mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 04:22:57 +02:00
6d6e55b42f
For cases where we TRUNCATE and then ZERO_EXTEND to a larger size (often from vector legalization), see if we can mask the source data and then ZERO_EXTEND (instead of after a ANY_EXTEND). This can help avoid having to generate a larger mask, and possibly applying it to several sub-vectors. (zext (truncate x)) -> (zext (and(x, m)) Includes a minor patch to SystemZ to better recognise 8/16-bit zero extension patterns from RISBG bit-extraction code. This is the first of a number of minor patches to help improve the conversion of byte masks to clear mask shuffles. Differential Revision: http://reviews.llvm.org/D11764 llvm-svn: 245160
28 lines
746 B
LLVM
28 lines
746 B
LLVM
; RUN: llc < %s -march=arm64 -aarch64-neon-syntax=apple | FileCheck %s
|
|
|
|
;CHECK: @func30
|
|
;CHECK: movi.4h v1, #0x1
|
|
;CHECK: and.8b v0, v0, v1
|
|
;CHECK: ushll.4s v0, v0, #0
|
|
;CHECK: str q0, [x0]
|
|
;CHECK: ret
|
|
|
|
%T0_30 = type <4 x i1>
|
|
%T1_30 = type <4 x i32>
|
|
define void @func30(%T0_30 %v0, %T1_30* %p1) {
|
|
%r = zext %T0_30 %v0 to %T1_30
|
|
store %T1_30 %r, %T1_30* %p1
|
|
ret void
|
|
}
|
|
|
|
; Extend from v1i1 was crashing things (PR20791). Make sure we do something
|
|
; sensible instead.
|
|
define <1 x i32> @autogen_SD7918() {
|
|
; CHECK-LABEL: autogen_SD7918
|
|
; CHECK: movi d0, #0000000000000000
|
|
; CHECK-NEXT: ret
|
|
%I29 = insertelement <1 x i1> zeroinitializer, i1 false, i32 0
|
|
%ZE = zext <1 x i1> %I29 to <1 x i32>
|
|
ret <1 x i32> %ZE
|
|
}
|