Hi all,
The neoversen1 tuning struct gives better performance on the Cortex-A76,
so use that.
The only difference from the current tuning is the function and label
alignment settings.
This gives about 1.3% improvement on SPEC2006 int and 0.3% on SPEC2006 fp.
Tested on aarch64-none-elf.
Ok for trunk?
Thanks,
Kyrill
2019-07-31 Kyrylo Tkachov <kyrylo.tkac...@arm.com>
* config/aarch64/aarch64-cores.def (cortex-a76): Use neoversen1 tuning
struct.
diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def
index 82d91d62519f0476e059718d8c2f02e3ea5a0613..bd257aeb34e7948caf729e5a684ddd9ceba457a4 100644
--- a/gcc/config/aarch64/aarch64-cores.def
+++ b/gcc/config/aarch64/aarch64-cores.def
@@ -99,7 +99,7 @@ AARCH64_CORE("thunderx2t99", thunderx2t99, thunderx2t99, 8_1A, AARCH64_FL_FOR
/* ARM ('A') cores. */
AARCH64_CORE("cortex-a55", cortexa55, cortexa53, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa53, 0x41, 0xd05, -1)
AARCH64_CORE("cortex-a75", cortexa75, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa73, 0x41, 0xd0a, -1)
-AARCH64_CORE("cortex-a76", cortexa76, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa72, 0x41, 0xd0b, -1)
+AARCH64_CORE("cortex-a76", cortexa76, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, neoversen1, 0x41, 0xd0b, -1)
AARCH64_CORE("ares", ares, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_PROFILE, neoversen1, 0x41, 0xd0c, -1)
AARCH64_CORE("neoverse-n1", neoversen1, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_PROFILE, neoversen1, 0x41, 0xd0c, -1)
AARCH64_CORE("neoverse-e1", neoversee1, cortexa53, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_SSBS, cortexa53, 0x41, 0xd4a, -1)
