summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--include/llvm/IntrinsicsX86.td165
-rw-r--r--lib/Target/X86/X86InstrSSE.td517
-rw-r--r--test/CodeGen/X86/avx2-intrinsics-x86.ll384
3 files changed, 920 insertions, 146 deletions
diff --git a/include/llvm/IntrinsicsX86.td b/include/llvm/IntrinsicsX86.td
index 912307b939..0f3c01d57c 100644
--- a/include/llvm/IntrinsicsX86.td
+++ b/include/llvm/IntrinsicsX86.td
@@ -1361,6 +1361,171 @@ let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
}
//===----------------------------------------------------------------------===//
+// AVX2
+
+// Integer arithmetic ops.
+let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
+ def int_x86_avx2_padds_b : GCCBuiltin<"__builtin_ia32_paddsb256">,
+ Intrinsic<[llvm_v32i8_ty], [llvm_v32i8_ty,
+ llvm_v32i8_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_padds_w : GCCBuiltin<"__builtin_ia32_paddsw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_paddus_b : GCCBuiltin<"__builtin_ia32_paddusb256">,
+ Intrinsic<[llvm_v32i8_ty], [llvm_v32i8_ty,
+ llvm_v32i8_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_paddus_w : GCCBuiltin<"__builtin_ia32_paddusw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_psubs_b : GCCBuiltin<"__builtin_ia32_psubsb256">,
+ Intrinsic<[llvm_v32i8_ty], [llvm_v32i8_ty,
+ llvm_v32i8_ty], [IntrNoMem]>;
+ def int_x86_avx2_psubs_w : GCCBuiltin<"__builtin_ia32_psubsw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem]>;
+ def int_x86_avx2_psubus_b : GCCBuiltin<"__builtin_ia32_psubusb256">,
+ Intrinsic<[llvm_v32i8_ty], [llvm_v32i8_ty,
+ llvm_v32i8_ty], [IntrNoMem]>;
+ def int_x86_avx2_psubus_w : GCCBuiltin<"__builtin_ia32_psubusw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem]>;
+ def int_x86_avx2_pmulhu_w : GCCBuiltin<"__builtin_ia32_pmulhuw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pmulh_w : GCCBuiltin<"__builtin_ia32_pmulhw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pmulu_dq : GCCBuiltin<"__builtin_ia32_pmuludq256">,
+ Intrinsic<[llvm_v4i64_ty], [llvm_v8i32_ty,
+ llvm_v8i32_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pmadd_wd : GCCBuiltin<"__builtin_ia32_pmaddwd256">,
+ Intrinsic<[llvm_v8i32_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pavg_b : GCCBuiltin<"__builtin_ia32_pavgb256">,
+ Intrinsic<[llvm_v32i8_ty], [llvm_v32i8_ty,
+ llvm_v32i8_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pavg_w : GCCBuiltin<"__builtin_ia32_pavgw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pmaxu_b : GCCBuiltin<"__builtin_ia32_pmaxub256">,
+ Intrinsic<[llvm_v32i8_ty], [llvm_v32i8_ty,
+ llvm_v32i8_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pmaxs_w : GCCBuiltin<"__builtin_ia32_pmaxsw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pminu_b : GCCBuiltin<"__builtin_ia32_pminub256">,
+ Intrinsic<[llvm_v32i8_ty], [llvm_v32i8_ty,
+ llvm_v32i8_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pmins_w : GCCBuiltin<"__builtin_ia32_pminsw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem, Commutative]>;
+ def int_x86_avx2_psad_bw : GCCBuiltin<"__builtin_ia32_psadbw256">,
+ Intrinsic<[llvm_v4i64_ty], [llvm_v32i8_ty,
+ llvm_v32i8_ty], [IntrNoMem, Commutative]>;
+}
+
+// Integer shift ops.
+let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
+ def int_x86_avx2_psll_w : GCCBuiltin<"__builtin_ia32_psllw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v8i16_ty], [IntrNoMem]>;
+ def int_x86_avx2_psll_d : GCCBuiltin<"__builtin_ia32_pslld256">,
+ Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty,
+ llvm_v4i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_psll_q : GCCBuiltin<"__builtin_ia32_psllq256">,
+ Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty,
+ llvm_v2i64_ty], [IntrNoMem]>;
+ def int_x86_avx2_psrl_w : GCCBuiltin<"__builtin_ia32_psrlw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v8i16_ty], [IntrNoMem]>;
+ def int_x86_avx2_psrl_d : GCCBuiltin<"__builtin_ia32_psrld256">,
+ Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty,
+ llvm_v4i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_psrl_q : GCCBuiltin<"__builtin_ia32_psrlq256">,
+ Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty,
+ llvm_v2i64_ty], [IntrNoMem]>;
+ def int_x86_avx2_psra_w : GCCBuiltin<"__builtin_ia32_psraw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v8i16_ty], [IntrNoMem]>;
+ def int_x86_avx2_psra_d : GCCBuiltin<"__builtin_ia32_psrad256">,
+ Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty,
+ llvm_v4i32_ty], [IntrNoMem]>;
+
+ def int_x86_avx2_pslli_w : GCCBuiltin<"__builtin_ia32_psllwi256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_pslli_d : GCCBuiltin<"__builtin_ia32_pslldi256">,
+ Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_pslli_q : GCCBuiltin<"__builtin_ia32_psllqi256">,
+ Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_psrli_w : GCCBuiltin<"__builtin_ia32_psrlwi256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_psrli_d : GCCBuiltin<"__builtin_ia32_psrldi256">,
+ Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_psrli_q : GCCBuiltin<"__builtin_ia32_psrlqi256">,
+ Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_psrai_w : GCCBuiltin<"__builtin_ia32_psrawi256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_psrai_d : GCCBuiltin<"__builtin_ia32_psradi256">,
+ Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+
+ def int_x86_avx2_psll_dq : GCCBuiltin<"__builtin_ia32_pslldqi256">,
+ Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_psrl_dq : GCCBuiltin<"__builtin_ia32_psrldqi256">,
+ Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_psll_dq_bs : GCCBuiltin<"__builtin_ia32_pslldqi256_byteshift">,
+ Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_psrl_dq_bs : GCCBuiltin<"__builtin_ia32_psrldqi256_byteshift">,
+ Intrinsic<[llvm_v4i64_ty], [llvm_v4i64_ty,
+ llvm_i32_ty], [IntrNoMem]>;
+}
+
+// Integer comparison ops
+let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
+ def int_x86_avx2_pcmpeq_b : GCCBuiltin<"__builtin_ia32_pcmpeqb256">,
+ Intrinsic<[llvm_v32i8_ty], [llvm_v32i8_ty, llvm_v32i8_ty],
+ [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pcmpeq_w : GCCBuiltin<"__builtin_ia32_pcmpeqw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty, llvm_v16i16_ty],
+ [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pcmpeq_d : GCCBuiltin<"__builtin_ia32_pcmpeqd256">,
+ Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty, llvm_v8i32_ty],
+ [IntrNoMem, Commutative]>;
+ def int_x86_avx2_pcmpgt_b : GCCBuiltin<"__builtin_ia32_pcmpgtb256">,
+ Intrinsic<[llvm_v32i8_ty], [llvm_v32i8_ty,
+ llvm_v32i8_ty], [IntrNoMem]>;
+ def int_x86_avx2_pcmpgt_w : GCCBuiltin<"__builtin_ia32_pcmpgtw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem]>;
+ def int_x86_avx2_pcmpgt_d : GCCBuiltin<"__builtin_ia32_pcmpgtd256">,
+ Intrinsic<[llvm_v8i32_ty], [llvm_v8i32_ty,
+ llvm_v8i32_ty], [IntrNoMem]>;
+}
+
+// Pack ops.
+let TargetPrefix = "x86" in { // All intrinsics start with "llvm.x86.".
+ def int_x86_avx2_packsswb : GCCBuiltin<"__builtin_ia32_packsswb256">,
+ Intrinsic<[llvm_v32i8_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem]>;
+ def int_x86_avx2_packssdw : GCCBuiltin<"__builtin_ia32_packssdw256">,
+ Intrinsic<[llvm_v16i16_ty], [llvm_v8i32_ty,
+ llvm_v8i32_ty], [IntrNoMem]>;
+ def int_x86_avx2_packuswb : GCCBuiltin<"__builtin_ia32_packuswb256">,
+ Intrinsic<[llvm_v32i8_ty], [llvm_v16i16_ty,
+ llvm_v16i16_ty], [IntrNoMem]>;
+}
+
+//===----------------------------------------------------------------------===//
// MMX
// Empty MMX state op.
diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index d3ced23450..b5eea45780 100644
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -3343,64 +3343,68 @@ let Predicates = [HasAVX] in {
let ExeDomain = SSEPackedInt in { // SSE integer instructions
multiclass PDI_binop_rm_int<bits<8> opc, string OpcodeStr, Intrinsic IntId,
- bit IsCommutable = 0, bit Is2Addr = 1> {
+ RegisterClass RC, PatFrag memop_frag,
+ X86MemOperand x86memop, bit IsCommutable = 0,
+ bit Is2Addr = 1> {
let isCommutable = IsCommutable in
- def rr : PDI<opc, MRMSrcReg, (outs VR128:$dst),
- (ins VR128:$src1, VR128:$src2),
+ def rr : PDI<opc, MRMSrcReg, (outs RC:$dst),
+ (ins RC:$src1, RC:$src2),
!if(Is2Addr,
!strconcat(OpcodeStr, "\t{$src2, $dst|$dst, $src2}"),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}")),
- [(set VR128:$dst, (IntId VR128:$src1, VR128:$src2))]>;
- def rm : PDI<opc, MRMSrcMem, (outs VR128:$dst),
- (ins VR128:$src1, i128mem:$src2),
+ [(set RC:$dst, (IntId RC:$src1, RC:$src2))]>;
+ def rm : PDI<opc, MRMSrcMem, (outs RC:$dst),
+ (ins RC:$src1, x86memop:$src2),
!if(Is2Addr,
!strconcat(OpcodeStr, "\t{$src2, $dst|$dst, $src2}"),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}")),
- [(set VR128:$dst, (IntId VR128:$src1,
- (bitconvert (memopv2i64 addr:$src2))))]>;
+ [(set RC:$dst, (IntId RC:$src1, (bitconvert (memop_frag addr:$src2))))]>;
}
multiclass PDI_binop_rmi_int<bits<8> opc, bits<8> opc2, Format ImmForm,
string OpcodeStr, Intrinsic IntId,
- Intrinsic IntId2, bit Is2Addr = 1> {
- def rr : PDI<opc, MRMSrcReg, (outs VR128:$dst),
- (ins VR128:$src1, VR128:$src2),
+ Intrinsic IntId2, RegisterClass RC,
+ bit Is2Addr = 1> {
+ // src2 is always 128-bit
+ def rr : PDI<opc, MRMSrcReg, (outs RC:$dst),
+ (ins RC:$src1, VR128:$src2),
!if(Is2Addr,
!strconcat(OpcodeStr, "\t{$src2, $dst|$dst, $src2}"),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}")),
- [(set VR128:$dst, (IntId VR128:$src1, VR128:$src2))]>;
- def rm : PDI<opc, MRMSrcMem, (outs VR128:$dst),
- (ins VR128:$src1, i128mem:$src2),
+ [(set RC:$dst, (IntId RC:$src1, VR128:$src2))]>;
+ def rm : PDI<opc, MRMSrcMem, (outs RC:$dst),
+ (ins RC:$src1, i128mem:$src2),
!if(Is2Addr,
!strconcat(OpcodeStr, "\t{$src2, $dst|$dst, $src2}"),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}")),
- [(set VR128:$dst, (IntId VR128:$src1,
- (bitconvert (memopv2i64 addr:$src2))))]>;
- def ri : PDIi8<opc2, ImmForm, (outs VR128:$dst),
- (ins VR128:$src1, i32i8imm:$src2),
+ [(set RC:$dst, (IntId RC:$src1, (bitconvert (memopv2i64 addr:$src2))))]>;
+ def ri : PDIi8<opc2, ImmForm, (outs RC:$dst),
+ (ins RC:$src1, i32i8imm:$src2),
!if(Is2Addr,
!strconcat(OpcodeStr, "\t{$src2, $dst|$dst, $src2}"),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}")),
- [(set VR128:$dst, (IntId2 VR128:$src1, (i32 imm:$src2)))]>;
+ [(set RC:$dst, (IntId2 RC:$src1, (i32 imm:$src2)))]>;
}
/// PDI_binop_rm - Simple SSE2 binary operator.
multiclass PDI_binop_rm<bits<8> opc, string OpcodeStr, SDNode OpNode,
- ValueType OpVT, bit IsCommutable = 0, bit Is2Addr = 1> {
+ ValueType OpVT, RegisterClass RC, PatFrag memop_frag,
+ X86MemOperand x86memop, bit IsCommutable = 0,
+ bit Is2Addr = 1> {
let isCommutable = IsCommutable in
- def rr : PDI<opc, MRMSrcReg, (outs VR128:$dst),
- (ins VR128:$src1, VR128:$src2),
+ def rr : PDI<opc, MRMSrcReg, (outs RC:$dst),
+ (ins RC:$src1, RC:$src2),
!if(Is2Addr,
!strconcat(OpcodeStr, "\t{$src2, $dst|$dst, $src2}"),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}")),
- [(set VR128:$dst, (OpVT (OpNode VR128:$src1, VR128:$src2)))]>;
- def rm : PDI<opc, MRMSrcMem, (outs VR128:$dst),
- (ins VR128:$src1, i128mem:$src2),
+ [(set RC:$dst, (OpVT (OpNode RC:$src1, RC:$src2)))]>;
+ def rm : PDI<opc, MRMSrcMem, (outs RC:$dst),
+ (ins RC:$src1, x86memop:$src2),
!if(Is2Addr,
!strconcat(OpcodeStr, "\t{$src2, $dst|$dst, $src2}"),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}")),
- [(set VR128:$dst, (OpVT (OpNode VR128:$src1,
- (bitconvert (memopv2i64 addr:$src2)))))]>;
+ [(set RC:$dst, (OpVT (OpNode RC:$src1,
+ (bitconvert (memop_frag addr:$src2)))))]>;
}
/// PDI_binop_rm_v2i64 - Simple SSE2 binary operator whose type is v2i64.
@@ -3425,93 +3429,203 @@ multiclass PDI_binop_rm_v2i64<bits<8> opc, string OpcodeStr, SDNode OpNode,
[(set VR128:$dst, (OpNode VR128:$src1, (memopv2i64 addr:$src2)))]>;
}
+/// PDI_binop_rm_v4i64 - Simple AVX2 binary operator whose type is v4i64.
+///
+/// FIXME: we could eliminate this and use PDI_binop_rm instead if tblgen knew
+/// to collapse (bitconvert VT to VT) into its operand.
+///
+multiclass PDI_binop_rm_v4i64<bits<8> opc, string OpcodeStr, SDNode OpNode,
+ bit IsCommutable = 0> {
+ let isCommutable = IsCommutable in
+ def rr : PDI<opc, MRMSrcReg, (outs VR256:$dst),
+ (ins VR256:$src1, VR256:$src2),
+ !strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
+ [(set VR256:$dst, (v4i64 (OpNode VR256:$src1, VR256:$src2)))]>;
+ def rm : PDI<opc, MRMSrcMem, (outs VR256:$dst),
+ (ins VR256:$src1, i256mem:$src2),
+ !strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
+ [(set VR256:$dst, (OpNode VR256:$src1, (memopv4i64 addr:$src2)))]>;
+}
+
} // ExeDomain = SSEPackedInt
// 128-bit Integer Arithmetic
let Predicates = [HasAVX] in {
-defm VPADDB : PDI_binop_rm<0xFC, "vpaddb", add, v16i8, 1, 0 /*3addr*/>, VEX_4V;
-defm VPADDW : PDI_binop_rm<0xFD, "vpaddw", add, v8i16, 1, 0>, VEX_4V;
-defm VPADDD : PDI_binop_rm<0xFE, "vpaddd", add, v4i32, 1, 0>, VEX_4V;
+defm VPADDB : PDI_binop_rm<0xFC, "vpaddb", add, v16i8, VR128, memopv2i64,
+ i128mem, 1, 0 /*3addr*/>, VEX_4V;
+defm VPADDW : PDI_binop_rm<0xFD, "vpaddw", add, v8i16, VR128, memopv2i64,
+ i128mem, 1, 0>, VEX_4V;
+defm VPADDD : PDI_binop_rm<0xFE, "vpaddd", add, v4i32, VR128, memopv2i64,
+ i128mem, 1, 0>, VEX_4V;
defm VPADDQ : PDI_binop_rm_v2i64<0xD4, "vpaddq", add, 1, 0>, VEX_4V;
-defm VPMULLW : PDI_binop_rm<0xD5, "vpmullw", mul, v8i16, 1, 0>, VEX_4V;
-defm VPSUBB : PDI_binop_rm<0xF8, "vpsubb", sub, v16i8, 0, 0>, VEX_4V;
-defm VPSUBW : PDI_binop_rm<0xF9, "vpsubw", sub, v8i16, 0, 0>, VEX_4V;
-defm VPSUBD : PDI_binop_rm<0xFA, "vpsubd", sub, v4i32, 0, 0>, VEX_4V;
+defm VPMULLW : PDI_binop_rm<0xD5, "vpmullw", mul, v8i16, VR128, memopv2i64,
+ i128mem, 1, 0>, VEX_4V;
+defm VPSUBB : PDI_binop_rm<0xF8, "vpsubb", sub, v16i8, VR128, memopv2i64,
+ i128mem, 0, 0>, VEX_4V;
+defm VPSUBW : PDI_binop_rm<0xF9, "vpsubw", sub, v8i16, VR128, memopv2i64,
+ i128mem, 0, 0>, VEX_4V;
+defm VPSUBD : PDI_binop_rm<0xFA, "vpsubd", sub, v4i32, VR128, memopv2i64,
+ i128mem, 0, 0>, VEX_4V;
defm VPSUBQ : PDI_binop_rm_v2i64<0xFB, "vpsubq", sub, 0, 0>, VEX_4V;
// Intrinsic forms
-defm VPSUBSB : PDI_binop_rm_int<0xE8, "vpsubsb" , int_x86_sse2_psubs_b, 0, 0>,
- VEX_4V;
-defm VPSUBSW : PDI_binop_rm_int<0xE9, "vpsubsw" , int_x86_sse2_psubs_w, 0, 0>,
- VEX_4V;
-defm VPSUBUSB : PDI_binop_rm_int<0xD8, "vpsubusb", int_x86_sse2_psubus_b, 0, 0>,
- VEX_4V;
-defm VPSUBUSW : PDI_binop_rm_int<0xD9, "vpsubusw", int_x86_sse2_psubus_w, 0, 0>,
- VEX_4V;
-defm VPADDSB : PDI_binop_rm_int<0xEC, "vpaddsb" , int_x86_sse2_padds_b, 1, 0>,
- VEX_4V;
-defm VPADDSW : PDI_binop_rm_int<0xED, "vpaddsw" , int_x86_sse2_padds_w, 1, 0>,
- VEX_4V;
-defm VPADDUSB : PDI_binop_rm_int<0xDC, "vpaddusb", int_x86_sse2_paddus_b, 1, 0>,
- VEX_4V;
-defm VPADDUSW : PDI_binop_rm_int<0xDD, "vpaddusw", int_x86_sse2_paddus_w, 1, 0>,
- VEX_4V;
-defm VPMULHUW : PDI_binop_rm_int<0xE4, "vpmulhuw", int_x86_sse2_pmulhu_w, 1, 0>,
- VEX_4V;
-defm VPMULHW : PDI_binop_rm_int<0xE5, "vpmulhw" , int_x86_sse2_pmulh_w, 1, 0>,
- VEX_4V;
-defm VPMULUDQ : PDI_binop_rm_int<0xF4, "vpmuludq", int_x86_sse2_pmulu_dq, 1, 0>,
- VEX_4V;
-defm VPMADDWD : PDI_binop_rm_int<0xF5, "vpmaddwd", int_x86_sse2_pmadd_wd, 1, 0>,
- VEX_4V;
-defm VPAVGB : PDI_binop_rm_int<0xE0, "vpavgb", int_x86_sse2_pavg_b, 1, 0>,
- VEX_4V;
-defm VPAVGW : PDI_binop_rm_int<0xE3, "vpavgw", int_x86_sse2_pavg_w, 1, 0>,
- VEX_4V;
-defm VPMINUB : PDI_binop_rm_int<0xDA, "vpminub", int_x86_sse2_pminu_b, 1, 0>,
- VEX_4V;
-defm VPMINSW : PDI_binop_rm_int<0xEA, "vpminsw", int_x86_sse2_pmins_w, 1, 0>,
- VEX_4V;
-defm VPMAXUB : PDI_binop_rm_int<0xDE, "vpmaxub", int_x86_sse2_pmaxu_b, 1, 0>,
- VEX_4V;
-defm VPMAXSW : PDI_binop_rm_int<0xEE, "vpmaxsw", int_x86_sse2_pmaxs_w, 1, 0>,
- VEX_4V;
-defm VPSADBW : PDI_binop_rm_int<0xF6, "vpsadbw", int_x86_sse2_psad_bw, 1, 0>,
- VEX_4V;
+defm VPSUBSB : PDI_binop_rm_int<0xE8, "vpsubsb" , int_x86_sse2_psubs_b,
+ VR128, memopv2i64, i128mem, 0, 0>, VEX_4V;
+defm VPSUBSW : PDI_binop_rm_int<0xE9, "vpsubsw" , int_x86_sse2_psubs_w,
+ VR128, memopv2i64, i128mem, 0, 0>, VEX_4V;
+defm VPSUBUSB : PDI_binop_rm_int<0xD8, "vpsubusb", int_x86_sse2_psubus_b,
+ VR128, memopv2i64, i128mem, 0, 0>, VEX_4V;
+defm VPSUBUSW : PDI_binop_rm_int<0xD9, "vpsubusw", int_x86_sse2_psubus_w,
+ VR128, memopv2i64, i128mem, 0, 0>, VEX_4V;
+defm VPADDSB : PDI_binop_rm_int<0xEC, "vpaddsb" , int_x86_sse2_padds_b,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPADDSW : PDI_binop_rm_int<0xED, "vpaddsw" , int_x86_sse2_padds_w,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPADDUSB : PDI_binop_rm_int<0xDC, "vpaddusb", int_x86_sse2_paddus_b,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPADDUSW : PDI_binop_rm_int<0xDD, "vpaddusw", int_x86_sse2_paddus_w,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPMULHUW : PDI_binop_rm_int<0xE4, "vpmulhuw", int_x86_sse2_pmulhu_w,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPMULHW : PDI_binop_rm_int<0xE5, "vpmulhw" , int_x86_sse2_pmulh_w,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPMULUDQ : PDI_binop_rm_int<0xF4, "vpmuludq", int_x86_sse2_pmulu_dq,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPMADDWD : PDI_binop_rm_int<0xF5, "vpmaddwd", int_x86_sse2_pmadd_wd,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPAVGB : PDI_binop_rm_int<0xE0, "vpavgb", int_x86_sse2_pavg_b,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPAVGW : PDI_binop_rm_int<0xE3, "vpavgw", int_x86_sse2_pavg_w,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPMINUB : PDI_binop_rm_int<0xDA, "vpminub", int_x86_sse2_pminu_b,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPMINSW : PDI_binop_rm_int<0xEA, "vpminsw", int_x86_sse2_pmins_w,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPMAXUB : PDI_binop_rm_int<0xDE, "vpmaxub", int_x86_sse2_pmaxu_b,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPMAXSW : PDI_binop_rm_int<0xEE, "vpmaxsw", int_x86_sse2_pmaxs_w,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+defm VPSADBW : PDI_binop_rm_int<0xF6, "vpsadbw", int_x86_sse2_psad_bw,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+}
+
+let Predicates = [HasAVX2] in {
+defm VPADDBY : PDI_binop_rm<0xFC, "vpaddb", add, v32i8, VR256, memopv4i64,
+ i256mem, 1, 0>, VEX_4V;
+defm VPADDWY : PDI_binop_rm<0xFD, "vpaddw", add, v16i16, VR256, memopv4i64,
+ i256mem, 1, 0>, VEX_4V;
+defm VPADDDY : PDI_binop_rm<0xFE, "vpaddd", add, v8i32, VR256, memopv4i64,
+ i256mem, 1, 0>, VEX_4V;
+defm VPADDQY : PDI_binop_rm_v4i64<0xD4, "vpaddq", add, 1>, VEX_4V;
+defm VPMULLWY : PDI_binop_rm<0xD5, "vpmullw", mul, v16i16, VR256, memopv4i64,
+ i256mem, 1, 0>, VEX_4V;
+defm VPSUBBY : PDI_binop_rm<0xF8, "vpsubb", sub, v32i8, VR256, memopv4i64,
+ i256mem, 0, 0>, VEX_4V;
+defm VPSUBWY : PDI_binop_rm<0xF9, "vpsubw", sub, v16i16,VR256, memopv4i64,
+ i256mem, 0, 0>, VEX_4V;
+defm VPSUBDY : PDI_binop_rm<0xFA, "vpsubd", sub, v8i32, VR256, memopv4i64,
+ i256mem, 0, 0>, VEX_4V;
+defm VPSUBQY : PDI_binop_rm_v4i64<0xFB, "vpsubq", sub, 0>, VEX_4V;
+
+// Intrinsic forms
+defm VPSUBSBY : PDI_binop_rm_int<0xE8, "vpsubsb" , int_x86_avx2_psubs_b,
+ VR256, memopv4i64, i256mem, 0, 0>, VEX_4V;
+defm VPSUBSWY : PDI_binop_rm_int<0xE9, "vpsubsw" , int_x86_avx2_psubs_w,
+ VR256, memopv4i64, i256mem, 0, 0>, VEX_4V;
+defm VPSUBUSBY : PDI_binop_rm_int<0xD8, "vpsubusb", int_x86_avx2_psubus_b,
+ VR256, memopv4i64, i256mem, 0, 0>, VEX_4V;
+defm VPSUBUSWY : PDI_binop_rm_int<0xD9, "vpsubusw", int_x86_avx2_psubus_w,
+ VR256, memopv4i64, i256mem, 0, 0>, VEX_4V;
+defm VPADDSBY : PDI_binop_rm_int<0xEC, "vpaddsb" , int_x86_avx2_padds_b,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPADDSWY : PDI_binop_rm_int<0xED, "vpaddsw" , int_x86_avx2_padds_w,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPADDUSBY : PDI_binop_rm_int<0xDC, "vpaddusb", int_x86_avx2_paddus_b,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPADDUSWY : PDI_binop_rm_int<0xDD, "vpaddusw", int_x86_avx2_paddus_w,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPMULHUWY : PDI_binop_rm_int<0xE4, "vpmulhuw", int_x86_avx2_pmulhu_w,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPMULHWY : PDI_binop_rm_int<0xE5, "vpmulhw" , int_x86_avx2_pmulh_w,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPMULUDQY : PDI_binop_rm_int<0xF4, "vpmuludq", int_x86_avx2_pmulu_dq,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPMADDWDY : PDI_binop_rm_int<0xF5, "vpmaddwd", int_x86_avx2_pmadd_wd,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPAVGBY : PDI_binop_rm_int<0xE0, "vpavgb", int_x86_avx2_pavg_b,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPAVGWY : PDI_binop_rm_int<0xE3, "vpavgw", int_x86_avx2_pavg_w,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPMINUBY : PDI_binop_rm_int<0xDA, "vpminub", int_x86_avx2_pminu_b,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPMINSWY : PDI_binop_rm_int<0xEA, "vpminsw", int_x86_avx2_pmins_w,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPMAXUBY : PDI_binop_rm_int<0xDE, "vpmaxub", int_x86_avx2_pmaxu_b,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPMAXSWY : PDI_binop_rm_int<0xEE, "vpmaxsw", int_x86_avx2_pmaxs_w,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+defm VPSADBWY : PDI_binop_rm_int<0xF6, "vpsadbw", int_x86_avx2_psad_bw,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
}
let Constraints = "$src1 = $dst" in {
-defm PADDB : PDI_binop_rm<0xFC, "paddb", add, v16i8, 1>;
-defm PADDW : PDI_binop_rm<0xFD, "paddw", add, v8i16, 1>;
-defm PADDD : PDI_binop_rm<0xFE, "paddd", add, v4i32, 1>;
+defm PADDB : PDI_binop_rm<0xFC, "paddb", add, v16i8, VR128, memopv2i64,
+ i128mem, 1>;
+defm PADDW : PDI_binop_rm<0xFD, "paddw", add, v8i16, VR128, memopv2i64,
+ i128mem, 1>;
+defm PADDD : PDI_binop_rm<0xFE, "paddd", add, v4i32, VR128, memopv2i64,
+ i128mem, 1>;
defm PADDQ : PDI_binop_rm_v2i64<0xD4, "paddq", add, 1>;
-defm PMULLW : PDI_binop_rm<0xD5, "pmullw", mul, v8i16, 1>;
-defm PSUBB : PDI_binop_rm<0xF8, "psubb", sub, v16i8>;
-defm PSUBW : PDI_binop_rm<0xF9, "psubw", sub, v8i16>;
-defm PSUBD : PDI_binop_rm<0xFA, "psubd", sub, v4i32>;
+defm PMULLW : PDI_binop_rm<0xD5, "pmullw", mul, v8i16, VR128, memopv2i64,
+ i128mem, 1>;
+defm PSUBB : PDI_binop_rm<0xF8, "psubb", sub, v16i8, VR128, memopv2i64,
+ i128mem>;
+defm PSUBW : PDI_binop_rm<0xF9, "psubw", sub, v8i16, VR128, memopv2i64,
+ i128mem>;
+defm PSUBD : PDI_binop_rm<0xFA, "psubd", sub, v4i32, VR128, memopv2i64,
+ i128mem>;
defm PSUBQ : PDI_binop_rm_v2i64<0xFB, "psubq", sub>;
// Intrinsic forms
-defm PSUBSB : PDI_binop_rm_int<0xE8, "psubsb" , int_x86_sse2_psubs_b>;
-defm PSUBSW : PDI_binop_rm_int<0xE9, "psubsw" , int_x86_sse2_psubs_w>;
-defm PSUBUSB : PDI_binop_rm_int<0xD8, "psubusb", int_x86_sse2_psubus_b>;
-defm PSUBUSW : PDI_binop_rm_int<0xD9, "psubusw", int_x86_sse2_psubus_w>;
-defm PADDSB : PDI_binop_rm_int<0xEC, "paddsb" , int_x86_sse2_padds_b, 1>;
-defm PADDSW : PDI_binop_rm_int<0xED, "paddsw" , int_x86_sse2_padds_w, 1>;
-defm PADDUSB : PDI_binop_rm_int<0xDC, "paddusb", int_x86_sse2_paddus_b, 1>;
-defm PADDUSW : PDI_binop_rm_int<0xDD, "paddusw", int_x86_sse2_paddus_w, 1>;
-defm PMULHUW : PDI_binop_rm_int<0xE4, "pmulhuw", int_x86_sse2_pmulhu_w, 1>;
-defm PMULHW : PDI_binop_rm_int<0xE5, "pmulhw" , int_x86_sse2_pmulh_w, 1>;
-defm PMULUDQ : PDI_binop_rm_int<0xF4, "pmuludq", int_x86_sse2_pmulu_dq, 1>;
-defm PMADDWD : PDI_binop_rm_int<0xF5, "pmaddwd", int_x86_sse2_pmadd_wd, 1>;
-defm PAVGB : PDI_binop_rm_int<0xE0, "pavgb", int_x86_sse2_pavg_b, 1>;
-defm PAVGW : PDI_binop_rm_int<0xE3, "pavgw", int_x86_sse2_pavg_w, 1>;
-defm PMINUB : PDI_binop_rm_int<0xDA, "pminub", int_x86_sse2_pminu_b, 1>;
-defm PMINSW : PDI_binop_rm_int<0xEA, "pminsw", int_x86_sse2_pmins_w, 1>;
-defm PMAXUB : PDI_binop_rm_int<0xDE, "pmaxub", int_x86_sse2_pmaxu_b, 1>;
-defm PMAXSW : PDI_binop_rm_int<0xEE, "pmaxsw", int_x86_sse2_pmaxs_w, 1>;
-defm PSADBW : PDI_binop_rm_int<0xF6, "psadbw", int_x86_sse2_psad_bw, 1>;
+defm PSUBSB : PDI_binop_rm_int<0xE8, "psubsb" , int_x86_sse2_psubs_b,
+ VR128, memopv2i64, i128mem>;
+defm PSUBSW : PDI_binop_rm_int<0xE9, "psubsw" , int_x86_sse2_psubs_w,
+ VR128, memopv2i64, i128mem>;
+defm PSUBUSB : PDI_binop_rm_int<0xD8, "psubusb", int_x86_sse2_psubus_b,
+ VR128, memopv2i64, i128mem>;
+defm PSUBUSW : PDI_binop_rm_int<0xD9, "psubusw", int_x86_sse2_psubus_w,
+ VR128, memopv2i64, i128mem>;
+defm PADDSB : PDI_binop_rm_int<0xEC, "paddsb" , int_x86_sse2_padds_b,
+ VR128, memopv2i64, i128mem, 1>;
+defm PADDSW : PDI_binop_rm_int<0xED, "paddsw" , int_x86_sse2_padds_w,
+ VR128, memopv2i64, i128mem, 1>;
+defm PADDUSB : PDI_binop_rm_int<0xDC, "paddusb", int_x86_sse2_paddus_b,
+ VR128, memopv2i64, i128mem, 1>;
+defm PADDUSW : PDI_binop_rm_int<0xDD, "paddusw", int_x86_sse2_paddus_w,
+ VR128, memopv2i64, i128mem, 1>;
+defm PMULHUW : PDI_binop_rm_int<0xE4, "pmulhuw", int_x86_sse2_pmulhu_w,
+ VR128, memopv2i64, i128mem, 1>;
+defm PMULHW : PDI_binop_rm_int<0xE5, "pmulhw" , int_x86_sse2_pmulh_w,
+ VR128, memopv2i64, i128mem, 1>;
+defm PMULUDQ : PDI_binop_rm_int<0xF4, "pmuludq", int_x86_sse2_pmulu_dq,
+ VR128, memopv2i64, i128mem, 1>;
+defm PMADDWD : PDI_binop_rm_int<0xF5, "pmaddwd", int_x86_sse2_pmadd_wd,
+ VR128, memopv2i64, i128mem, 1>;
+defm PAVGB : PDI_binop_rm_int<0xE0, "pavgb", int_x86_sse2_pavg_b,
+ VR128, memopv2i64, i128mem, 1>;
+defm PAVGW : PDI_binop_rm_int<0xE3, "pavgw", int_x86_sse2_pavg_w,
+ VR128, memopv2i64, i128mem, 1>;
+defm PMINUB : PDI_binop_rm_int<0xDA, "pminub", int_x86_sse2_pminu_b,
+ VR128, memopv2i64, i128mem, 1>;
+defm PMINSW : PDI_binop_rm_int<0xEA, "pminsw", int_x86_sse2_pmins_w,
+ VR128, memopv2i64, i128mem, 1>;
+defm PMAXUB : PDI_binop_rm_int<0xDE, "pmaxub", int_x86_sse2_pmaxu_b,
+ VR128, memopv2i64, i128mem, 1>;
+defm PMAXSW : PDI_binop_rm_int<0xEE, "pmaxsw", int_x86_sse2_pmaxs_w,
+ VR128, memopv2i64, i128mem, 1>;
+defm PSADBW : PDI_binop_rm_int<0xF6, "psadbw", int_x86_sse2_psad_bw,
+ VR128, memopv2i64, i128mem, 1>;
} // Constraints = "$src1 = $dst"
@@ -3521,31 +3635,31 @@ defm PSADBW : PDI_binop_rm_int<0xF6, "psadbw", int_x86_sse2_psad_bw, 1>;
let Predicates = [HasAVX] in {
defm VPSLLW : PDI_binop_rmi_int<0xF1, 0x71, MRM6r, "vpsllw",
- int_x86_sse2_psll_w, int_x86_sse2_pslli_w, 0>,
- VEX_4V;
+ int_x86_sse2_psll_w, int_x86_sse2_pslli_w,
+ VR128, 0>, VEX_4V;
defm VPSLLD : PDI_binop_rmi_int<0xF2, 0x72, MRM6r, "vpslld",
- int_x86_sse2_psll_d, int_x86_sse2_pslli_d, 0>,
- VEX_4V;
+ int_x86_sse2_psll_d, int_x86_sse2_pslli_d,
+ VR128, 0>, VEX_4V;
defm VPSLLQ : PDI_binop_rmi_int<0xF3, 0x73, MRM6r, "vpsllq",
- int_x86_sse2_psll_q, int_x86_sse2_pslli_q, 0>,
- VEX_4V;
+ int_x86_sse2_psll_q, int_x86_sse2_pslli_q,
+ VR128, 0>, VEX_4V;
defm VPSRLW : PDI_binop_rmi_int<0xD1, 0x71, MRM2r, "vpsrlw",
- int_x86_sse2_psrl_w, int_x86_sse2_psrli_w, 0>,
- VEX_4V;
+ int_x86_sse2_psrl_w, int_x86_sse2_psrli_w,
+ VR128, 0>, VEX_4V;
defm VPSRLD : PDI_binop_rmi_int<0xD2, 0x72, MRM2r, "vpsrld",
- int_x86_sse2_psrl_d, int_x86_sse2_psrli_d, 0>,
- VEX_4V;
+ int_x86_sse2_psrl_d, int_x86_sse2_psrli_d,
+ VR128, 0>, VEX_4V;
defm VPSRLQ : PDI_binop_rmi_int<0xD3, 0x73, MRM2r, "vpsrlq",
- int_x86_sse2_psrl_q, int_x86_sse2_psrli_q, 0>,
- VEX_4V;
+ int_x86_sse2_psrl_q, int_x86_sse2_psrli_q,
+ VR128, 0>, VEX_4V;
defm VPSRAW : PDI_binop_rmi_int<0xE1, 0x71, MRM4r, "vpsraw",
- int_x86_sse2_psra_w, int_x86_sse2_psrai_w, 0>,
- VEX_4V;
+ int_x86_sse2_psra_w, int_x86_sse2_psrai_w,
+ VR128, 0>, VEX_4V;
defm VPSRAD : PDI_binop_rmi_int<0xE2, 0x72, MRM4r, "vpsrad",
- int_x86_sse2_psra_d, int_x86_sse2_psrai_d, 0>,
- VEX_4V;
+ int_x86_sse2_psra_d, int_x86_sse2_psrai_d,
+ VR128, 0>, VEX_4V;
defm VPAND : PDI_binop_rm_v2i64<0xDB, "vpand", and, 1, 0>, VEX_4V;
defm VPOR : PDI_binop_rm_v2i64<0xEB, "vpor" , or, 1, 0>, VEX_4V;
@@ -3578,25 +3692,92 @@ let ExeDomain = SSEPackedInt in {
}
}
+let Predicates = [HasAVX2] in {
+defm VPSLLWY : PDI_binop_rmi_int<0xF1, 0x71, MRM6r, "vpsllw",
+ int_x86_avx2_psll_w, int_x86_avx2_pslli_w,
+ VR256, 0>, VEX_4V;
+defm VPSLLDY : PDI_binop_rmi_int<0xF2, 0x72, MRM6r, "vpslld",
+ int_x86_avx2_psll_d, int_x86_avx2_pslli_d,
+ VR256, 0>, VEX_4V;
+defm VPSLLQY : PDI_binop_rmi_int<0xF3, 0x73, MRM6r, "vpsllq",
+ int_x86_avx2_psll_q, int_x86_avx2_pslli_q,
+ VR256, 0>, VEX_4V;
+
+defm VPSRLWY : PDI_binop_rmi_int<0xD1, 0x71, MRM2r, "vpsrlw",
+ int_x86_avx2_psrl_w, int_x86_avx2_psrli_w,
+ VR256, 0>, VEX_4V;
+defm VPSRLDY : PDI_binop_rmi_int<0xD2, 0x72, MRM2r, "vpsrld",
+ int_x86_avx2_psrl_d, int_x86_avx2_psrli_d,
+ VR256, 0>, VEX_4V;
+defm VPSRLQY : PDI_binop_rmi_int<0xD3, 0x73, MRM2r, "vpsrlq",
+ int_x86_avx2_psrl_q, int_x86_avx2_psrli_q,
+ VR256, 0>, VEX_4V;
+
+defm VPSRAWY : PDI_binop_rmi_int<0xE1, 0x71, MRM4r, "vpsraw",
+ int_x86_avx2_psra_w, int_x86_avx2_psrai_w,
+ VR256, 0>, VEX_4V;
+defm VPSRADY : PDI_binop_rmi_int<0xE2, 0x72, MRM4r, "vpsrad",
+ int_x86_avx2_psra_d, int_x86_avx2_psrai_d,
+ VR256, 0>, VEX_4V;
+
+defm VPANDY : PDI_binop_rm_v4i64<0xDB, "vpand", and, 1>, VEX_4V;
+defm VPORY : PDI_binop_rm_v4i64<0xEB, "vpor" , or, 1>, VEX_4V;
+defm VPXORY : PDI_binop_rm_v4i64<0xEF, "vpxor", xor, 1>, VEX_4V;
+
+let ExeDomain = SSEPackedInt in {
+ let neverHasSideEffects = 1 in {
+ // 128-bit logical shifts.
+ def VPSLLDQYri : PDIi8<0x73, MRM7r,
+ (outs VR256:$dst), (ins VR256:$src1, i32i8imm:$src2),
+ "vpslldq\t{$src2, $src1, $dst|$dst, $src1, $src2}", []>,
+ VEX_4V;
+ def VPSRLDQYri : PDIi8<0x73, MRM3r,
+ (outs VR256:$dst), (ins VR256:$src1, i32i8imm:$src2),
+ "vpsrldq\t{$src2, $src1, $dst|$dst, $src1, $src2}", []>,
+ VEX_4V;
+ // PSRADQYri doesn't exist in SSE[1-3].
+ }
+ def VPANDNYrr : PDI<0xDF, MRMSrcReg,
+ (outs VR256:$dst), (ins VR256:$src1, VR256:$src2),
+ "vpandn\t{$src2, $src1, $dst|$dst, $src1, $src2}",
+ [(set VR256:$dst,
+ (v4i64 (X86andnp VR256:$src1, VR256:$src2)))]>,VEX_4V;
+
+ def VPANDNYrm : PDI<0xDF, MRMSrcMem,
+ (outs VR256:$dst), (ins VR256:$src1, i256mem:$src2),
+ "vpandn\t{$src2, $src1, $dst|$dst, $src1, $src2}",
+ [(set VR256:$dst, (X86andnp VR256:$src1,
+ (memopv4i64 addr:$src2)))]>, VEX_4V;
+}
+}
+
let Constraints = "$src1 = $dst" in {
defm PSLLW : PDI_binop_rmi_int<0xF1, 0x71, MRM6r, "psllw",
- int_x86_sse2_psll_w, int_x86_sse2_pslli_w>;
+ int_x86_sse2_psll_w, int_x86_sse2_pslli_w,
+ VR128>;
defm PSLLD : PDI_binop_rmi_int<0xF2, 0x72, MRM6r, "pslld",
- int_x86_sse2_psll_d, int_x86_sse2_pslli_d>;
+ int_x86_sse2_psll_d, int_x86_sse2_pslli_d,
+ VR128>;
defm PSLLQ : PDI_binop_rmi_int<0xF3, 0x73, MRM6r, "psllq",
- int_x86_sse2_psll_q, int_x86_sse2_pslli_q>;
+ int_x86_sse2_psll_q, int_x86_sse2_pslli_q,
+ VR128>;
defm PSRLW : PDI_binop_rmi_int<0xD1, 0x71, MRM2r, "psrlw",
- int_x86_sse2_psrl_w, int_x86_sse2_psrli_w>;
+ int_x86_sse2_psrl_w, int_x86_sse2_psrli_w,
+ VR128>;
defm PSRLD : PDI_binop_rmi_int<0xD2, 0x72, MRM2r, "psrld",
- int_x86_sse2_psrl_d, int_x86_sse2_psrli_d>;
+ int_x86_sse2_psrl_d, int_x86_sse2_psrli_d,
+ VR128>;
defm PSRLQ : PDI_binop_rmi_int<0xD3, 0x73, MRM2r, "psrlq",
- int_x86_sse2_psrl_q, int_x86_sse2_psrli_q>;
+ int_x86_sse2_psrl_q, int_x86_sse2_psrli_q,
+ VR128>;
defm PSRAW : PDI_binop_rmi_int<0xE1, 0x71, MRM4r, "psraw",
- int_x86_sse2_psra_w, int_x86_sse2_psrai_w>;
+ int_x86_sse2_psra_w, int_x86_sse2_psrai_w,
+ VR128>;
defm PSRAD : PDI_binop_rmi_int<0xE2, 0x72, MRM4r, "psrad",
- int_x86_sse2_psra_d, int_x86_sse2_psrai_d>;
+ int_x86_sse2_psra_d, int_x86_sse2_psrai_d,
+ VR128>;
defm PAND : PDI_binop_rm_v2i64<0xDB, "pand", and, 1>;
defm POR : PDI_binop_rm_v2i64<0xEB, "por" , or, 1>;
@@ -3642,6 +3823,17 @@ let Predicates = [HasAVX] in {
(v2i64 (VPSRLDQri VR128:$src, (BYTE_imm imm:$amt)))>;
}
+let Predicates = [HasAVX2] in {
+ def : Pat<(int_x86_avx2_psll_dq VR256:$src1, imm:$src2),
+ (v4i64 (VPSLLDQYri VR256:$src1, (BYTE_imm imm:$src2)))>;
+ def : Pat<(int_x86_avx2_psrl_dq VR256:$src1, imm:$src2),
+ (v4i64 (VPSRLDQYri VR256:$src1, (BYTE_imm imm:$src2)))>;
+ def : Pat<(int_x86_avx2_psll_dq_bs VR256:$src1, imm:$src2),
+ (v4i64 (VPSLLDQYri VR256:$src1, imm:$src2))>;
+ def : Pat<(int_x86_avx2_psrl_dq_bs VR256:$src1, imm:$src2),
+ (v4i64 (VPSRLDQYri VR256:$src1, imm:$src2))>;
+}
+
let Predicates = [HasSSE2] in {
def : Pat<(int_x86_sse2_psll_dq VR128:$src1, imm:$src2),
(v2i64 (PSLLDQri VR128:$src1, (BYTE_imm imm:$src2)))>;
@@ -3666,18 +3858,18 @@ let Predicates = [HasSSE2] in {
//===---------------------------------------------------------------------===//
let Predicates = [HasAVX] in {
- defm VPCMPEQB : PDI_binop_rm_int<0x74, "vpcmpeqb", int_x86_sse2_pcmpeq_b, 1,
- 0>, VEX_4V;
- defm VPCMPEQW : PDI_binop_rm_int<0x75, "vpcmpeqw", int_x86_sse2_pcmpeq_w, 1,
- 0>, VEX_4V;
- defm VPCMPEQD : PDI_binop_rm_int<0x76, "vpcmpeqd", int_x86_sse2_pcmpeq_d, 1,
- 0>, VEX_4V;
- defm VPCMPGTB : PDI_binop_rm_int<0x64, "vpcmpgtb", int_x86_sse2_pcmpgt_b, 0,
- 0>, VEX_4V;
- defm VPCMPGTW : PDI_binop_rm_int<0x65, "vpcmpgtw", int_x86_sse2_pcmpgt_w, 0,
- 0>, VEX_4V;
- defm VPCMPGTD : PDI_binop_rm_int<0x66, "vpcmpgtd", int_x86_sse2_pcmpgt_d, 0,
- 0>, VEX_4V;
+ defm VPCMPEQB : PDI_binop_rm_int<0x74, "vpcmpeqb", int_x86_sse2_pcmpeq_b,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+ defm VPCMPEQW : PDI_binop_rm_int<0x75, "vpcmpeqw", int_x86_sse2_pcmpeq_w,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+ defm VPCMPEQD : PDI_binop_rm_int<0x76, "vpcmpeqd", int_x86_sse2_pcmpeq_d,
+ VR128, memopv2i64, i128mem, 1, 0>, VEX_4V;
+ defm VPCMPGTB : PDI_binop_rm_int<0x64, "vpcmpgtb", int_x86_sse2_pcmpgt_b,
+ VR128, memopv2i64, i128mem, 0, 0>, VEX_4V;
+ defm VPCMPGTW : PDI_binop_rm_int<0x65, "vpcmpgtw", int_x86_sse2_pcmpgt_w,
+ VR128, memopv2i64, i128mem, 0, 0>, VEX_4V;
+ defm VPCMPGTD : PDI_binop_rm_int<0x66, "vpcmpgtd", int_x86_sse2_pcmpgt_d,
+ VR128, memopv2i64, i128mem, 0, 0>, VEX_4V;
def : Pat<(v16i8 (X86pcmpeqb VR128:$src1, VR128:$src2)),
(VPCMPEQBrr VR128:$src1, VR128:$src2)>;
@@ -3706,13 +3898,34 @@ let Predicates = [HasAVX] in {
(VPCMPGTDrm VR128:$src1, addr:$src2)>;
}
+let Predicates = [HasAVX2] in {
+ defm VPCMPEQBY : PDI_binop_rm_int<0x74, "vpcmpeqb", int_x86_avx2_pcmpeq_b,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+ defm VPCMPEQWY : PDI_binop_rm_int<0x75, "vpcmpeqw", int_x86_avx2_pcmpeq_w,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+ defm VPCMPEQDY : PDI_binop_rm_int<0x76, "vpcmpeqd", int_x86_avx2_pcmpeq_d,
+ VR256, memopv4i64, i256mem, 1, 0>, VEX_4V;
+ defm VPCMPGTBY : PDI_binop_rm_int<0x64, "vpcmpgtb", int_x86_avx2_pcmpgt_b,
+ VR256, memopv4i64, i256mem, 0, 0>, VEX_4V;
+ defm VPCMPGTWY : PDI_binop_rm_int<0x65, "vpcmpgtw", int_x86_avx2_pcmpgt_w,
+ VR256, memopv4i64, i256mem, 0, 0>, VEX_4V;
+ defm VPCMPGTDY : PDI_binop_rm_int<0x66, "vpcmpgtd", int_x86_avx2_pcmpgt_d,
+ VR256, memopv4i64, i256mem, 0, 0>, VEX_4V;
+}
+
let Constraints = "$src1 = $dst" in {
- defm PCMPEQB : PDI_binop_rm_int<0x74, "pcmpeqb", int_x86_sse2_pcmpeq_b, 1>;
- defm PCMPEQW : PDI_binop_rm_int<0x75, "pcmpeqw", int_x86_sse2_pcmpeq_w, 1>;
- defm PCMPEQD : PDI_binop_rm_int<0x76, "pcmpeqd", int_x86_sse2_pcmpeq_d, 1>;
- defm PCMPGTB : PDI_binop_rm_int<0x64, "pcmpgtb", int_x86_sse2_pcmpgt_b>;
- defm PCMPGTW : PDI_binop_rm_int<0x65, "pcmpgtw", int_x86_sse2_pcmpgt_w>;
- defm PCMPGTD : PDI_binop_rm_int<0x66, "pcmpgtd", int_x86_sse2_pcmpgt_d>;
+ defm PCMPEQB : PDI_binop_rm_int<0x74, "pcmpeqb", int_x86_sse2_pcmpeq_b,
+ VR128, memopv2i64, i128mem, 1>;
+ defm PCMPEQW : PDI_binop_rm_int<0x75, "pcmpeqw", int_x86_sse2_pcmpeq_w,
+ VR128, memopv2i64, i128mem, 1>;
+ defm PCMPEQD : PDI_binop_rm_int<0x76, "pcmpeqd", int_x86_sse2_pcmpeq_d,
+ VR128, memopv2i64, i128mem, 1>;
+ defm PCMPGTB : PDI_binop_rm_int<0x64, "pcmpgtb", int_x86_sse2_pcmpgt_b,
+ VR128, memopv2i64, i128mem>;
+ defm PCMPGTW : PDI_binop_rm_int<0x65, "pcmpgtw", int_x86_sse2_pcmpgt_w,
+ VR128, memopv2i64, i128mem>;
+ defm PCMPGTD : PDI_binop_rm_int<0x66, "pcmpgtd", int_x86_sse2_pcmpgt_d,
+ VR128, memopv2i64, i128mem>;
} // Constraints = "$src1 = $dst"
let Predicates = [HasSSE2] in {
@@ -3749,17 +3962,29 @@ let Predicates = [HasSSE2] in {
let Predicates = [HasAVX] in {
defm VPACKSSWB : PDI_binop_rm_int<0x63, "vpacksswb", int_x86_sse2_packsswb_128,
- 0, 0>, VEX_4V;
+ VR128, memopv2i64, i128mem, 0, 0>, VEX_4V;
defm VPACKSSDW : PDI_binop_rm_int<0x6B, "vpackssdw", int_x86_sse2_packssdw_128,
- 0, 0>, VEX_4V;
+ VR128, memopv2i64, i128mem, 0, 0>, VEX_4V;
defm VPACKUSWB : PDI_binop_rm_int<0x67, "vpackuswb", int_x86_sse2_packuswb_128,
- 0, 0>, VEX_4V;
+ VR128, memopv2i64, i128mem, 0, 0>, VEX_4V;
+}
+
+let Predicates = [HasAVX2] in {
+defm VPACKSSWBY : PDI_binop_rm_int<0x63, "vpacksswb", int_x86_avx2_packsswb,
+ VR256, memopv4i64, i256mem, 0, 0>, VEX_4V;
+defm VPACKSSDWY : PDI_binop_rm_int<0x6B, "vpackssdw", int_x86_avx2_packssdw,
+ VR256, memopv4i64, i256mem, 0, 0>, VEX_4V;
+defm VPACKUSWBY : PDI_binop_rm_int<0x67, "vpackuswb", int_x86_avx2_packuswb,
+ VR256, memopv4i64, i256mem, 0, 0>, VEX_4V;
}
let Constraints = "$src1 = $dst" in {
-defm PACKSSWB : PDI_binop_rm_int<0x63, "packsswb", int_x86_sse2_packsswb_128>;
-defm PACKSSDW : PDI_binop_rm_int<0x6B, "packssdw", int_x86_sse2_packssdw_128>;
-defm PACKUSWB : PDI_binop_rm_int<0x67, "packuswb", int_x86_sse2_packuswb_128>;
+defm PACKSSWB : PDI_binop_rm_int<0x63, "packsswb", int_x86_sse2_packsswb_128,
+ VR128, memopv2i64, i128mem>;
+defm PACKSSDW : PDI_binop_rm_int<0x6B, "packssdw", int_x86_sse2_packssdw_128,
+ VR128, memopv2i64, i128mem>;
+defm PACKUSWB : PDI_binop_rm_int<0x67, "packuswb", int_x86_sse2_packuswb_128,
+ VR128, memopv2i64, i128mem>;
} // Constraints = "$src1 = $dst"
//===---------------------------------------------------------------------===//
diff --git a/test/CodeGen/X86/avx2-intrinsics-x86.ll b/test/CodeGen/X86/avx2-intrinsics-x86.ll
new file mode 100644
index 0000000000..9e24f50f05
--- /dev/null
+++ b/test/CodeGen/X86/avx2-intrinsics-x86.ll
@@ -0,0 +1,384 @@
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mcpu=core-avx2 -mattr=avx2 | FileCheck %s
+
+define <16 x i16> @test_x86_avx2_packssdw(<8 x i32> %a0, <8 x i32> %a1) {
+ ; CHECK: vpackssdw
+ %res = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a0, <8 x i32> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32>, <8 x i32>) nounwind readnone
+
+
+define <32 x i8> @test_x86_avx2_packsswb(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpacksswb
+ %res = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a0, <16 x i16> %a1) ; <<32 x i8>> [#uses=1]
+ ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <32 x i8> @test_x86_avx2_packuswb(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpackuswb
+ %res = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a0, <16 x i16> %a1) ; <<32 x i8>> [#uses=1]
+ ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <32 x i8> @test_x86_avx2_padds_b(<32 x i8> %a0, <32 x i8> %a1) {
+ ; CHECK: vpaddsb
+ %res = call <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
+ ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8>, <32 x i8>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_padds_w(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpaddsw
+ %res = call <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <32 x i8> @test_x86_avx2_paddus_b(<32 x i8> %a0, <32 x i8> %a1) {
+ ; CHECK: vpaddusb
+ %res = call <32 x i8> @llvm.x86.avx2.paddus.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
+ ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.paddus.b(<32 x i8>, <32 x i8>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_paddus_w(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpaddusw
+ %res = call <16 x i16> @llvm.x86.avx2.paddus.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.paddus.w(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <32 x i8> @test_x86_avx2_pavg_b(<32 x i8> %a0, <32 x i8> %a1) {
+ ; CHECK: vpavgb
+ %res = call <32 x i8> @llvm.x86.avx2.pavg.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
+ ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.pavg.b(<32 x i8>, <32 x i8>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_pavg_w(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpavgw
+ %res = call <16 x i16> @llvm.x86.avx2.pavg.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.pavg.w(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <32 x i8> @test_x86_avx2_pcmpeq_b(<32 x i8> %a0, <32 x i8> %a1) {
+ ; CHECK: vpcmpeqb
+ %res = call <32 x i8> @llvm.x86.avx2.pcmpeq.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
+ ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.pcmpeq.b(<32 x i8>, <32 x i8>) nounwind readnone
+
+
+define <8 x i32> @test_x86_avx2_pcmpeq_d(<8 x i32> %a0, <8 x i32> %a1) {
+ ; CHECK: vpcmpeqd
+ %res = call <8 x i32> @llvm.x86.avx2.pcmpeq.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
+ ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.pcmpeq.d(<8 x i32>, <8 x i32>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_pcmpeq_w(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpcmpeqw
+ %res = call <16 x i16> @llvm.x86.avx2.pcmpeq.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.pcmpeq.w(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <32 x i8> @test_x86_avx2_pcmpgt_b(<32 x i8> %a0, <32 x i8> %a1) {
+ ; CHECK: vpcmpgtb
+ %res = call <32 x i8> @llvm.x86.avx2.pcmpgt.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
+ ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.pcmpgt.b(<32 x i8>, <32 x i8>) nounwind readnone
+
+
+define <8 x i32> @test_x86_avx2_pcmpgt_d(<8 x i32> %a0, <8 x i32> %a1) {
+ ; CHECK: vpcmpgtd
+ %res = call <8 x i32> @llvm.x86.avx2.pcmpgt.d(<8 x i32> %a0, <8 x i32> %a1) ; <<8 x i32>> [#uses=1]
+ ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.pcmpgt.d(<8 x i32>, <8 x i32>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_pcmpgt_w(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpcmpgtw
+ %res = call <16 x i16> @llvm.x86.avx2.pcmpgt.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.pcmpgt.w(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <8 x i32> @test_x86_avx2_pmadd_wd(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpmaddwd
+ %res = call <8 x i32> @llvm.x86.avx2.pmadd.wd(<16 x i16> %a0, <16 x i16> %a1) ; <<8 x i32>> [#uses=1]
+ ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.pmadd.wd(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_pmaxs_w(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpmaxsw
+ %res = call <16 x i16> @llvm.x86.avx2.pmaxs.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.pmaxs.w(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <32 x i8> @test_x86_avx2_pmaxu_b(<32 x i8> %a0, <32 x i8> %a1) {
+ ; CHECK: vpmaxub
+ %res = call <32 x i8> @llvm.x86.avx2.pmaxu.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
+ ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.pmaxu.b(<32 x i8>, <32 x i8>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_pmins_w(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpminsw
+ %res = call <16 x i16> @llvm.x86.avx2.pmins.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.pmins.w(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <32 x i8> @test_x86_avx2_pminu_b(<32 x i8> %a0, <32 x i8> %a1) {
+ ; CHECK: vpminub
+ %res = call <32 x i8> @llvm.x86.avx2.pminu.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
+ ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.pminu.b(<32 x i8>, <32 x i8>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_pmulh_w(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpmulhw
+ %res = call <16 x i16> @llvm.x86.avx2.pmulh.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.pmulh.w(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_pmulhu_w(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpmulhuw
+ %res = call <16 x i16> @llvm.x86.avx2.pmulhu.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.pmulhu.w(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <4 x i64> @test_x86_avx2_pmulu_dq(<8 x i32> %a0, <8 x i32> %a1) {
+ ; CHECK: vpmuludq
+ %res = call <4 x i64> @llvm.x86.avx2.pmulu.dq(<8 x i32> %a0, <8 x i32> %a1) ; <<4 x i64>> [#uses=1]
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.pmulu.dq(<8 x i32>, <8 x i32>) nounwind readnone
+
+
+define <4 x i64> @test_x86_avx2_psad_bw(<32 x i8> %a0, <32 x i8> %a1) {
+ ; CHECK: vpsadbw
+ %res = call <4 x i64> @llvm.x86.avx2.psad.bw(<32 x i8> %a0, <32 x i8> %a1) ; <<4 x i64>> [#uses=1]
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.psad.bw(<32 x i8>, <32 x i8>) nounwind readnone
+
+
+define <8 x i32> @test_x86_avx2_psll_d(<8 x i32> %a0, <4 x i32> %a1) {
+ ; CHECK: vpslld
+ %res = call <8 x i32> @llvm.x86.avx2.psll.d(<8 x i32> %a0, <4 x i32> %a1) ; <<8 x i32>> [#uses=1]
+ ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.psll.d(<8 x i32>, <4 x i32>) nounwind readnone
+
+
+define <4 x i64> @test_x86_avx2_psll_dq(<4 x i64> %a0) {
+ ; CHECK: vpslldq
+ %res = call <4 x i64> @llvm.x86.avx2.psll.dq(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.psll.dq(<4 x i64>, i32) nounwind readnone
+
+
+define <4 x i64> @test_x86_avx2_psll_dq_bs(<4 x i64> %a0) {
+ ; CHECK: vpslldq
+ %res = call <4 x i64> @llvm.x86.avx2.psll.dq.bs(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.psll.dq.bs(<4 x i64>, i32) nounwind readnone
+
+
+define <4 x i64> @test_x86_avx2_psll_q(<4 x i64> %a0, <2 x i64> %a1) {
+ ; CHECK: vpsllq
+ %res = call <4 x i64> @llvm.x86.avx2.psll.q(<4 x i64> %a0, <2 x i64> %a1) ; <<4 x i64>> [#uses=1]
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.psll.q(<4 x i64>, <2 x i64>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_psll_w(<16 x i16> %a0, <8 x i16> %a1) {
+ ; CHECK: vpsllw
+ %res = call <16 x i16> @llvm.x86.avx2.psll.w(<16 x i16> %a0, <8 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.psll.w(<16 x i16>, <8 x i16>) nounwind readnone
+
+
+define <8 x i32> @test_x86_avx2_pslli_d(<8 x i32> %a0) {
+ ; CHECK: vpslld
+ %res = call <8 x i32> @llvm.x86.avx2.pslli.d(<8 x i32> %a0, i32 7) ; <<8 x i32>> [#uses=1]
+ ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.pslli.d(<8 x i32>, i32) nounwind readnone
+
+
+define <4 x i64> @test_x86_avx2_pslli_q(<4 x i64> %a0) {
+ ; CHECK: vpsllq
+ %res = call <4 x i64> @llvm.x86.avx2.pslli.q(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.pslli.q(<4 x i64>, i32) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_pslli_w(<16 x i16> %a0) {
+ ; CHECK: vpsllw
+ %res = call <16 x i16> @llvm.x86.avx2.pslli.w(<16 x i16> %a0, i32 7) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.pslli.w(<16 x i16>, i32) nounwind readnone
+
+
+define <8 x i32> @test_x86_avx2_psra_d(<8 x i32> %a0, <4 x i32> %a1) {
+ ; CHECK: vpsrad
+ %res = call <8 x i32> @llvm.x86.avx2.psra.d(<8 x i32> %a0, <4 x i32> %a1) ; <<8 x i32>> [#uses=1]
+ ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.psra.d(<8 x i32>, <4 x i32>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_psra_w(<16 x i16> %a0, <8 x i16> %a1) {
+ ; CHECK: vpsraw
+ %res = call <16 x i16> @llvm.x86.avx2.psra.w(<16 x i16> %a0, <8 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.psra.w(<16 x i16>, <8 x i16>) nounwind readnone
+
+
+define <8 x i32> @test_x86_avx2_psrai_d(<8 x i32> %a0) {
+ ; CHECK: vpsrad
+ %res = call <8 x i32> @llvm.x86.avx2.psrai.d(<8 x i32> %a0, i32 7) ; <<8 x i32>> [#uses=1]
+ ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.psrai.d(<8 x i32>, i32) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_psrai_w(<16 x i16> %a0) {
+ ; CHECK: vpsraw
+ %res = call <16 x i16> @llvm.x86.avx2.psrai.w(<16 x i16> %a0, i32 7) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.psrai.w(<16 x i16>, i32) nounwind readnone
+
+
+define <8 x i32> @test_x86_avx2_psrl_d(<8 x i32> %a0, <4 x i32> %a1) {
+ ; CHECK: vpsrld
+ %res = call <8 x i32> @llvm.x86.avx2.psrl.d(<8 x i32> %a0, <4 x i32> %a1) ; <<8 x i32>> [#uses=1]
+ ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.psrl.d(<8 x i32>, <4 x i32>) nounwind readnone
+
+
+define <4 x i64> @test_x86_avx2_psrl_dq(<4 x i64> %a0) {
+ ; CHECK: vpsrldq
+ %res = call <4 x i64> @llvm.x86.avx2.psrl.dq(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.psrl.dq(<4 x i64>, i32) nounwind readnone
+
+
+define <4 x i64> @test_x86_avx2_psrl_dq_bs(<4 x i64> %a0) {
+ ; CHECK: vpsrldq
+ %res = call <4 x i64> @llvm.x86.avx2.psrl.dq.bs(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.psrl.dq.bs(<4 x i64>, i32) nounwind readnone
+
+
+define <4 x i64> @test_x86_avx2_psrl_q(<4 x i64> %a0, <2 x i64> %a1) {
+ ; CHECK: vpsrlq
+ %res = call <4 x i64> @llvm.x86.avx2.psrl.q(<4 x i64> %a0, <2 x i64> %a1) ; <<4 x i64>> [#uses=1]
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.psrl.q(<4 x i64>, <2 x i64>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_psrl_w(<16 x i16> %a0, <8 x i16> %a1) {
+ ; CHECK: vpsrlw
+ %res = call <16 x i16> @llvm.x86.avx2.psrl.w(<16 x i16> %a0, <8 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.psrl.w(<16 x i16>, <8 x i16>) nounwind readnone
+
+
+define <8 x i32> @test_x86_avx2_psrli_d(<8 x i32> %a0) {
+ ; CHECK: vpsrld
+ %res = call <8 x i32> @llvm.x86.avx2.psrli.d(<8 x i32> %a0, i32 7) ; <<8 x i32>> [#uses=1]
+ ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.psrli.d(<8 x i32>, i32) nounwind readnone
+
+
+define <4 x i64> @test_x86_avx2_psrli_q(<4 x i64> %a0) {
+ ; CHECK: vpsrlq
+ %res = call <4 x i64> @llvm.x86.avx2.psrli.q(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1]
+ ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.psrli.q(<4 x i64>, i32) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_psrli_w(<16 x i16> %a0) {
+ ; CHECK: vpsrlw
+ %res = call <16 x i16> @llvm.x86.avx2.psrli.w(<16 x i16> %a0, i32 7) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.psrli.w(<16 x i16>, i32) nounwind readnone
+
+
+define <32 x i8> @test_x86_avx2_psubs_b(<32 x i8> %a0, <32 x i8> %a1) {
+ ; CHECK: vpsubsb
+ %res = call <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
+ ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8>, <32 x i8>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_psubs_w(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpsubsw
+ %res = call <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16>, <16 x i16>) nounwind readnone
+
+
+define <32 x i8> @test_x86_avx2_psubus_b(<32 x i8> %a0, <32 x i8> %a1) {
+ ; CHECK: vpsubusb
+ %res = call <32 x i8> @llvm.x86.avx2.psubus.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1]
+ ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.psubus.b(<32 x i8>, <32 x i8>) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_psubus_w(<16 x i16> %a0, <16 x i16> %a1) {
+ ; CHECK: vpsubusw
+ %res = call <16 x i16> @llvm.x86.avx2.psubus.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#uses=1]
+ ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.psubus.w(<16 x i16>, <16 x i16>) nounwind readnone
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-21 07:26:31 +0000