This patch fixes a bug whereby a vector like V8QImode {1,0,1,0,1,0,1,0} can
result in an instruction like
movi v1.4h, 0x1
whereas on bigendian this should be
movi v1.4h, 0x1, lsl 8
Regression tested on aarch64_be-none-elf: no changes in libstdc++, newlib; no
regressions in gcc or g++ and FAIL->PASS as listed below.
Ok for trunk (stage 4) ?
Cheers, Alan
gcc/ChangeLog:
2014-03-21 Alan Lawrence alan.lawre...@arm.com
* config/aarch64/aarch64.c (aarch64_simd_valid_immediate): reverse order
of elements for bigendian.
=====
FAIL->PASS in gcc testsuite:
c-c++-common/cilk-plus/PS/reduction-1.c -ftree-vectorize -fcilkplus -std=c99
execution test
gcc.c-torture/execute/20000112-1.c execution, -O0
gcc.c-torture/execute/900409-1.c execution, -O0
gcc.c-torture/execute/p18298.c execution, -O0
gcc.c-torture/execute/pr53645-2.c execution, -O1
gcc.c-torture/execute/pr53645-2.c execution, -O2
gcc.c-torture/execute/pr53645-2.c execution, -O2 -flto
gcc.c-torture/execute/pr53645-2.c execution, -O2 -flto -flto-partition=none
gcc.c-torture/execute/pr53645-2.c execution, -O2 -flto -fno-use-linker-plugin
-flto-partition=none
gcc.c-torture/execute/pr53645-2.c execution, -O2 -flto -fuse-linker-plugin
-fno-fat-lto-objects
gcc.c-torture/execute/pr53645-2.c execution, -O3 -fomit-frame-pointer
gcc.c-torture/execute/pr53645-2.c execution, -O3 -fomit-frame-pointer
-funroll-all-loops -finline-functions
gcc.c-torture/execute/pr53645-2.c execution, -O3 -fomit-frame-pointer
-funroll-loops
gcc.c-torture/execute/pr53645-2.c execution, -O3 -g
gcc.c-torture/execute/pr53645-2.c execution, -Og -g
gcc.c-torture/execute/pr53645-2.c execution, -Os
gcc.c-torture/execute/pr53645.c execution, -O1
gcc.c-torture/execute/pr53645.c execution, -O2
gcc.c-torture/execute/pr53645.c execution, -O2 -flto
gcc.c-torture/execute/pr53645.c execution, -O2 -flto -flto-partition=none
gcc.c-torture/execute/pr53645.c execution, -O2 -flto -fno-use-linker-plugin
-flto-partition=none
gcc.c-torture/execute/pr53645.c execution, -O2 -flto -fuse-linker-plugin
-fno-fat-lto-objects
gcc.c-torture/execute/pr53645.c execution, -O3 -fomit-frame-pointer
gcc.c-torture/execute/pr53645.c execution, -O3 -fomit-frame-pointer
-funroll-all-loops -finline-functions
gcc.c-torture/execute/pr53645.c execution, -O3 -fomit-frame-pointer
-funroll-loops
gcc.c-torture/execute/pr53645.c execution, -O3 -g
gcc.c-torture/execute/pr53645.c execution, -Og -g
FAIL->PASS in g++ testsuite:
g++.dg/torture/pr37922.C -O3 -fomit-frame-pointer execution test
g++.dg/torture/pr37922.C -O3 -fomit-frame-pointer -funroll-loops execution
test
g++.dg/torture/pr37922.C -O3 -fomit-frame-pointer -funroll-all-loops
-finline-functions execution test
g++.dg/torture/pr37922.C -O3 -g execution test
g++.dg/torture/pr37922.C -O3 -fomit-frame-pointer execution test
g++.dg/torture/pr37922.C -O3 -fomit-frame-pointer -funroll-loops execution
test
g++.dg/torture/pr37922.C -O3 -fomit-frame-pointer -funroll-all-loops
-finline-functions execution test
g++.dg/torture/pr37922.C -O3 -g execution test
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index f24b248..3166ebd 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -6563,7 +6563,9 @@ aarch64_simd_valid_immediate (rtx op, enum machine_mode mode, bool inverse,
/* Splat vector constant out into a byte vector. */
for (i = 0; i < n_elts; i++)
{
- rtx el = CONST_VECTOR_ELT (op, i);
+ /* The vector is provided in gcc endian-neutral fashion. For aarch64_be,
+ it must be laid out in the vector register in reverse order. */
+ rtx el = CONST_VECTOR_ELT (op, BYTES_BIG_ENDIAN ? (n_elts - 1 - i) : i);
unsigned HOST_WIDE_INT elpart;
unsigned int part, parts;
