[llvm] 868da2e - [SelectionDAG] Remove an early-out from computeKnownBits for smin/smax

[Jay Foad via llvm-commits]

Author: Jay Foad
Date: 2021-01-14T18:15:17Z
New Revision: 868da2ea939baf8c71a6dcb878cf6094ede9486e

URL: https://github.com/llvm/llvm-project/commit/868da2ea939baf8c71a6dcb878cf6094ede9486e
DIFF: https://github.com/llvm/llvm-project/commit/868da2ea939baf8c71a6dcb878cf6094ede9486e.diff

LOG: [SelectionDAG] Remove an early-out from computeKnownBits for smin/smax

Even if we know nothing about LHS, it can still be useful to know that
smax(LHS, RHS) >= RHS and smin(LHS, RHS) <= RHS.

Differential Revision: https://reviews.llvm.org/D87145

Added: 
    

Modified: 
    llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
    llvm/test/CodeGen/X86/known-bits-vector.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 7084ab68524b..82da553954d2 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -3416,7 +3416,6 @@ KnownBits SelectionDAG::computeKnownBits(SDValue Op, const APInt &DemandedElts,
     }
 
     Known = computeKnownBits(Op.getOperand(0), DemandedElts, Depth + 1);
-    if (Known.isUnknown()) break; // Early-out
     Known2 = computeKnownBits(Op.getOperand(1), DemandedElts, Depth + 1);
     if (IsMax)
       Known = KnownBits::smax(Known, Known2);

diff  --git a/llvm/test/CodeGen/X86/known-bits-vector.ll b/llvm/test/CodeGen/X86/known-bits-vector.ll
index 3b6912a9d946..05bf984101ab 100644
--- a/llvm/test/CodeGen/X86/known-bits-vector.ll
+++ b/llvm/test/CodeGen/X86/known-bits-vector.ll
@@ -435,11 +435,7 @@ define <4 x float> @knownbits_smax_smin_shuffle_uitofp(<4 x i32> %a0) {
 ; X32-NEXT:    vpminsd {{\.LCPI.*}}, %xmm0, %xmm0
 ; X32-NEXT:    vpmaxsd {{\.LCPI.*}}, %xmm0, %xmm0
 ; X32-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,3,3]
-; X32-NEXT:    vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
-; X32-NEXT:    vpsrld $16, %xmm0, %xmm0
-; X32-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
-; X32-NEXT:    vsubps {{\.LCPI.*}}, %xmm0, %xmm0
-; X32-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; X32-NEXT:    vcvtdq2ps %xmm0, %xmm0
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: knownbits_smax_smin_shuffle_uitofp:
@@ -447,11 +443,7 @@ define <4 x float> @knownbits_smax_smin_shuffle_uitofp(<4 x i32> %a0) {
 ; X64-NEXT:    vpminsd {{.*}}(%rip), %xmm0, %xmm0
 ; X64-NEXT:    vpmaxsd {{.*}}(%rip), %xmm0, %xmm0
 ; X64-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,3,3]
-; X64-NEXT:    vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
-; X64-NEXT:    vpsrld $16, %xmm0, %xmm0
-; X64-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
-; X64-NEXT:    vsubps {{.*}}(%rip), %xmm0, %xmm0
-; X64-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; X64-NEXT:    vcvtdq2ps %xmm0, %xmm0
 ; X64-NEXT:    retq
   %1 = call <4 x i32> @llvm.x86.sse41.pminsd(<4 x i32> %a0, <4 x i32> <i32 0, i32 -65535, i32 -65535, i32 0>)
   %2 = call <4 x i32> @llvm.x86.sse41.pmaxsd(<4 x i32> %1, <4 x i32> <i32 65535, i32 -1, i32 -1, i32 131071>)