From bae45d94d13ee0e4b8e041b4a10d82198298409d Mon Sep 17 00:00:00 2001
From: Bart Oldeman <bartoldeman@users.noreply.github.com>
Date: Tue, 29 Nov 2022 08:02:45 -0500
Subject: [PATCH] scal benchmark: eliminate y, move init/timing out of loop

Removing y avoids cache effects (if y is the size of the L1 cache, the
main array x is removed from it).
Moving init and timing out of the loop makes the scal benchmark behave like
the gemm benchmark, and allows higher accuracy for smaller test cases since
the loop overhead is much smaller than the timing overhead.

Example:
OPENBLAS_LOOPS=10000 ./dscal.goto 1024 8192 1024
on AMD Zen2 (7532) with 32k (4k doubles) L1 cache per core.

Before
From : 1024  To : 8192 Step = 1024 Inc_x = 1 Inc_y = 1 Loops = 10000
   SIZE       Flops
   1024 :     5627.08 MFlops   0.000000 sec
   2048 :     5907.34 MFlops   0.000000 sec
   3072 :     5553.30 MFlops   0.000001 sec
   4096 :     5446.38 MFlops   0.000001 sec
   5120 :     5504.61 MFlops   0.000001 sec
   6144 :     5501.80 MFlops   0.000001 sec
   7168 :     5547.43 MFlops   0.000001 sec
   8192 :     5548.46 MFlops   0.000001 sec

After
From : 1024  To : 8192 Step = 1024 Inc_x = 1 Inc_y = 1 Loops = 10000
   SIZE       Flops
   1024 :     6310.28 MFlops   0.000000 sec
   2048 :     6396.29 MFlops   0.000000 sec
   3072 :     6439.14 MFlops   0.000000 sec
   4096 :     6327.14 MFlops   0.000001 sec
   5120 :     5628.24 MFlops   0.000001 sec
   6144 :     5616.41 MFlops   0.000001 sec
   7168 :     5553.13 MFlops   0.000001 sec
   8192 :     5600.88 MFlops   0.000001 sec

We can see the L1->L2 switchover point is now where it should be, and the
number of flops for L1 is more accurate.
---
 benchmark/scal.c | 32 +++++++++-----------------------
 1 file changed, 9 insertions(+), 23 deletions(-)

diff --git a/benchmark/scal.c b/benchmark/scal.c
index 8de6cfd04..79bcb6729 100644
--- a/benchmark/scal.c
+++ b/benchmark/scal.c
@@ -45,7 +45,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 int main(int argc, char *argv[]){
 
-  FLOAT *x, *y;
+  FLOAT *x;
   FLOAT alpha[2] = { 2.0, 2.0 };
   blasint m, i;
   blasint inc_x=1,inc_y=1;
@@ -74,10 +74,6 @@ int main(int argc, char *argv[]){
     fprintf(stderr,"Out of Memory!!\n");exit(1);
   }
 
-  if (( y = (FLOAT *)malloc(sizeof(FLOAT) * to * abs(inc_y) * COMPSIZE)) == NULL){
-    fprintf(stderr,"Out of Memory!!\n");exit(1);
-  }
-
 #ifdef __linux
   srandom(getpid());
 #endif
@@ -91,30 +87,20 @@ int main(int argc, char *argv[]){
 
    fprintf(stderr, " %6d : ", (int)m);
 
+   for(i = 0; i < m * COMPSIZE * abs(inc_x); i++){
+	x[i] = ((FLOAT) rand() / (FLOAT) RAND_MAX) - 0.5;
+   }
 
+   begin();
    for (l=0; l<loops; l++)
    {
-
-   	for(i = 0; i < m * COMPSIZE * abs(inc_x); i++){
-			x[i] = ((FLOAT) rand() / (FLOAT) RAND_MAX) - 0.5;
-   	}
-
-   	for(i = 0; i < m * COMPSIZE * abs(inc_y); i++){
-			y[i] = ((FLOAT) rand() / (FLOAT) RAND_MAX) - 0.5;
-   	}
-    	begin();
-
     	SCAL (&m, alpha, x, &inc_x);
+   }
+   end();
 
-    	end();
+   time1 = getsec();
 
-    	time1 = getsec();
-
-	timeg += time1;
-
-    }
-
-    timeg /= loops;
+   timeg = time1 / loops;
 
 #ifdef COMPLEX
     fprintf(stderr, " %10.2f MFlops %10.6f sec\n", 6. * (double)m / timeg * 1.e-6, timeg);