dzaima

instruction test sequences "scraped" from https://github.com/dougallj/applecpu / https://dougallj.github.io/applecpu/firestorm.html

  A53  A520  A720    X4 
 1.00  1.00  0.50  0.50 STR_reg_uxtw_64.html Test 2: throughput
 3.00  4.00  2.00  2.00 SQSUB_v_4S.html Test 2: Latency 1->2
 3.00  4.00  2.00  2.00 SQSUB_v_4S.html Test 3: Latency 1->3
 1.00  0.50  0.50  0.25 SQSUB_v_4S.html Test 4: throughput
 3.00  8.01  6.00  7.00 FCVTZS_s_fp_D_to_W.html Test 2: Latency 1->2 roundtrip
 1.00  1.00  1.00  1.00 FCVTZS_s_fp_D_to_W.html Test 3: throughput
 1.00  3.00  2.00  2.00 SLI_s_D.html Test 2: Latency 1->1

dzaima

#ifndef SEL
  #define SEL 2 // select between first and second image
#endif

#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <stdbool.h>
#include <immintrin.h>