Hi,
this patch disables use of FMA in matrix multiplication loop for generic (for
x86-64-v3) and zen4. I tested this on zen4 and Xenon Gold Gold 6212U.
For Intel this is neutral both on the matrix multiplication microbenchmark
(attached) and spec2k17 where the difference was within noise for Core.
On core the micro-benchmark runs as follows:
With FMA:
578,500,241 cycles:u # 3.645 GHz
( +- 0.12% )
753,318,477 instructions:u # 1.30 insn per
cycle ( +- 0.00% )
125,417,701 branches:u # 790.227 M/sec
( +- 0.00% )
0.159146 +- 0.000363 seconds time elapsed ( +- 0.23% )
No FMA:
577,573,960 cycles:u # 3.514 GHz
( +- 0.15% )
878,318,479 instructions:u # 1.52 insn per
cycle ( +- 0.00% )
125,417,702 branches:u # 763.035 M/sec
( +- 0.00% )
0.164734 +- 0.000321 seconds time elapsed ( +- 0.19% )
So the cycle count is unchanged and discrete multiply+add takes same time as
FMA.
While on zen:
With FMA:
484875179 cycles:u # 3.599 GHz
( +- 0.05% ) (82.11%)
752031517 instructions:u # 1.55 insn per
cycle
125106525 branches:u # 928.712 M/sec
( +- 0.03% ) (85.09%)
128356 branch-misses:u # 0.10% of all
branches ( +- 0.06% ) (83.58%)
No FMA:
375875209 cycles:u # 3.592 GHz
( +- 0.08% ) (80.74%)
875725341 instructions:u # 2.33 insn per
cycle
124903825 branches:u # 1.194 G/sec
( +- 0.04% ) (84.59%)
0.105203 +- 0.000188 seconds time elapsed ( +- 0.18% )
The diffrerence is that Cores understand the fact that fmadd does not need
all three parameters to start computation, while Zen cores doesn't.
Since this seems noticeable win on zen and not loss on Core it seems like good
default for generic.
I plan to commit the patch next week if there are no compplains.
Honza
#include <stdio.h>
#include <time.h>
#define SIZE 1000
float a[SIZE][SIZE];
float b[SIZE][SIZE];
float c[SIZE][SIZE];
void init(void)
{
int i, j, k;
for(i=0; i<SIZE; ++i)
{
for(j=0; j<SIZE; ++j)
{
a[i][j] = (float)i + j;
b[i][j] = (float)i - j;
c[i][j] = 0.0f;
}
}
}
void mult(void)
{
int i, j, k;
for(i=0; i<SIZE; ++i)
{
for(j=0; j<SIZE; ++j)
{
for(k=0; k<SIZE; ++k)
{
c[i][j] += a[i][k] * b[k][j];
}
}
}
}
int main(void)
{
clock_t s, e;
init();
s=clock();
mult();
e=clock();
printf(" mult took %10d clocks\n", (int)(e-s));
return 0;
}
* confg/i386/x86-tune.def (X86_TUNE_AVOID_128FMA_CHAINS,
X86_TUNE_AVOID_256FMA_CHAINS)
Enable for znver4 and Core.
diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index 43fa9e8fd6d..74b03cbcc60 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -515,13 +515,13 @@ DEF_TUNE (X86_TUNE_USE_SCATTER_8PARTS,
"use_scatter_8parts",
/* X86_TUNE_AVOID_128FMA_CHAINS: Avoid creating loops with tight 128bit or
smaller FMA chain. */
-DEF_TUNE (X86_TUNE_AVOID_128FMA_CHAINS, "avoid_fma_chains", m_ZNVER1 |
m_ZNVER2 | m_ZNVER3
- | m_YONGFENG)
+DEF_TUNE (X86_TUNE_AVOID_128FMA_CHAINS, "avoid_fma_chains", m_ZNVER1 |
m_ZNVER2 | m_ZNVER3 | m_ZNVER4
+ | m_YONGFENG | m_GENERIC)
/* X86_TUNE_AVOID_256FMA_CHAINS: Avoid creating loops with tight 256bit or
smaller FMA chain. */
-DEF_TUNE (X86_TUNE_AVOID_256FMA_CHAINS, "avoid_fma256_chains", m_ZNVER2 |
m_ZNVER3
- | m_CORE_HYBRID | m_SAPPHIRERAPIDS | m_CORE_ATOM)
+DEF_TUNE (X86_TUNE_AVOID_256FMA_CHAINS, "avoid_fma256_chains", m_ZNVER2 |
m_ZNVER3 | m_ZNVER4
+ | m_CORE_HYBRID | m_SAPPHIRERAPIDS | m_CORE_ATOM | m_GENERIC)
/* X86_TUNE_AVOID_512FMA_CHAINS: Avoid creating loops with tight 512bit or
smaller FMA chain. */
