}}(%rip), %ymm2, %ymm0
|
||||
; AVX512VLBW-NEXT: vpsrlw $4, %ymm0, %ymm0
|
||||
; AVX512VLBW-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX512VLBW-NEXT: vpand {{.*}}(%rip), %ymm1, %ymm1
|
||||
; AVX512VLBW-NEXT: vpor %ymm0, %ymm1, %ymm0
|
||||
; AVX512VLBW-NEXT: retq
|
||||
;
|
||||
; XOPAVX1-LABEL: splatconstant_rotate_mask_v32i8:
|
||||
|
|
|
|||
|
|
@ -179,11 +179,12 @@ define <64 x i8> @var_rotate_v64i8(<64 x i8> %a, <64 x i8> %b) nounwind {
|
|||
; AVX512VL-NEXT: vpaddb %ymm2, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm5, %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm3, %ymm4
|
||||
; AVX512VL-NEXT: vpaddb %ymm3, %ymm3, %ymm5
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm8 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
|
||||
; AVX512VL-NEXT: vpternlogq $248, %ymm8, %ymm4, %ymm5
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm5 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
|
||||
; AVX512VL-NEXT: vpand %ymm5, %ymm4, %ymm4
|
||||
; AVX512VL-NEXT: vpaddb %ymm3, %ymm3, %ymm8
|
||||
; AVX512VL-NEXT: vpor %ymm4, %ymm8, %ymm4
|
||||
; AVX512VL-NEXT: vpaddb %ymm2, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm5, %ymm3, %ymm2
|
||||
; AVX512VL-NEXT: vpblendvb %ymm2, %ymm4, %ymm3, %ymm2
|
||||
; AVX512VL-NEXT: vpsrlw $4, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpsllw $4, %ymm0, %ymm4
|
||||
; AVX512VL-NEXT: vpternlogq $226, %ymm3, %ymm6, %ymm4
|
||||
|
|
@ -195,10 +196,11 @@ define <64 x i8> @var_rotate_v64i8(<64 x i8> %a, <64 x i8> %b) nounwind {
|
|||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm4, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsrlw $7, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpand %ymm5, %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm0, %ymm0, %ymm4
|
||||
; AVX512VL-NEXT: vpternlogq $248, %ymm8, %ymm3, %ymm4
|
||||
; AVX512VL-NEXT: vpor %ymm3, %ymm4, %ymm3
|
||||
; AVX512VL-NEXT: vpaddb %ymm1, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm4, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpblendvb %ymm1, %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
@ -423,11 +425,13 @@ define <64 x i8> @splatvar_rotate_v64i8(<64 x i8> %a, <64 x i8> %b) nounwind {
|
|||
; AVX512VL-NEXT: vpsrlw %xmm1, %xmm5, %xmm5
|
||||
; AVX512VL-NEXT: vpsrlw $8, %xmm5, %xmm5
|
||||
; AVX512VL-NEXT: vpbroadcastb %xmm5, %ymm5
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm5, %ymm4, %ymm2
|
||||
; AVX512VL-NEXT: vpand %ymm5, %ymm2, %ymm2
|
||||
; AVX512VL-NEXT: vpor %ymm2, %ymm4, %ymm2
|
||||
; AVX512VL-NEXT: vpsllw %xmm3, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpand %ymm6, %ymm3, %ymm3
|
||||
; AVX512VL-NEXT: vpsrlw %xmm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $236, %ymm5, %ymm3, %ymm0
|
||||
; AVX512VL-NEXT: vpand %ymm5, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpor %ymm0, %ymm3, %ymm0
|
||||
; AVX512VL-NEXT: vinserti64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
@ -442,11 +446,12 @@ define <64 x i8> @splatvar_rotate_v64i8(<64 x i8> %a, <64 x i8> %b) nounwind {
|
|||
; AVX512BW-NEXT: vpsllw %xmm2, %xmm4, %xmm2
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm2, %zmm2
|
||||
; AVX512BW-NEXT: vpandq %zmm2, %zmm3, %zmm2
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %zmm0, %zmm3
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %xmm4, %xmm0
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpternlogq $236, %zmm3, %zmm2, %zmm0
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %xmm4, %xmm1
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpandq %zmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vporq %zmm0, %zmm2, %zmm0
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512VLBW-LABEL: splatvar_rotate_v64i8:
|
||||
|
|
@ -460,11 +465,12 @@ define <64 x i8> @splatvar_rotate_v64i8(<64 x i8> %a, <64 x i8> %b) nounwind {
|
|||
; AVX512VLBW-NEXT: vpsllw %xmm2, %xmm4, %xmm2
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm2, %zmm2
|
||||
; AVX512VLBW-NEXT: vpandq %zmm2, %zmm3, %zmm2
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm1, %zmm0, %zmm3
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm1, %xmm4, %xmm0
|
||||
; AVX512VLBW-NEXT: vpsrlw $8, %xmm0, %xmm0
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpternlogq $236, %zmm3, %zmm2, %zmm0
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm1, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpsrlw %xmm1, %xmm4, %xmm1
|
||||
; AVX512VLBW-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512VLBW-NEXT: vpbroadcastb %xmm1, %zmm1
|
||||
; AVX512VLBW-NEXT: vpandq %zmm1, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vporq %zmm0, %zmm2, %zmm0
|
||||
; AVX512VLBW-NEXT: retq
|
||||
%splat = shufflevector <64 x i8> %b, <64 x i8> undef, <64 x i32> zeroinitializer
|
||||
%splat8 = sub <64 x i8> <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>, %splat
|
||||
|
|
@ -883,27 +889,31 @@ define <32 x i16> @splatconstant_rotate_mask_v32i16(<32 x i16> %a) nounwind {
|
|||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm2 = [55,55,55,55,55,55,55,55,55,55,55,55,55,55,55,55]
|
||||
; AVX512VL-NEXT: vpsrlw $11, %ymm1, %ymm3
|
||||
; AVX512VL-NEXT: vpsllw $5, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpternlogq $200, %ymm3, %ymm2, %ymm1
|
||||
; AVX512VL-NEXT: vpor %ymm3, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpand %ymm2, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpsrlw $11, %ymm0, %ymm3
|
||||
; AVX512VL-NEXT: vpsllw $5, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $200, %ymm3, %ymm2, %ymm0
|
||||
; AVX512VL-NEXT: vpor %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpand %ymm2, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatconstant_rotate_mask_v32i16:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpsllw $5, %zmm0, %zmm1
|
||||
; AVX512BW-NEXT: vpsrlw $11, %zmm0, %zmm2
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
||||
; AVX512BW-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
||||
; AVX512BW-NEXT: vpsrlw $11, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
||||
; AVX512BW-NEXT: vporq %zmm0, %zmm1, %zmm0
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512VLBW-LABEL: splatconstant_rotate_mask_v32i16:
|
||||
; AVX512VLBW: # %bb.0:
|
||||
; AVX512VLBW-NEXT: vpsllw $5, %zmm0, %zmm1
|
||||
; AVX512VLBW-NEXT: vpsrlw $11, %zmm0, %zmm2
|
||||
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
||||
; AVX512VLBW-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
||||
; AVX512VLBW-NEXT: vpsrlw $11, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
||||
; AVX512VLBW-NEXT: vporq %zmm0, %zmm1, %zmm0
|
||||
; AVX512VLBW-NEXT: retq
|
||||
%shl = shl <32 x i16> %a, <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>
|
||||
%lshr = lshr <32 x i16> %a, <i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11>
|
||||
|
|
@ -938,34 +948,34 @@ define <64 x i8> @splatconstant_rotate_mask_v64i8(<64 x i8> %a) nounwind {
|
|||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
||||
; AVX512VL-NEXT: vpsrlw $4, %ymm1, %ymm2
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm3 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
||||
; AVX512VL-NEXT: vpandn %ymm2, %ymm3, %ymm2
|
||||
; AVX512VL-NEXT: vpsllw $4, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpand %ymm3, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm4 = [39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39]
|
||||
; AVX512VL-NEXT: vpternlogq $200, %ymm2, %ymm4, %ymm1
|
||||
; AVX512VL-NEXT: vpsrlw $4, %ymm0, %ymm2
|
||||
; AVX512VL-NEXT: vpandn %ymm2, %ymm3, %ymm2
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm3 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240]
|
||||
; AVX512VL-NEXT: vpternlogq $226, %ymm2, %ymm3, %ymm1
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm2 = [39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39,39]
|
||||
; AVX512VL-NEXT: vpand %ymm2, %ymm1, %ymm1
|
||||
; AVX512VL-NEXT: vpsrlw $4, %ymm0, %ymm4
|
||||
; AVX512VL-NEXT: vpsllw $4, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpand %ymm3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $200, %ymm2, %ymm4, %ymm0
|
||||
; AVX512VL-NEXT: vpternlogq $226, %ymm4, %ymm3, %ymm0
|
||||
; AVX512VL-NEXT: vpand %ymm2, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: splatconstant_rotate_mask_v64i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpsllw $4, %zmm0, %zmm1
|
||||
; AVX512BW-NEXT: vpsrlw $4, %zmm0, %zmm2
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
||||
; AVX512BW-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
||||
; AVX512BW-NEXT: vpsrlw $4, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
||||
; AVX512BW-NEXT: vporq %zmm0, %zmm1, %zmm0
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512VLBW-LABEL: splatconstant_rotate_mask_v64i8:
|
||||
; AVX512VLBW: # %bb.0:
|
||||
; AVX512VLBW-NEXT: vpsllw $4, %zmm0, %zmm1
|
||||
; AVX512VLBW-NEXT: vpsrlw $4, %zmm0, %zmm2
|
||||
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm0
|
||||
; AVX512VLBW-NEXT: vpternlogq $248, {{.*}}(%rip), %zmm2, %zmm0
|
||||
; AVX512VLBW-NEXT: vpsrlw $4, %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; AVX512VLBW-NEXT: vpandq {{.*}}(%rip), %zmm1, %zmm1
|
||||
; AVX512VLBW-NEXT: vporq %zmm0, %zmm1, %zmm0
|
||||
; AVX512VLBW-NEXT: retq
|
||||
%shl = shl <64 x i8> %a, <i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4>
|
||||
%lshr = lshr <64 x i8> %a, <i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4, i8 4>
|
||||
|
|
|
|||
|
|
@ -1443,8 +1443,9 @@ define <16 x i8> @splatconstant_shift_v16i8(<16 x i8> %a) nounwind {
|
|||
; AVX512VL-LABEL: splatconstant_shift_v16i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpsrlw $3, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm1 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
|
||||
; AVX512VL-NEXT: vpternlogq $108, {{.*}}(%rip), %xmm1, %xmm0
|
||||
; AVX512VL-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
|
|||
|
|
@ -946,14 +946,15 @@ define <32 x i8> @splatvar_shift_v32i8(<32 x i8> %a, <32 x i8> %b) nounwind {
|
|||
; AVX512DQVL: # %bb.0:
|
||||
; AVX512DQVL-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512DQVL-NEXT: vpsrlw %xmm1, %ymm0, %ymm0
|
||||
; AVX512DQVL-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
||||
; AVX512DQVL-NEXT: vpsrlw %xmm1, %xmm2, %xmm2
|
||||
; AVX512DQVL-NEXT: vpsrlw $8, %xmm2, %xmm2
|
||||
; AVX512DQVL-NEXT: vpbroadcastb %xmm2, %ymm2
|
||||
; AVX512DQVL-NEXT: vpand %ymm2, %ymm0, %ymm0
|
||||
; AVX512DQVL-NEXT: vmovdqa {{.*#+}} ymm2 = [32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896]
|
||||
; AVX512DQVL-NEXT: vpsrlw %xmm1, %ymm2, %ymm2
|
||||
; AVX512DQVL-NEXT: vpcmpeqd %xmm3, %xmm3, %xmm3
|
||||
; AVX512DQVL-NEXT: vpsrlw %xmm1, %xmm3, %xmm1
|
||||
; AVX512DQVL-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512DQVL-NEXT: vpbroadcastb %xmm1, %ymm1
|
||||
; AVX512DQVL-NEXT: vpternlogq $108, %ymm1, %ymm2, %ymm0
|
||||
; AVX512DQVL-NEXT: vpsubb %ymm2, %ymm0, %ymm0
|
||||
; AVX512DQVL-NEXT: vpsrlw %xmm1, %ymm2, %ymm1
|
||||
; AVX512DQVL-NEXT: vpxor %ymm1, %ymm0, %ymm0
|
||||
; AVX512DQVL-NEXT: vpsubb %ymm1, %ymm0, %ymm0
|
||||
; AVX512DQVL-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: splatvar_shift_v32i8:
|
||||
|
|
@ -1631,8 +1632,9 @@ define <32 x i8> @splatconstant_shift_v32i8(<32 x i8> %a) nounwind {
|
|||
; AVX512VL-LABEL: splatconstant_shift_v32i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpsrlw $3, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm1 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
|
||||
; AVX512VL-NEXT: vpternlogq $108, {{.*}}(%rip), %ymm1, %ymm0
|
||||
; AVX512VL-NEXT: vpxor %ymm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpsubb %ymm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
|
|||
|
|
@ -212,14 +212,15 @@ define <64 x i8> @splatvar_shift_v64i8(<64 x i8> %a, <64 x i8> %b) nounwind {
|
|||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpcmpeqd %xmm2, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm2, %zmm2
|
||||
; AVX512BW-NEXT: vpandq %zmm2, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vmovdqa64 {{.*#+}} zmm2 = [32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896,32896]
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %zmm2, %zmm2
|
||||
; AVX512BW-NEXT: vpcmpeqd %xmm3, %xmm3, %xmm3
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %xmm3, %xmm1
|
||||
; AVX512BW-NEXT: vpsrlw $8, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpbroadcastb %xmm1, %zmm1
|
||||
; AVX512BW-NEXT: vpternlogq $108, %zmm1, %zmm2, %zmm0
|
||||
; AVX512BW-NEXT: vpsubb %zmm2, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpsrlw %xmm1, %zmm2, %zmm1
|
||||
; AVX512BW-NEXT: vpxorq %zmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpsubb %zmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: retq
|
||||
%splat = shufflevector <64 x i8> %b, <64 x i8> undef, <64 x i32> zeroinitializer
|
||||
%shift = ashr <64 x i8> %a, %splat
|
||||
|
|
@ -374,8 +375,9 @@ define <64 x i8> @splatconstant_shift_v64i8(<64 x i8> %a) nounwind {
|
|||
; AVX512BW-LABEL: splatconstant_shift_v64i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpsrlw $3, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpandq {{.*}}(%rip), %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vmovdqa64 {{.*#+}} zmm1 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
|
||||
; AVX512BW-NEXT: vpternlogq $108, {{.*}}(%rip), %zmm1, %zmm0
|
||||
; AVX512BW-NEXT: vpxorq %zmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpsubb %zmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: retq
|
||||
%shift = ashr <64 x i8> %a, <i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3, i8 3>
|
||||
|
|
|
|||
|
|
@ -2354,8 +2354,9 @@ define <8 x i8> @splatconstant_shift_v8i8(<8 x i8> %a) nounwind {
|
|||
; AVX512VL-LABEL: splatconstant_shift_v8i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpsrlw $3, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm1 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
|
||||
; AVX512VL-NEXT: vpternlogq $108, {{.*}}(%rip), %xmm1, %xmm0
|
||||
; AVX512VL-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
@ -2407,8 +2408,9 @@ define <4 x i8> @splatconstant_shift_v4i8(<4 x i8> %a) nounwind {
|
|||
; AVX512VL-LABEL: splatconstant_shift_v4i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpsrlw $3, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm1 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
|
||||
; AVX512VL-NEXT: vpternlogq $108, {{.*}}(%rip), %xmm1, %xmm0
|
||||
; AVX512VL-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
@ -2460,8 +2462,9 @@ define <2 x i8> @splatconstant_shift_v2i8(<2 x i8> %a) nounwind {
|
|||
; AVX512VL-LABEL: splatconstant_shift_v2i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpsrlw $3, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm1 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
|
||||
; AVX512VL-NEXT: vpternlogq $108, {{.*}}(%rip), %xmm1, %xmm0
|
||||
; AVX512VL-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpsubb %xmm1, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
|
|||
Loading…
Reference in New Issue