[TargetLowering] SimplifyDemandedBits SIGN_EXTEND_VECTOR_INREG -> ANY/ZERO_EXTEND_VEC...

Simplify SIGN_EXTEND_VECTOR_INREG if the extended bits are not required/known zero.

Matches what we already do for SIGN_EXTEND.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@363802 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index dcd8478e48b740e2af7a2eeb68aa2b825303a136..9d45742752875c68a82e227242fa9315ce6a58d7 100644 (file)
--- a/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -1413,9 +1413,11 @@ bool TargetLowering::SimplifyDemandedBits(
     bool IsVecInReg = Op.getOpcode() == ISD::SIGN_EXTEND_VECTOR_INREG;
 
     // If none of the top bits are demanded, convert this into an any_extend.
-    // TODO: Add SIGN_EXTEND_VECTOR_INREG - ANY_EXTEND_VECTOR_INREG fold.
-    if (DemandedBits.getActiveBits() <= InBits && !IsVecInReg)
-      return TLO.CombineTo(Op, TLO.DAG.getNode(ISD::ANY_EXTEND, dl, VT, Src));
+    if (DemandedBits.getActiveBits() <= InBits)
+      return TLO.CombineTo(
+          Op, TLO.DAG.getNode(IsVecInReg ? ISD::ANY_EXTEND_VECTOR_INREG
+                                         : ISD::ANY_EXTEND,
+                              dl, VT, Src));
 
     APInt InDemandedBits = DemandedBits.trunc(InBits);
     APInt InDemandedElts = DemandedElts.zextOrSelf(InElts);
@@ -1434,9 +1436,11 @@ bool TargetLowering::SimplifyDemandedBits(
     Known = Known.sext(BitWidth);
 
     // If the sign bit is known zero, convert this to a zero extend.
-    // TODO: Add SIGN_EXTEND_VECTOR_INREG - ZERO_EXTEND_VECTOR_INREG fold.
-    if (Known.isNonNegative() && !IsVecInReg)
-      return TLO.CombineTo(Op, TLO.DAG.getNode(ISD::ZERO_EXTEND, dl, VT, Src));
+    if (Known.isNonNegative())
+      return TLO.CombineTo(
+          Op, TLO.DAG.getNode(IsVecInReg ? ISD::ZERO_EXTEND_VECTOR_INREG
+                                         : ISD::ZERO_EXTEND,
+                              dl, VT, Src));
     break;
   }
   case ISD::ANY_EXTEND: {

diff --git a/test/CodeGen/X86/pmul.ll b/test/CodeGen/X86/pmul.ll
index 1960e790925a9fbdf66a98709f17ab5eb63288be..5d28f916f050df6f9c4c478108ae2195e2350dec 100644 (file)
--- a/test/CodeGen/X86/pmul.ll
+++ b/test/CodeGen/X86/pmul.ll
@@ -1326,15 +1326,13 @@ define <8 x i64> @mul_v8i64_sext(<8 x i16> %val1, <8 x i32> %val2) {
 ; SSE41-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[1,1,2,3]
 ; SSE41-NEXT:    pmovsxwq %xmm3, %xmm6
 ; SSE41-NEXT:    pmovsxwq %xmm0, %xmm7
-; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm2[2,3,0,1]
-; SSE41-NEXT:    pmovsxdq %xmm0, %xmm3
+; SSE41-NEXT:    pshufd {{.*#+}} xmm3 = xmm2[2,2,3,3]
 ; SSE41-NEXT:    pmuldq %xmm4, %xmm3
-; SSE41-NEXT:    pmovsxdq %xmm2, %xmm2
+; SSE41-NEXT:    pmovzxdq {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero
 ; SSE41-NEXT:    pmuldq %xmm5, %xmm2
-; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
-; SSE41-NEXT:    pmovsxdq %xmm0, %xmm4
+; SSE41-NEXT:    pshufd {{.*#+}} xmm4 = xmm1[2,2,3,3]
 ; SSE41-NEXT:    pmuldq %xmm6, %xmm4
-; SSE41-NEXT:    pmovsxdq %xmm1, %xmm0
+; SSE41-NEXT:    pmovzxdq {{.*#+}} xmm0 = xmm1[0],zero,xmm1[1],zero
 ; SSE41-NEXT:    pmuldq %xmm7, %xmm0
 ; SSE41-NEXT:    movdqa %xmm4, %xmm1
 ; SSE41-NEXT:    retq

diff --git a/test/CodeGen/X86/xop-ifma.ll b/test/CodeGen/X86/xop-ifma.ll
index b8ec25ec1ee8d39551c05ef1dae4b17dca5d27c3..4712910e11b36ec64cb54bb2010dc114bbbe6c42 100644 (file)
--- a/test/CodeGen/X86/xop-ifma.ll
+++ b/test/CodeGen/X86/xop-ifma.ll
@@ -67,12 +67,10 @@ define <8 x i32> @test_mul_v8i32_add_v8i32(<8 x i32> %a0, <8 x i32> %a1, <8 x i3
 define <4 x i64> @test_mulx_v4i32_add_v4i64(<4 x i32> %a0, <4 x i32> %a1, <4 x i64> %a2) {
 ; XOP-AVX1-LABEL: test_mulx_v4i32_add_v4i64:
 ; XOP-AVX1:       # %bb.0:
-; XOP-AVX1-NEXT:    vpmovsxdq %xmm0, %xmm3
-; XOP-AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; XOP-AVX1-NEXT:    vpmovsxdq %xmm0, %xmm0
-; XOP-AVX1-NEXT:    vpmovsxdq %xmm1, %xmm4
-; XOP-AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
-; XOP-AVX1-NEXT:    vpmovsxdq %xmm1, %xmm1
+; XOP-AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm3 = xmm0[0],zero,xmm0[1],zero
+; XOP-AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,1,3,3]
+; XOP-AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm4 = xmm1[0],zero,xmm1[1],zero
+; XOP-AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,1,3,3]
 ; XOP-AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm5
 ; XOP-AVX1-NEXT:    vpmacsdql %xmm5, %xmm1, %xmm0, %xmm0
 ; XOP-AVX1-NEXT:    vpmacsdql %xmm2, %xmm4, %xmm3, %xmm1