1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-01 13:11:39 +01:00
llvm-mirror/test/CodeGen/PowerPC/load-v4i8-improved.ll
Zaara Syeda d29969d956 [PowerPC] Improve codegen for vector loads using scalar_to_vector
This patch aims to improve the codegen for vector loads involving the
scalar_to_vector (load X) sequence. Initially, ld->mv instructions were used
for scalar_to_vector (load X), so this patch allows scalar_to_vector (load X)
to utilize:

LXSD and LXSDX for i64 and f64
LXSIWAX for i32 (sign extension to i64)
LXSIWZX for i32 and f64

Committing on behalf of Amy Kwan.
Differential Revision: https://reviews.llvm.org/D48950

llvm-svn: 339260
2018-08-08 15:20:43 +00:00

28 lines
1.2 KiB
LLVM

; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mtriple=powerpc64le-unknown-linux-gnu < %s \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names | FileCheck --check-prefix=CHECK-LE \
; RUN: -implicit-check-not vmrg -implicit-check-not=vperm %s
; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mtriple=powerpc64-unknown-linux-gnu < %s \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names | FileCheck \
; RUN: -implicit-check-not vmrg -implicit-check-not=vperm %s
define <16 x i8> @test(i32* %s, i32* %t) {
; CHECK-LE-LABEL: test:
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: lfiwzx f0, 0, r3
; CHECK-LE-NEXT: xxpermdi vs0, f0, f0, 2
; CHECK-LE-NEXT: xxspltw v2, vs0, 3
; CHECK-LE-NEXT: blr
; CHECK-LABEL: test:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lfiwzx f0, 0, r3
; CHECK-NEXT: xxsldwi vs0, f0, f0, 1
; CHECK-NEXT: xxspltw v2, vs0, 0
; CHECK-NEXT: blr
entry:
%0 = bitcast i32* %s to <4 x i8>*
%1 = load <4 x i8>, <4 x i8>* %0, align 4
%2 = shufflevector <4 x i8> %1, <4 x i8> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
ret <16 x i8> %2
}