[X86][Vectorizer Cost Model] Correct vectorization cost model for v2i64->v2f64

and v4i64->v4f64.

The new costs match what we did for SSE2 and reflect the reality of our codegen.

<rdar://problem/16381225>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@204884 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86TargetTransformInfo.cpp b/lib/Target/X86/X86TargetTransformInfo.cpp
index 10e4378054591a72c7849f9de1c636df46b5c85c..2d44db0acdbc999cfe07d55aae7fd00d090dee84 100644 (file)
--- a/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -512,6 +512,8 @@ unsigned X86TTI::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) const {
     { ISD::UINT_TO_FP,  MVT::v4f64, MVT::v4i8,  2 },
     { ISD::UINT_TO_FP,  MVT::v4f64, MVT::v4i16, 2 },
     { ISD::UINT_TO_FP,  MVT::v4f64, MVT::v4i32, 6 },
+    { ISD::UINT_TO_FP,  MVT::v2f64, MVT::v2i64, 2*10 },
+    { ISD::UINT_TO_FP,  MVT::v4f64, MVT::v4i64, 4*10 },
 
     { 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/uint64_to_fp64-cost-model.ll b/test/Transforms/LoopVectorize/X86/uint64_to_fp64-cost-model.ll
new file mode 100644 (file)
index 0000000..86c32b2
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/uint64_to_fp64-cost-model.ll
@@ -0,0 +1,26 @@
+; RUN: opt < %s  -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -S -debug-only=loop-vectorize 2>&1 | FileCheck %s
+; REQUIRES: asserts
+
+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 20 for VF 2 For instruction:   %conv = uitofp i64 %tmp to double
+; CHECK: cost of 40 for VF 4 For instruction:   %conv = uitofp i64 %tmp to double
+define void @uint64_to_double_cost(i64* noalias nocapture %a, double* 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 i64* %a, i64 %indvars.iv
+  %tmp = load i64* %arrayidx, align 4
+  %conv = uitofp i64 %tmp to double
+  %arrayidx2 = getelementptr inbounds double* %b, i64 %indvars.iv
+  store double %conv, double* %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
+}