./cpufp --thread_pool=[20]
Number Threads: 1
Thread Pool Binding: 20
--------------------------------------------------------------
| Instruction Set | Core Computation      | Peak Performance |
| AVX_VNNI        | DP4A(s32,u8,s8)       | 139.3 GOPS       |
| AVX_VNNI        | DP2A(s32,s16,s16)     | 69.222 GOPS      |
| FMA             | FMA(f32,f32,f32)      | 34.956 GFLOPS    |
| FMA             | FMA(f64,f64,f64)      | 17.595 GFLOPS    |
| AVX             | ADD(MUL(f32,f32),f32) | 17.464 GFLOPS    |
| AVX             | ADD(MUL(f64,f64),f64) | 8.7641 GFLOPS    |
| SSE             | ADD(MUL(f32,f32),f32) | 17.717 GFLOPS    |
| SSE2            | ADD(MUL(f64,f64),f64) | 8.6435 GFLOPS    |
--------------------------------------------------------------

./cpufp --thread_pool=[20,21]
Number Threads: 2
Thread Pool Binding: 20 21
--------------------------------------------------------------
| Instruction Set | Core Computation      | Peak Performance |
| AVX_VNNI        | DP4A(s32,u8,s8)       | 298.27 GOPS      |
| AVX_VNNI        | DP2A(s32,s16,s16)     | 149.24 GOPS      |
| FMA             | FMA(f32,f32,f32)      | 74.84 GFLOPS     |
| FMA             | FMA(f64,f64,f64)      | 37.259 GFLOPS    |
| AVX             | ADD(MUL(f32,f32),f32) | 37.011 GFLOPS    |
| AVX             | ADD(MUL(f64,f64),f64) | 18.686 GFLOPS    |
| SSE             | ADD(MUL(f32,f32),f32) | 37.204 GFLOPS    |
| SSE2            | ADD(MUL(f64,f64),f64) | 18.8 GFLOPS      |
--------------------------------------------------------------