AVX-512: Gather and Scatter patterns

Gather and scatter instructions additionally write to one of the source operands - mask register.
In this case Gather has 2 destination values - the loaded value and the mask.
Till now we did not support code gen pattern for gather - the instruction was generated from 
intrinsic only and machine node was hardcoded.
When we introduce the masked_gather node, we need to select instruction automatically,
in the standard way.
I added a flag "hasTwoExplicitDefs" that allows to handle 2 destination operands.

(Some code in the X86InstrFragmentsSIMD.td is commented out, just to split one big
patch in many small patches)

llvm-svn: 230471

3 files changed, 108 insertions, 44 deletions

diff --git a/llvm/lib/Target/X86/X86InstrAVX512.td b/llvm/lib/Target/X86/X86InstrAVX512.td
index 0b2392b9bce..4923bc5f1dd 100644
--- a/llvm/lib/Target/X86/X86InstrAVX512.td
+++ b/llvm/lib/Target/X86/X86InstrAVX512.td
@@ -4919,74 +4919,81 @@ defm VPMOVSXDQZ: avx512_extend<0x25, "vpmovsxdq", VK8WM, VR512, VR256X, X86vsext
 //===----------------------------------------------------------------------===//
 // GATHER - SCATTER Operations
 
-multiclass avx512_gather<bits<8> opc, string OpcodeStr, RegisterClass KRC,
-                       RegisterClass RC, X86MemOperand memop> {
-let mayLoad = 1,
+multiclass avx512_gather<bits<8> opc, string OpcodeStr, X86VectorVTInfo _,
+                         X86MemOperand memop, PatFrag GatherNode> {
+let mayLoad = 1, hasTwoExplicitDefs = 1,
   Constraints = "@earlyclobber $dst, $src1 = $dst, $mask = $mask_wb" in
-  def rm  : AVX5128I<opc, MRMSrcMem, (outs RC:$dst, KRC:$mask_wb),
-            (ins RC:$src1, KRC:$mask, memop:$src2),
+  def rm  : AVX5128I<opc, MRMSrcMem, (outs _.RC:$dst, _.KRCWM:$mask_wb),
+            (ins _.RC:$src1, _.KRCWM:$mask, memop:$src2),
             !strconcat(OpcodeStr,
             "\t{$src2, ${dst} {${mask}}|${dst} {${mask}}, $src2}"),
-            []>, EVEX, EVEX_K;
+            [(set _.RC:$dst, _.KRCWM:$mask_wb,
+              (_.VT (GatherNode  (_.VT _.RC:$src1), _.KRCWM:$mask,
+                     vectoraddr:$src2)))]>, EVEX, EVEX_K,
+             EVEX_CD8<_.EltSize, CD8VT1>;
 }
 
 let ExeDomain = SSEPackedDouble in {
-defm VGATHERDPDZ : avx512_gather<0x92, "vgatherdpd", VK8WM, VR512, vy64xmem>,
-                                 EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>;
-defm VGATHERQPDZ : avx512_gather<0x93, "vgatherqpd", VK8WM, VR512, vz64mem>,
-                                 EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>;
+defm VGATHERDPDZ : avx512_gather<0x92, "vgatherdpd", v8f64_info, vy64xmem,
+                                 mgatherv8i32>, EVEX_V512, VEX_W;
+defm VGATHERQPDZ : avx512_gather<0x93, "vgatherqpd", v8f64_info, vz64mem,
+                                 mgatherv8i64>, EVEX_V512, VEX_W;
 }
 
 let ExeDomain = SSEPackedSingle in {
-defm VGATHERDPSZ : avx512_gather<0x92, "vgatherdps", VK16WM, VR512, vz32mem>,
-                                 EVEX_V512, EVEX_CD8<32, CD8VT1>;
-defm VGATHERQPSZ : avx512_gather<0x93, "vgatherqps", VK8WM, VR256X, vz64mem>,
-                                 EVEX_V512, EVEX_CD8<32, CD8VT1>;
+defm VGATHERDPSZ : avx512_gather<0x92, "vgatherdps", v16f32_info, vz32mem,
+                                 mgatherv16i32>, EVEX_V512;
+defm VGATHERQPSZ : avx512_gather<0x93, "vgatherqps", v8f32x_info, vz64mem,
+                                 mgatherv8i64>,  EVEX_V512;
 }
 
-defm VPGATHERDQZ : avx512_gather<0x90, "vpgatherdq", VK8WM, VR512,  vy64xmem>,
-                                 EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>;
-defm VPGATHERDDZ : avx512_gather<0x90, "vpgatherdd", VK16WM, VR512, vz32mem>,
-                                 EVEX_V512, EVEX_CD8<32, CD8VT1>;
+defm VPGATHERDQZ : avx512_gather<0x90, "vpgatherdq", v8i64_info,  vy64xmem,
+                                 mgatherv8i32>, EVEX_V512, VEX_W;
+defm VPGATHERDDZ : avx512_gather<0x90, "vpgatherdd", v16i32_info, vz32mem,
+                                 mgatherv16i32>, EVEX_V512;
+
+defm VPGATHERQQZ : avx512_gather<0x91, "vpgatherqq", v8i64_info,  vz64mem,
+                                 mgatherv8i64>, EVEX_V512, VEX_W;
+defm VPGATHERQDZ : avx512_gather<0x91, "vpgatherqd", v8i32x_info,  vz64mem,
+                                 mgatherv8i64>, EVEX_V512;
 
-defm VPGATHERQQZ : avx512_gather<0x91, "vpgatherqq", VK8WM, VR512,  vz64mem>,
-                                 EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>;
-defm VPGATHERQDZ : avx512_gather<0x91, "vpgatherqd", VK8WM, VR256X,  vz64mem>,
-                                 EVEX_V512, EVEX_CD8<32, CD8VT1>;
+multiclass avx512_scatter<bits<8> opc, string OpcodeStr, X86VectorVTInfo _,
+                          X86MemOperand memop, PatFrag ScatterNode> {
 
-multiclass avx512_scatter<bits<8> opc, string OpcodeStr, RegisterClass KRC,
-                       RegisterClass RC, X86MemOperand memop> {
 let mayStore = 1, Constraints = "$mask = $mask_wb" in
-  def mr  : AVX5128I<opc, MRMDestMem, (outs KRC:$mask_wb),
-            (ins memop:$dst, KRC:$mask, RC:$src2),
+
+  def mr  : AVX5128I<opc, MRMDestMem, (outs _.KRCWM:$mask_wb),
+            (ins memop:$dst, _.KRCWM:$mask, _.RC:$src),
             !strconcat(OpcodeStr,
-            "\t{$src2, ${dst} {${mask}}|${dst} {${mask}}, $src2}"),
-            []>, EVEX, EVEX_K;
+            "\t{$src, ${dst} {${mask}}|${dst} {${mask}}, $src}"),
+            [(set _.KRCWM:$mask_wb, (ScatterNode (_.VT _.RC:$src),
+                                     _.KRCWM:$mask,  vectoraddr:$dst))]>,
+            EVEX, EVEX_K, EVEX_CD8<_.EltSize, CD8VT1>;
 }
 
 let ExeDomain = SSEPackedDouble in {
-defm VSCATTERDPDZ : avx512_scatter<0xA2, "vscatterdpd", VK8WM, VR512, vy64xmem>,
-                                   EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>;
-defm VSCATTERQPDZ : avx512_scatter<0xA3, "vscatterqpd", VK8WM, VR512, vz64mem>,
-                                   EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>;
+defm VSCATTERDPDZ : avx512_scatter<0xA2, "vscatterdpd", v8f64_info, vy64xmem,
+                                   mscatterv8i32>, EVEX_V512, VEX_W;
+defm VSCATTERQPDZ : avx512_scatter<0xA3, "vscatterqpd", v8f64_info, vz64mem,
+                                   mscatterv8i64>, EVEX_V512, VEX_W;
 }
 
 let ExeDomain = SSEPackedSingle in {
-defm VSCATTERDPSZ : avx512_scatter<0xA2, "vscatterdps", VK16WM, VR512, vz32mem>,
-                                   EVEX_V512, EVEX_CD8<32, CD8VT1>;
-defm VSCATTERQPSZ : avx512_scatter<0xA3, "vscatterqps", VK8WM, VR256X, vz64mem>,
-                                   EVEX_V512, EVEX_CD8<32, CD8VT1>;
+defm VSCATTERDPSZ : avx512_scatter<0xA2, "vscatterdps", v16f32_info, vz32mem,
+                                   mscatterv16i32>, EVEX_V512;
+defm VSCATTERQPSZ : avx512_scatter<0xA3, "vscatterqps", v8f32x_info, vz64mem,
+                                   mscatterv8i64>, EVEX_V512;
 }
 
-defm VPSCATTERDQZ : avx512_scatter<0xA0, "vpscatterdq", VK8WM, VR512, vy64xmem>,
-                                   EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>;
-defm VPSCATTERDDZ : avx512_scatter<0xA0, "vpscatterdd", VK16WM, VR512, vz32mem>,
-                                   EVEX_V512, EVEX_CD8<32, CD8VT1>;
+defm VPSCATTERDQZ : avx512_scatter<0xA0, "vpscatterdq", v8i64_info, vy64xmem,
+                                   mscatterv8i32>, EVEX_V512, VEX_W;
+defm VPSCATTERDDZ : avx512_scatter<0xA0, "vpscatterdd", v16i32_info, vz32mem,
+                                   mscatterv16i32>, EVEX_V512;
 
-defm VPSCATTERQQZ : avx512_scatter<0xA1, "vpscatterqq", VK8WM, VR512, vz64mem>,
-                                  EVEX_V512, VEX_W, EVEX_CD8<64, CD8VT1>;
-defm VPSCATTERQDZ : avx512_scatter<0xA1, "vpscatterqd", VK8WM, VR256X, vz64mem>,
-                                  EVEX_V512, EVEX_CD8<32, CD8VT1>;
+defm VPSCATTERQQZ : avx512_scatter<0xA1, "vpscatterqq", v8i64_info, vz64mem,
+                                   mscatterv8i64>, EVEX_V512, VEX_W;
+defm VPSCATTERQDZ : avx512_scatter<0xA1, "vpscatterqd", v8i32x_info, vz64mem,
+                                   mscatterv8i64>, EVEX_V512;
 
 // prefetch
 multiclass avx512_gather_scatter_prefetch<bits<8> opc, Format F, string OpcodeStr,
diff --git a/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td b/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
index a80843fc48f..bf515a847db 100644
--- a/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
+++ b/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
@@ -304,6 +304,8 @@ def X86exp2      : SDNode<"X86ISD::EXP2",     STDFp1SrcRm>;
 def X86rsqrt28s  : SDNode<"X86ISD::RSQRT28",  STDFp2SrcRm>;
 def X86rcp28s    : SDNode<"X86ISD::RCP28",    STDFp2SrcRm>;
 def X86RndScale  : SDNode<"X86ISD::RNDSCALE", STDFp3SrcRm>;
+def X86mgather   : SDNode<"X86ISD::GATHER", SDTypeProfile<1, 3, 
+                          [SDTCisVec<0>, SDTCisVec<1>, SDTCisVec<2>]>>;
 
 def SDT_PCMPISTRI : SDTypeProfile<2, 3, [SDTCisVT<0, i32>, SDTCisVT<1, i32>,
                                          SDTCisVT<2, v16i8>, SDTCisVT<3, v16i8>,
@@ -524,6 +526,58 @@ def unalignednontemporalstore : PatFrag<(ops node:$val, node:$ptr),
   return false;
 }]>;
 
+def mgatherv8i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
+  (masked_gather node:$src1, node:$src2, node:$src3) , [{
+  //if (MaskedGatherSDNode *Mgt = dyn_cast<MaskedGatherSDNode>(N))
+  //  return (Mgt->getIndex().getValueType() == MVT::v8i32 ||
+  //          Mgt->getBasePtr().getValueType() == MVT::v8i32);
+  //return false;
+  return N != 0;
+}]>;
+
+def mgatherv8i64 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
+  (masked_gather node:$src1, node:$src2, node:$src3) , [{
+  //if (MaskedGatherSDNode *Mgt = dyn_cast<MaskedGatherSDNode>(N))
+  //  return (Mgt->getIndex().getValueType() == MVT::v8i64 ||
+  //          Mgt->getBasePtr().getValueType() == MVT::v8i64);
+  //return false;
+  return N != 0;
+}]>;
+def mgatherv16i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
+  (masked_gather node:$src1, node:$src2, node:$src3) , [{
+  //if (MaskedGatherSDNode *Mgt = dyn_cast<MaskedGatherSDNode>(N))
+  //  return (Mgt->getIndex().getValueType() == MVT::v16i32 ||
+  //          Mgt->getBasePtr().getValueType() == MVT::v16i32);
+  //return false;
+  return N != 0;
+}]>;
+
+def mscatterv8i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
+  (masked_scatter node:$src1, node:$src2, node:$src3) , [{
+  //if (MaskedScatterSDNode *Sc = dyn_cast<MaskedScatterSDNode>(N))
+  //  return (Sc->getIndex().getValueType() == MVT::v8i32 ||
+  //          Sc->getBasePtr().getValueType() == MVT::v8i32);
+  //return false;
+  return N != 0;
+}]>;
+
+def mscatterv8i64 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
+  (masked_scatter node:$src1, node:$src2, node:$src3) , [{
+  //if (MaskedScatterSDNode *Sc = dyn_cast<MaskedScatterSDNode>(N))
+  //  return (Sc->getIndex().getValueType() == MVT::v8i64 ||
+  //          Sc->getBasePtr().getValueType() == MVT::v8i64);
+  //return false;
+  return N != 0;
+}]>;
+def mscatterv16i32 : PatFrag<(ops node:$src1, node:$src2, node:$src3),
+  (masked_scatter node:$src1, node:$src2, node:$src3) , [{
+  //if (MaskedScatterSDNode *Sc = dyn_cast<MaskedScatterSDNode>(N))
+  //  return (Sc->getIndex().getValueType() == MVT::v16i32 ||
+  //          Sc->getBasePtr().getValueType() == MVT::v16i32);
+  //return false;
+  return N != 0;
+}]>;
+
 // 128-bit bitconvert pattern fragments
 def bc_v4f32 : PatFrag<(ops node:$in), (v4f32 (bitconvert node:$in))>;
 def bc_v2f64 : PatFrag<(ops node:$in), (v2f64 (bitconvert node:$in))>;
diff --git a/llvm/lib/Target/X86/X86InstrInfo.td b/llvm/lib/Target/X86/X86InstrInfo.td
index 7ab8822ff31..9881cafa84d 100644
--- a/llvm/lib/Target/X86/X86InstrInfo.td
+++ b/llvm/lib/Target/X86/X86InstrInfo.td
@@ -713,6 +713,9 @@ def tls64addr : ComplexPattern<i64, 5, "SelectTLSADDRAddr",
 def tls64baseaddr : ComplexPattern<i64, 5, "SelectTLSADDRAddr",
                                [tglobaltlsaddr], []>;
 
+def vectoraddr : ComplexPattern<iPTR, 5, "SelectAddr", [],[SDNPWantParent]>;
+//def vectoraddr : ComplexPattern<iPTR, 5, "SelectVectorAddr", [],[SDNPWantParent]>;
+
 //===----------------------------------------------------------------------===//
 // X86 Instruction Predicate Definitions.
 def HasCMov      : Predicate<"Subtarget->hasCMov()">;