https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106069
--- Comment #20 from Xionghu Luo (luoxhu at gcc dot gnu.org) <yinyuefengyi at
gmail dot com> ---
Another reference is manually change the generated assembly with modifying the
source and index vspltw to verify:
luoxhu@gcc135 build $ diff q.bad.s q.good.s -U12
--- q.bad.s 2022-08-03 06:30:08.298451116 +0000
+++ q.good.s 2022-08-03 06:30:52.887250451 +0000
@@ -18,31 +18,31 @@
addi 2,2,.TOC.-.LCF0@l
.localentry _Z3fooPhPjDv4_jS1_S1_S1_,.-_Z3fooPhPjDv4_jS1_S1_S1_
mflr %r0
std %r0,16(%r1)
std %r30,-16(%r1)
std %r31,-8(%r1)
stdu %r1,-112(%r1)
.cfi_def_cfa_offset 112
.cfi_offset 65, 16
.cfi_offset 30, -16
.cfi_offset 31, -8
mr %r30,%r3
- vspltw %v0,%v2,0
+ vspltw %v0,%v5,3
mfvsrwz %r7,%vs32
- vspltw %v0,%v3,0
+ vspltw %v0,%v4,3
mfvsrwz %r6,%vs32
- vspltw %v0,%v4,0
+ vspltw %v0,%v3,3
mfvsrwz %r5,%vs32
- vspltw %v0,%v5,0
+ vspltw %v0,%v2,3
mfvsrwz %r31,%vs32
rldicl %r7,%r7,0,32
rldicl %r6,%r6,0,32
rldicl %r5,%r5,0,32
rldicl %r4,%r31,0,32
addis %r3,%r2,.LC0@toc@ha
addi %r3,%r3,.LC0@toc@l
bl printf
nop
stb %r31,0(%r30)
addi %r1,%r1,112
.cfi_def_cfa_offset 0
luoxhu@gcc135 build $ gcc q.good.s -o q.good
luoxhu@gcc135 build $ ./q.good
B0: 41fcef98, 91648e8b,7dca18c6,61707865
Which means both register and index are incorrectly used in LE nested
vec_select optimization.
