[X86] Always prefer to lower a VECTOR_SHUFFLE into a BLENDI instead of SHUFP (or VPERM2X128).

This patch teaches method 'LowerVECTOR_SHUFFLE' to give higher precedence to
the check for 'isBlendMask'; the idea is that, when possible, we should firstly
check if a shuffle performs a blend, and in case, try to lower it into a BLENDI
instead of selecting a SHUFP or (worse) a VPERM2X128.

In general:
 - AVX VBLENDPS/D always have better latency and throughput than VPERM2F128;
 - BLENDPS/D instructions tend to always have better 'reciprocal throughput'
   than the equivalent SHUFPS/D;
 - Both BLENDPS/D and SHUFPS/D are often decoded into the same number of
   m-ops; however, a m-op obtained from a BLENDPS/D can be scheduled to more
   than one execution port.

This patch:
 - Moves the check for 'isBlendMask' immediately before the check for
   'isSHUFPMask' within method 'LowerVECTOR_SHUFFLE';
 - Updates existing tests for sse/avx shuffle/blend instructions to verify
   that we select (v)blendps/d when possible (instead of (v)shufps/d or
   vperm2f128).

llvm-svn: 211720

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -8337,6 +8337,11 @@ X86TargetLowering::LowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG) const {
                                 getShufflePSHUFLWImmediate(SVOp),
                                 DAG);
 
+  unsigned MaskValue;
+  if (isBlendMask(M, VT, Subtarget->hasSSE41(), Subtarget->hasInt256(),
+                  &MaskValue))
+    return LowerVECTOR_SHUFFLEtoBlend(SVOp, MaskValue, Subtarget, DAG);
+
   if (isSHUFPMask(M, VT))
     return getTargetShuffleNode(X86ISD::SHUFP, dl, VT, V1, V2,
                                 getShuffleSHUFImmediate(SVOp), DAG);
@@ -8374,11 +8379,6 @@ X86TargetLowering::LowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG) const {
     return getTargetShuffleNode(X86ISD::VPERM2X128, dl, VT, V1,
                                 V2, getShuffleVPERM2X128Immediate(SVOp), DAG);
 
-  unsigned MaskValue;
-  if (isBlendMask(M, VT, Subtarget->hasSSE41(), Subtarget->hasInt256(),
-                  &MaskValue))
-    return LowerVECTOR_SHUFFLEtoBlend(SVOp, MaskValue, Subtarget, DAG);
-
   if (Subtarget->hasSSE41() && isINSERTPSMask(M, VT))
     return getINSERTPS(SVOp, dl, DAG);
 

llvm/lib/Target/X86/X86InstrSSE.td

@@ -5374,8 +5374,8 @@ let Predicates = [HasAVX] in {
   // - the 1st and 3rd element from the first input vector (the 'fsub' node);
   // - the 2nd and 4th element from the second input vector (the 'fadd' node).
 
-  def : Pat<(v4f64 (X86Shufp (v4f64 (fsub VR256:$lhs, VR256:$rhs)),
-                             (v4f64 (fadd VR256:$lhs, VR256:$rhs)), (i8 10))),
+  def : Pat<(v4f64 (X86Blendi (v4f64 (fsub VR256:$lhs, VR256:$rhs)),
+                             (v4f64 (fadd VR256:$lhs, VR256:$rhs)), (i32 10))),
             (VADDSUBPDYrr VR256:$lhs, VR256:$rhs)>;
   def : Pat<(v4f64 (X86Blendi (v4f64 (fsub VR256:$lhs, VR256:$rhs)),
                               (v4f64 (fadd VR256:$lhs, VR256:$rhs)), (i32 10))),

llvm/test/CodeGen/X86/avx-blend.ll

@@ -110,7 +110,7 @@ define <8 x i64> @vsel_i648(<8 x i64> %v1, <8 x i64> %v2) {
 
 ;CHECK-LABEL: vsel_double4:
 ;CHECK-NOT: vinsertf128
-;CHECK: vshufpd $10
+;CHECK: vblendpd $10
 ;CHECK-NEXT: ret
 define <4 x double> @vsel_double4(<4 x double> %v1, <4 x double> %v2) {
   %vsel = select <4 x i1> <i1 true, i1 false, i1 true, i1 false>, <4 x double> %v1, <4 x double> %v2

llvm/test/CodeGen/X86/avx-shuffle.ll

@@ -25,7 +25,7 @@ define <4 x i64> @test3(<4 x i64> %a, <4 x i64> %b) nounwind {
   %c = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 4, i32 5, i32 2, i32 undef>
   ret <4 x i64> %c
 ; CHECK-LABEL: test3:
-; CHECK: vperm2f128
+; CHECK: vblendpd
 ; CHECK: ret
 }
 

llvm/test/CodeGen/X86/avx-vperm2f128.ll

@@ -9,7 +9,7 @@ entry:
 }
 
 ; CHECK: _B
-; CHECK: vperm2f128 $48
+; CHECK: vblendps $240
 define <8 x float> @B(<8 x float> %a, <8 x float> %b) nounwind uwtable readnone ssp {
 entry:
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>

llvm/test/CodeGen/X86/avx-vshufp.ll

@@ -32,14 +32,14 @@ entry:
   ret <8 x i32> %shuffle
 }
 
-; CHECK: vshufpd  $10, %ymm
+; CHECK: vblendpd  $10, %ymm
 define <4 x double> @B(<4 x double> %a, <4 x double> %b) nounwind uwtable readnone ssp {
 entry:
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
   ret <4 x double> %shuffle
 }
 
-; CHECK: vshufpd  $10, (%{{.*}}), %ymm
+; CHECK: vblendpd  $10, (%{{.*}}), %ymm
 define <4 x double> @B2(<4 x double>* %a, <4 x double>* %b) nounwind uwtable readnone ssp {
 entry:
   %a2 = load <4 x double>* %a
@@ -48,14 +48,14 @@ entry:
   ret <4 x double> %shuffle
 }
 
-; CHECK: vshufpd  $10, %ymm
+; CHECK: vblendpd  $10, %ymm
 define <4 x i64> @B3(<4 x i64> %a, <4 x i64> %b) nounwind uwtable readnone ssp {
 entry:
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
   ret <4 x i64> %shuffle
 }
 
-; CHECK: vshufpd  $10, (%{{.*}}), %ymm
+; CHECK: vblendpd  $10, (%{{.*}}), %ymm
 define <4 x i64> @B4(<4 x i64>* %a, <4 x i64>* %b) nounwind uwtable readnone ssp {
 entry:
   %a2 = load <4 x i64>* %a
@@ -71,7 +71,7 @@ entry:
   ret <8 x float> %shuffle
 }
 
-; CHECK: vshufpd  $2, %ymm
+; CHECK: vblendpd  $2, %ymm
 define <4 x double> @D(<4 x double> %a, <4 x double> %b) nounwind uwtable readnone ssp {
 entry:
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 5, i32 2, i32 undef>

llvm/test/CodeGen/X86/combine-or.ll

@@ -74,7 +74,7 @@ define <4 x i32> @test6(<4 x i32> %a, <4 x i32> %b) {
 }
 ; CHECK-LABEL: test6
 ; CHECK-NOT: xorps
-; CHECK: shufps
+; CHECK: blendps $12
 ; CHECK-NEXT: ret
 
 
@@ -86,7 +86,7 @@ define <4 x i32> @test7(<4 x i32> %a, <4 x i32> %b) {
 }
 ; CHECK-LABEL: test7
 ; CHECK-NOT: xorps
-; CHECK: shufps
+; CHECK: blendps $12
 ; CHECK-NEXT: ret