[llvm] r292612 - [CostModel][X86] Removed unused cost. NFCI.

[Simon Pilgrim via llvm-commits]

Author: rksimon
Date: Fri Jan 20 09:14:38 2017
New Revision: 292612

URL: http://llvm.org/viewvc/llvm-project?rev=292612&view=rev
Log:
[CostModel][X86] Removed unused cost. NFCI.

SHL v8i32 is already handled in the SSE41 cost table

Modified:
    llvm/trunk/lib/Target/X86/X86TargetTransformInfo.cpp

Modified: llvm/trunk/lib/Target/X86/X86TargetTransformInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86TargetTransformInfo.cpp?rev=292612&r1=292611&r2=292612&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86TargetTransformInfo.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86TargetTransformInfo.cpp Fri Jan 20 09:14:38 2017
@@ -611,7 +611,6 @@ int X86TTIImpl::getArithmeticInstrCost(
     { ISD::SHL,  MVT::v16i8,    26 }, // cmpgtb sequence.
     { ISD::SHL,  MVT::v8i16,    32 }, // cmpgtb sequence.
     { ISD::SHL,  MVT::v4i32,   2*5 }, // We optimized this using mul.
-    { ISD::SHL,  MVT::v8i32, 2*2*5 }, // We optimized this using mul.
     { ISD::SHL,  MVT::v2i64,     4 }, // splat+shuffle sequence.
     { ISD::SHL,  MVT::v4i64,   2*4 }, // splat+shuffle sequence.