mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-21 20:12:56 +02:00
b9ecf8a3ee
This commit changes the interface of the vld[1234], vld[234]lane, and vst[1234], vst[234]lane ARM neon intrinsics and associates an address space with the pointer that these intrinsics take. This changes, e.g., <2 x i32> @llvm.arm.neon.vld1.v2i32(i8*, i32) to <2 x i32> @llvm.arm.neon.vld1.v2i32.p0i8(i8*, i32) This change ensures that address spaces are fully taken into account in the ARM target during lowering of interleaved loads and stores. Differential Revision: http://reviews.llvm.org/D12985 llvm-svn: 248887
22 lines
871 B
LLVM
22 lines
871 B
LLVM
; REQUIRES: asserts
|
|
; RUN: llc < %s -mtriple=thumbv7-apple-ios -disable-ifcvt-diamond -stats 2>&1 | FileCheck %s
|
|
; Evaluate the two vld1.8 instructions in separate MBB's,
|
|
; instead of stalling on one and conditionally overwriting its result.
|
|
;
|
|
; Update: After if-conversion the two vld1.8 instructions are in the same MBB
|
|
; again. So we disable this if-conversion to eliminate its influence to this
|
|
; test.
|
|
|
|
; CHECK-NOT: Number of pipeline stalls
|
|
define <16 x i8> @multiselect(i32 %avail, i8* %foo, i8* %bar) {
|
|
entry:
|
|
%vld1 = call <16 x i8> @llvm.arm.neon.vld1.v16i8.p0i8(i8* %foo, i32 1)
|
|
%vld2 = call <16 x i8> @llvm.arm.neon.vld1.v16i8.p0i8(i8* %bar, i32 1)
|
|
%and = and i32 %avail, 3
|
|
%tobool = icmp eq i32 %and, 0
|
|
%retv = select i1 %tobool, <16 x i8> %vld1, <16 x i8> %vld2
|
|
ret <16 x i8> %retv
|
|
}
|
|
|
|
declare <16 x i8> @llvm.arm.neon.vld1.v16i8.p0i8(i8* , i32 )
|