Enable AVX512 512bit vectors by default on Zen4

Message ID Y977ZULaCk6iP74+@kam.mff.cuni.cz
State Committed
Commit a7502c4a614238ac3f80271886b217b156bdf923
Series Enable AVX512 512bit vectors by default on Zen4 |

Commit Message

Jan Hubicka Feb. 5, 2023, 12:42 a.m. UTC
this patch enables AVX512 by default on Zen4.  While internally 512
registers are splits into two 256 halves, 512 bit vectors reduces number
of instructions to retire and has chance to improve paralelism.
There are few tsvc benchmarks that improves significantly:

benchmark  256bit  512bit
s2275      48.57   20.67    -58%
s311       32.29   16.06    -50%
s312       32.30   16.07    -50%
vsumr      32.30   16.07    -50%
s314       10.77   5.42     -50%
s313       21.52   10.85    -50%
vdotr      43.05   21.69    -50%
s316       10.80   5.64     -48%
s235       61.72   33.91    -45%
s161       15.91   9.95     -38%
s3251      32.13   20.31    -36%

And there are no benchmarks with off-noise regression.  The basic matrix
multiplication loop improves by 32% (for 1000x1000 marices).  It is also
expected that 512 bit vectors are more power effecient (I can't masure

The down side is that loops with low trip counts slower for an iteration
ranges where the epilogue is hit more often.  In SPECfp this problem
happens with x264 (12% regression) and bwaves (6% regression) and this
is tracked in 
and will need more work on vectorizer to support masked epilogues.

After some additional testing it seems that using 512 bit vectors by
default is now overall better choice.

Bootstrapped/regtested x86_64-linux. Plan to commit it tomorrow.

	* config/i386/x86-tune.def (X86_TUNE_AVX256_OPTIMAL): Turn off
	for znver4.


diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index c78dad07c88..3054656a12c 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -551,7 +551,7 @@  DEF_TUNE (X86_TUNE_AVX128_OPTIMAL, "avx128_optimal", m_BDVER | m_BTVER2
 /* X86_TUNE_AVX256_OPTIMAL: Use 256-bit AVX instructions instead of 512-bit AVX
    instructions in the auto-vectorizer.  */
-DEF_TUNE (X86_TUNE_AVX256_OPTIMAL, "avx256_optimal", m_CORE_AVX512 | m_ZNVER4)
+DEF_TUNE (X86_TUNE_AVX256_OPTIMAL, "avx256_optimal", m_CORE_AVX512)
 /* X86_TUNE_AVX256_SPLIT_REGS: if true, AVX512 ops are split into two AVX256 ops.  */
 DEF_TUNE (X86_TUNE_AVX512_SPLIT_REGS, "avx512_split_regs", m_ZNVER4)