llvm-6502/test/CodeGen/X86/vec_uint_to_fp.ll
Nadav Rotem 06cc324b9d Add support for legalizing UINT_TO_FP of vectors on platforms which do
not have native support for this operation (such as X86).
The legalized code uses two vector INT_TO_FP operations and is faster
than scalarizing.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127951 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-19 13:09:10 +00:00

12 lines
281 B
LLVM

; RUN: llc < %s -march=x86 -mcpu=sandybridge | FileCheck %s
; Test that we are not lowering uinttofp to scalars
define <4 x float> @test1(<4 x i32> %A) nounwind {
; CHECK: test1:
; CHECK-NOT: cvtsd2ss
; CHECK: ret
%C = uitofp <4 x i32> %A to <4 x float>
ret <4 x float> %C
}