From: Jim Grosbach <grosbach@apple.com>
Date: Thu, 27 Mar 2014 00:04:11 +0000 (+0000)
Subject: X86: Correct vectorization cost model for v8f32->v8i8.
X-Git-Url: http://plrg.eecs.uci.edu/git/?a=commitdiff_plain;h=f20d9ee6a65e3c1eea9ea9c7619e984628fe020b;p=oota-llvm.git

X86: Correct vectorization cost model for v8f32->v8i8.

Fix the cost model to reflect the reality of our codegen.

rdar://16370633

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@204880 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Target/X86/X86TargetTransformInfo.cpp b/lib/Target/X86/X86TargetTransformInfo.cpp
index 80f75cd6b6a..10e43780545 100644
--- a/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -513,7 +513,7 @@ unsigned X86TTI::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) const {
     { ISD::UINT_TO_FP,  MVT::v4f64, MVT::v4i16, 2 },
     { ISD::UINT_TO_FP,  MVT::v4f64, MVT::v4i32, 6 },
 
-    { ISD::FP_TO_SINT,  MVT::v8i8,  MVT::v8f32, 1 },
+    { ISD::FP_TO_SINT,  MVT::v8i8,  MVT::v8f32, 7 },
     { ISD::FP_TO_SINT,  MVT::v4i8,  MVT::v4f32, 1 },
   };
 
diff --git a/test/Transforms/LoopVectorize/X86/fp_to_sint8-cost-model.ll b/test/Transforms/LoopVectorize/X86/fp_to_sint8-cost-model.ll
new file mode 100644
index 00000000000..6bc3b4cf3f2
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/fp_to_sint8-cost-model.ll
@@ -0,0 +1,24 @@
+; RUN: opt < %s  -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -S -debug-only=loop-vectorize 2>&1 | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+
+; CHECK: cost of 7 for VF 8 For instruction:   %conv = fptosi float %tmp to i8
+define void @float_to_sint8_cost(i8* noalias nocapture %a, float* noalias nocapture readonly %b) nounwind {
+entry:
+  br label %for.body
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds float* %b, i64 %indvars.iv
+  %tmp = load float* %arrayidx, align 4
+  %conv = fptosi float %tmp to i8
+  %arrayidx2 = getelementptr inbounds i8* %a, i64 %indvars.iv
+  store i8 %conv, i8* %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 256
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:
+  ret void
+}