[llvm] 2347276 - [X86] X86FixupInstTuning.cpp - fix comment in ProcessVPERMILPSri. NFC.

[Simon Pilgrim via llvm-commits]

Author: Simon Pilgrim
Date: 2023-04-23T10:32:17+01:00
New Revision: 23472766734a13fbccb9877a288a4f67f73af3b4

URL: https://github.com/llvm/llvm-project/commit/23472766734a13fbccb9877a288a4f67f73af3b4
DIFF: https://github.com/llvm/llvm-project/commit/23472766734a13fbccb9877a288a4f67f73af3b4.diff

LOG: [X86] X86FixupInstTuning.cpp - fix comment in ProcessVPERMILPSri. NFC.

PERMILPS is only available on AVX or later (VEX/EVEX encoding)

Added: 
    

Modified: 
    llvm/lib/Target/X86/X86FixupInstTuning.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/X86FixupInstTuning.cpp b/llvm/lib/Target/X86/X86FixupInstTuning.cpp
index ab0dd72fd796..ba143a79a973 100644
--- a/llvm/lib/Target/X86/X86FixupInstTuning.cpp
+++ b/llvm/lib/Target/X86/X86FixupInstTuning.cpp
@@ -129,7 +129,7 @@ bool X86FixupInstTuningPass::processInstruction(
   // `vpermilps r, i` -> `vshufps r, r, i`
   // `vpermilps r, i, k` -> `vshufps r, r, i, k`
   // `vshufps` is always as fast or faster than `vpermilps` and takes
-  // 1 less byte of code size for VEX and SSE encoding.
+  // 1 less byte of code size for VEX and EVEX encoding.
   auto ProcessVPERMILPSri = [&](unsigned NewOpc) -> bool {
     if (!NewOpcPreferable(NewOpc))
       return false;