diff options
author | Adam Nemet <anemet@apple.com> | 2014-03-31 21:54:48 +0000 |
---|---|---|
committer | Adam Nemet <anemet@apple.com> | 2014-03-31 21:54:48 +0000 |
commit | 4ffbb65494d1991993c0fb7cc4f999e96a799af8 (patch) | |
tree | 2bc53a5f169ced178987d00a07f31d309eb0cbd5 /test/Transforms/LoopVectorize | |
parent | c779918bcdcc2ce0ec309c0e66c301cecd4cdf7d (diff) | |
download | llvm-4ffbb65494d1991993c0fb7cc4f999e96a799af8.tar.gz llvm-4ffbb65494d1991993c0fb7cc4f999e96a799af8.tar.bz2 llvm-4ffbb65494d1991993c0fb7cc4f999e96a799af8.tar.xz |
[X86] Adjust cost of FP_TO_UINT v4f64->v4i32 as well
Pretty obvious follow-on to r205159 to also handle conversion from double
besides float.
Fixes <rdar://problem/16373208>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205253 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/LoopVectorize')
-rw-r--r-- | test/Transforms/LoopVectorize/X86/fp64_to_uint32-cost-model.ll | 40 |
1 files changed, 40 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/X86/fp64_to_uint32-cost-model.ll b/test/Transforms/LoopVectorize/X86/fp64_to_uint32-cost-model.ll new file mode 100644 index 0000000000..ef3e3bec79 --- /dev/null +++ b/test/Transforms/LoopVectorize/X86/fp64_to_uint32-cost-model.ll @@ -0,0 +1,40 @@ +; RUN: opt < %s -mcpu=core-avx2 -loop-vectorize -S | llc -mcpu=core-avx2 | FileCheck %s + +target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-apple-macosx" + +@n = global i32 10000, align 4 +@double_array = common global [10000 x double] zeroinitializer, align 16 +@unsigned_array = common global [10000 x i32] zeroinitializer, align 16 + +; If we need to scalarize the fptoui and then use inserts to build up the +; vector again, then there is certainly no value in going 256-bit wide. +; CHECK-NOT: vpinsrd + +define void @convert() { +entry: + %0 = load i32* @n, align 4 + %cmp4 = icmp eq i32 %0, 0 + br i1 %cmp4, label %for.end, label %for.body.preheader + +for.body.preheader: ; preds = %entry + br label %for.body + +for.body: ; preds = %for.body.preheader, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ] + %arrayidx = getelementptr inbounds [10000 x double]* @double_array, i64 0, i64 %indvars.iv + %1 = load double* %arrayidx, align 8 + %conv = fptoui double %1 to i32 + %arrayidx2 = getelementptr inbounds [10000 x i32]* @unsigned_array, i64 0, i64 %indvars.iv + store i32 %conv, i32* %arrayidx2, align 4 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %2 = trunc i64 %indvars.iv.next to i32 + %cmp = icmp ult i32 %2, %0 + br i1 %cmp, label %for.body, label %for.end.loopexit + +for.end.loopexit: ; preds = %for.body + br label %for.end + +for.end: ; preds = %for.end.loopexit, %entry + ret void +} |