[x86] avoid unnecessary shuffle mask math in combineX86ShufflesRecursively()

This is a follow-up to https://reviews.llvm.org/D34174 / https://reviews.llvm.org/rL305398.

We mentioned replacing the multiplies with shifts, but the real win seems to be in
bypassing the extra ops in the common case when the RootRatio and OpRatio are one.

This gives us another 1-2% overall win for the test in PR32037:
https://bugs.llvm.org/show_bug.cgi?id=32037

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@305414 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index c7e4f4dc14e5a66a814b7c40d499d2e6a98fe638..29b438e9bffb7c7f74e7ce888e64f82dabf399e9 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -28005,10 +28005,10 @@ static bool combineX86ShufflesRecursively(ArrayRef<SDValue> SrcOps,
       continue;
     }
 
-    // TODO: Here and below, we could convert multiply to shift-left for
-    // performance because we know that our mask sizes are power-of-2.
     unsigned RootMaskedIdx =
-        RootMask[RootIdx] * RootRatio + (i & (RootRatio - 1));
+        RootRatio == 1
+            ? RootMask[RootIdx]
+            : (RootMask[RootIdx] << RootRatioLog2) + (i & (RootRatio - 1));
 
     // Just insert the scaled root mask value if it references an input other
     // than the SrcOp we're currently inserting.
@@ -28019,7 +28019,6 @@ static bool combineX86ShufflesRecursively(ArrayRef<SDValue> SrcOps,
     }
 
     RootMaskedIdx = RootMaskedIdx & (MaskWidth - 1);
-
     unsigned OpIdx = RootMaskedIdx >> OpRatioLog2;
     if (OpMask[OpIdx] < 0) {
       // The incoming lanes are zero or undef, it doesn't matter which ones we
@@ -28030,9 +28029,11 @@ static bool combineX86ShufflesRecursively(ArrayRef<SDValue> SrcOps,
 
     // Ok, we have non-zero lanes, map them through to one of the Op's inputs.
     unsigned OpMaskedIdx =
-        OpMask[OpIdx] * OpRatio + (RootMaskedIdx & (OpRatio - 1));
-    OpMaskedIdx = OpMaskedIdx & (MaskWidth - 1);
+        OpRatio == 1
+            ? OpMask[OpIdx]
+            : (OpMask[OpIdx] << OpRatioLog2) + (RootMaskedIdx & (OpRatio - 1));
 
+    OpMaskedIdx = OpMaskedIdx & (MaskWidth - 1);
     if (OpMask[OpIdx] < (int)OpMask.size()) {
       assert(0 <= InputIdx0 && "Unknown target shuffle input");
       OpMaskedIdx += InputIdx0 * MaskWidth;