mirror of
https://github.com/RPCS3/llvm.git
synced 2024-12-22 12:08:33 +00:00
ddbc274169
I followed three heuristics for deciding whether to set 'true' or 'false': - Everything target independent got 'true' as that is the expected common output of the GCC builtins. - If the target arch only has one way of implementing this operation, set the flag in the way that exercises the most of codegen. For most architectures this is also the likely path from a GCC builtin, with 'true' being set. It will (eventually) require lowering away that difference, and then lowering to the architecture's operation. - Otherwise, set the flag differently dependending on which target operation should be tested. Let me know if anyone has any issue with this pattern or would like specific tests of another form. This should allow the x86 codegen to just iteratively improve as I teach the backend how to differentiate between the two forms, and everything else should remain exactly the same. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146370 91177308-0d34-0410-b5e6-96231b3b80d8
13 lines
482 B
LLVM
13 lines
482 B
LLVM
; RUN: llc < %s -march=ppc64 -mcpu=g5 | grep cntlzd
|
|
|
|
define i32 @_ZNK4llvm5APInt17countLeadingZerosEv(i64 *%t) nounwind {
|
|
%tmp19 = load i64* %t
|
|
%tmp22 = tail call i64 @llvm.ctlz.i64( i64 %tmp19, i1 true ) ; <i64> [#uses=1]
|
|
%tmp23 = trunc i64 %tmp22 to i32
|
|
%tmp89 = add i32 %tmp23, -64 ; <i32> [#uses=1]
|
|
%tmp90 = add i32 %tmp89, 0 ; <i32> [#uses=1]
|
|
ret i32 %tmp90
|
|
}
|
|
|
|
declare i64 @llvm.ctlz.i64(i64, i1)
|