llvm/test/CodeGen/X86/vec_ss_load_fold.ll
Dan Gohman ae3a0be92e Split the Add, Sub, and Mul instruction opcodes into separate
integer and floating-point opcodes, introducing
FAdd, FSub, and FMul.

For now, the AsmParser, BitcodeReader, and IRBuilder all preserve
backwards compatability, and the Core LLVM APIs preserve backwards
compatibility for IR producers. Most front-ends won't need to change
immediately.

This implements the first step of the plan outlined here:
http://nondot.org/sabre/LLVMNotes/IntegerOverflow.txt


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@72897 91177308-0d34-0410-b5e6-96231b3b80d8
2009-06-04 22:49:04 +00:00

42 lines
2.6 KiB
LLVM

; RUN: llvm-as < %s | llc -march=x86 -mattr=+sse,+sse2 -o %t -f
; RUN: grep minss %t | grep CPI | count 2
; RUN: grep CPI %t | not grep movss
target datalayout = "e-p:32:32"
target triple = "i686-apple-darwin8.7.2"
define i16 @test1(float %f) nounwind {
%tmp = insertelement <4 x float> undef, float %f, i32 0 ; <<4 x float>> [#uses=1]
%tmp10 = insertelement <4 x float> %tmp, float 0.000000e+00, i32 1 ; <<4 x float>> [#uses=1]
%tmp11 = insertelement <4 x float> %tmp10, float 0.000000e+00, i32 2 ; <<4 x float>> [#uses=1]
%tmp12 = insertelement <4 x float> %tmp11, float 0.000000e+00, i32 3 ; <<4 x float>> [#uses=1]
%tmp28 = tail call <4 x float> @llvm.x86.sse.sub.ss( <4 x float> %tmp12, <4 x float> < float 1.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp37 = tail call <4 x float> @llvm.x86.sse.mul.ss( <4 x float> %tmp28, <4 x float> < float 5.000000e-01, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp48 = tail call <4 x float> @llvm.x86.sse.min.ss( <4 x float> %tmp37, <4 x float> < float 6.553500e+04, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp59 = tail call <4 x float> @llvm.x86.sse.max.ss( <4 x float> %tmp48, <4 x float> zeroinitializer ) ; <<4 x float>> [#uses=1]
%tmp.upgrd.1 = tail call i32 @llvm.x86.sse.cvttss2si( <4 x float> %tmp59 ) ; <i32> [#uses=1]
%tmp69 = trunc i32 %tmp.upgrd.1 to i16 ; <i16> [#uses=1]
ret i16 %tmp69
}
define i16 @test2(float %f) nounwind {
%tmp28 = fsub float %f, 1.000000e+00 ; <float> [#uses=1]
%tmp37 = fmul float %tmp28, 5.000000e-01 ; <float> [#uses=1]
%tmp375 = insertelement <4 x float> undef, float %tmp37, i32 0 ; <<4 x float>> [#uses=1]
%tmp48 = tail call <4 x float> @llvm.x86.sse.min.ss( <4 x float> %tmp375, <4 x float> < float 6.553500e+04, float undef, float undef, float undef > ) ; <<4 x float>> [#uses=1]
%tmp59 = tail call <4 x float> @llvm.x86.sse.max.ss( <4 x float> %tmp48, <4 x float> < float 0.000000e+00, float undef, float undef, float undef > ) ; <<4 x float>> [#uses=1]
%tmp = tail call i32 @llvm.x86.sse.cvttss2si( <4 x float> %tmp59 ) ; <i32> [#uses=1]
%tmp69 = trunc i32 %tmp to i16 ; <i16> [#uses=1]
ret i16 %tmp69
}
declare <4 x float> @llvm.x86.sse.sub.ss(<4 x float>, <4 x float>)
declare <4 x float> @llvm.x86.sse.mul.ss(<4 x float>, <4 x float>)
declare <4 x float> @llvm.x86.sse.min.ss(<4 x float>, <4 x float>)
declare <4 x float> @llvm.x86.sse.max.ss(<4 x float>, <4 x float>)
declare i32 @llvm.x86.sse.cvttss2si(<4 x float>)