maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

add a note 

llvm-svn: 27414
This commit is contained in:
Chris Lattner 2006-04-04 22:43:55 +00:00
parent 4a744e5c9d
commit 4464383a17
1 changed files with 13 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
llvm/lib/Target/PowerPC/README_ALTIVEC.txt
View File

@ -52,8 +52,6 @@ Missing intrinsics:
ds* ds*
mf* mf*
vavg* vavg*
vmax*
vmin*
vmladduhm vmladduhm
vmr* vmr*
vsel (some aliases only accessible using builtins) vsel (some aliases only accessible using builtins)
@ -64,6 +62,19 @@ FABS/FNEG can be codegen'd with the appropriate and/xor of -0.0.
//===----------------------------------------------------------------------===// //===----------------------------------------------------------------------===//
Codegen the constant here with something better than a constant pool load.
void %test_f(<4 x float>* %P, <4 x float>* %Q, float %X) {
%tmp = load <4 x float>* %Q
%tmp = cast <4 x float> %tmp to <4 x int>
%tmp1 = and <4 x int> %tmp, < int 2147483647, int 2147483647, int 2147483647, int 2147483647 >
%tmp2 = cast <4 x int> %tmp1 to <4 x float>
store <4 x float> %tmp2, <4 x float>* %P
ret void
}
//===----------------------------------------------------------------------===//
For functions that use altivec AND have calls, we are VRSAVE'ing all call For functions that use altivec AND have calls, we are VRSAVE'ing all call
clobbered regs. clobbered regs.