procyberian/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

aarch64: Extend aarch64-autovec-preference==2 to 128-bit SVE

Browse source 
When compiling with -msve-vector-bits=128, aarch64_preferred_simd_mode
would pass the same vector width to aarch64_simd_container_mode for
both SVE and Advanced SIMD, and so Advanced SIMD would always “win”.
This patch instead makes it choose directly between SVE and Advanced
SIMD modes, so that aarch64-autovec-preference==2 and
aarch64-autovec-preference==4 work for this configuration.

(aarch64-autovec-preference shouldn't affect aarch64_simd_container_mode
because that would have an ABI impact for things like GNU vectors.)

gcc/
	* config/aarch64/aarch64.c (aarch64_preferred_simd_mode): Use
	aarch64_full_sve_mode and aarch64_vq_mode directly, instead of
	going via aarch64_simd_container_mode.
This commit is contained in:
Richard Sandiford 2020-12-18 16:33:43 +00:00
parent bcac28716b
commit 7ff5706fcd
1 changed files with 5 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
gcc/config/aarch64/aarch64.c
View file

@ -17421,10 +17421,11 @@ aarch64_preferred_simd_mode (scalar_mode mode)
{
/* Take into account explicit auto-vectorization ISA preferences through
aarch64_cmp_autovec_modes. */
poly_int64 bits
= (TARGET_SVE && aarch64_cmp_autovec_modes (VNx16QImode, V16QImode))
? BITS_PER_SVE_VECTOR : 128;
return aarch64_simd_container_mode (mode, bits);
if (TARGET_SVE && aarch64_cmp_autovec_modes (VNx16QImode, V16QImode))
return aarch64_full_sve_mode (mode).else_mode (word_mode);
if (TARGET_SIMD)
return aarch64_vq_mode (mode).else_mode (word_mode);
return word_mode;
}
/* Return a list of possible vector sizes for the vectorizer