Demonstrate multiple TOPS performance for Zen4 AMD CPUs

AVX512_VNNI.DP2A_s32_s16_s16.cpp

/*
f=AVX512_VNNI.DP2A_s32_s16_s16
g++ -O3 -fopenmp -Wall -Wextra -pedantic $f.cpp -o $f
cpplint --filter=-legal/copyright $f.cpp
cppcheck --enable=all --suppress=missingIncludeSystem $f.cpp --check-config

echo off | sudo tee /sys/devices/system/cpu/smt/control
echo 0 | sudo tee /proc/sys/kernel/perf_event_paranoid
perf stat -a -e fp_ops_retired_by_width.pack_512_uops_retired,cycles,instructions,task-clock ./$f

Outputs for "./f":
Performance:    2.23851 TOPS (Tera-Ops/sec)   on AMD 8840HS 8C laptop CPU  (at 4.400 GHz)
Performance:    5.12171 TOPS (Tera-Ops/sec)   on AMD 7950X 16C CPU         (at 5.013 GHz)

Outputs for "./f byte":
Performance:    4.17551 TOPS (Tera-Ops/sec)   on AMD 8840HS 8C laptop CPU  (at 4.116 GHz)
Performance:    10.2413 TOPS (Tera-Ops/sec)   on AMD 7950X 16C CPU         (at 5.013 GHz)
*/
#include <omp.h>
#include <inttypes.h>
#include <iostream>
#include <chrono>   // NOLINT [build/c++11]

int main(int argc, char**) {
  const int iterations = 2000000000;  // 2*10^9
  const bool byt = (argc > 1);

  std::cout << "Starting hardware-bound benchmark using "
            << omp_get_max_threads() << " threads...\n";

  auto start_time = std::chrono::high_resolution_clock::now();

  #pragma omp parallel
  {
    if (byt) {
      for (int i = 0; i < iterations; ++i) {
        asm __volatile__ ("vpdpbusd %%zmm0,  %%zmm0,  %%zmm0"  : : :  "zmm0");
        asm __volatile__ ("vpdpbusd %%zmm1,  %%zmm1,  %%zmm1"  : : :  "zmm1");
        asm __volatile__ ("vpdpbusd %%zmm2,  %%zmm2,  %%zmm2"  : : :  "zmm2");
        asm __volatile__ ("vpdpbusd %%zmm3,  %%zmm3,  %%zmm3"  : : :  "zmm3");
        asm __volatile__ ("vpdpbusd %%zmm4,  %%zmm4,  %%zmm4"  : : :  "zmm4");
      }
    } else {
      for (int i = 0; i < iterations; ++i) {
        asm __volatile__ ("vpdpwssd %%zmm0,  %%zmm0,  %%zmm0"  : : :  "zmm0");
        asm __volatile__ ("vpdpwssd %%zmm1,  %%zmm1,  %%zmm1"  : : :  "zmm1");
        asm __volatile__ ("vpdpwssd %%zmm2,  %%zmm2,  %%zmm2"  : : :  "zmm2");
        asm __volatile__ ("vpdpwssd %%zmm3,  %%zmm3,  %%zmm3"  : : :  "zmm3");
        asm __volatile__ ("vpdpwssd %%zmm4,  %%zmm4,  %%zmm4"  : : :  "zmm4");
      }
    }
  }

  std::cout << "... [AVX512_VNNI] DP2A(s32,s16,s16) completed\n";
  std::cout <<
    "https://www.officedaytime.com/simd512e/simdimg/vpdpwssd_3.png?v=22\n";

  std::chrono::duration<double> duration =
    std::chrono::high_resolution_clock::now() - start_time;

  int64_t mult_s16_per_vpdpwssd = 32 * (byt ? 2 : 1);
  int64_t add_s32_per_vpdpwssd = (16 + 16) * (byt ? 2 : 1);
  int64_t ops_per_vpdpwssd = mult_s16_per_vpdpwssd + add_s32_per_vpdpwssd;
  int64_t ops_per_loop = 5 * ops_per_vpdpwssd * omp_get_max_threads();
  int64_t total_ops = ops_per_loop * iterations;
  int64_t giga_cnt = total_ops / ops_per_vpdpwssd;
  double tera_ops = total_ops / 1e12;
  double performance = tera_ops / duration.count();

  std::cout << "-------------------------------------------\n";
  std::cout << "Execution Time: " << duration.count() << " seconds\n";
  std::cout.imbue(std::locale(""));
  std::cout << "Counter:        " << giga_cnt << "\n";
  std::cout << "Total Compute:  " << tera_ops
            << " Tera-Operations (counter * (32+16+16) * "
	    << (byt ? 2 : 1) << ")\n";
  std::cout << "Performance:    " << performance << " TOPS (Tera-Ops/sec)\n";
  std::cout << "-------------------------------------------\n";

  return 0;
}

With new "byte" option TOPS numbers double (multiplying 64 byte pairs vs. 32 word pairs):

hermann@7950x:~$ perf stat -a -e fp_ops_retired_by_width.pack_512_uops_retired,cycles,instructions,task-clock ./$f byte
Starting hardware-bound benchmark using 16 threads...
... [AVX512_VNNI] DP2A(s32,s16,s16) completed
https://www.officedaytime.com/simd512e/simdimg/vpdpwssd_3.png?v=22
-------------------------------------------
Execution Time: 1.99975 seconds
Counter:        160,000,000,000
Total Compute:  20.48 Tera-Operations (counter * (32+16+16) * 2)
Performance:    10.2413 TOPS (Tera-Ops/sec)
-------------------------------------------

 Performance counter stats for 'system wide':

   160,000,038,892      fp_ops_retired_by_width.pack_512_uops_retired #    4.997 G/sec                     
   160,518,614,310      cycles                           #    5.013 GHz                       
   224,246,479,090      instructions                     #    1.40  insn per cycle            
         32,018.54 msec task-clock                       #   16.000 CPUs utilized             

       2.001118241 seconds time elapsed

hermann@7950x:~$ 

hermann@8840hs:~$ perf stat -a -e fp_ops_retired_by_width.pack_512_uops_retired,cycles,instructions,task-clock ./$f byte
Starting hardware-bound benchmark using 8 threads...
... [AVX512_VNNI] DP2A(s32,s16,s16) completed
https://www.officedaytime.com/simd512e/simdimg/vpdpwssd_3.png?v=22
-------------------------------------------
Execution Time: 2.4524 seconds
Counter:        80,000,000,000
Total Compute:  10.24 Tera-Operations (counter * (32+16+16) * 2)
Performance:    4.17551 TOPS (Tera-Ops/sec)
-------------------------------------------

 Performance counter stats for 'system wide':

    80,001,396,997      fp_ops_retired_by_width.pack_512_uops_retired #    4.073 G/sec                     
    80,848,144,482      cycles                           #    4.116 GHz                       
   112,521,408,812      instructions                     #    1.39  insn per cycle            
    19,641,966,642      task-clock                       #    7.999 CPUs utilized             

       2.455592230 seconds time elapsed

hermann@8840hs:~$