PCMPEQB (XMM, M128) - Throughput and Uops (IACA 2.1)


With a non-indexed addressing mode

With 1 independent instruction

Throughput Analysis Report
--------------------------
Block Throughput: 1.00 Cycles       Throughput Bottleneck: InterIteration

Port Binding In Cycles Per Iteration:
-------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |
-------------------------------------------------------------------------
| Cycles | 0.0    0.0  | 0.5  | 0.5    0.5  | 0.5    0.5  | 0.0  | 0.5  |
-------------------------------------------------------------------------


| Num Of |              Ports pressure in cycles               |    |
|  Uops  |  0  - DV  |  1  |  2  -  D  |  3  -  D  |  4  |  5  |    |
---------------------------------------------------------------------
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm0, xmmword ptr [r14]
Total Num Of Uops: 2

With 13 independent instructions


Throughput Analysis Report
--------------------------
Block Throughput: 6.50 Cycles       Throughput Bottleneck: Port1, PORT2_AGU, Port2_DATA, PORT3_AGU, Port3_DATA, Port5

Port Binding In Cycles Per Iteration:
-------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |
-------------------------------------------------------------------------
| Cycles | 0.0    0.0  | 6.5  | 6.5    6.5  | 6.5    6.5  | 0.0  | 6.5  |
-------------------------------------------------------------------------


| Num Of |              Ports pressure in cycles               |    |
|  Uops  |  0  - DV  |  1  |  2  -  D  |  3  -  D  |  4  |  5  |    |
---------------------------------------------------------------------
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm0, xmmword ptr [r14]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm1, xmmword ptr [r14+0x10]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm2, xmmword ptr [r14+0x20]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm3, xmmword ptr [r14+0x30]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm4, xmmword ptr [r14+0x40]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm5, xmmword ptr [r14+0x50]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm6, xmmword ptr [r14+0x60]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm7, xmmword ptr [r14+0x70]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm8, xmmword ptr [r14+0x80]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm9, xmmword ptr [r14+0x90]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm10, xmmword ptr [r14+0xa0]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm11, xmmword ptr [r14+0xb0]
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm12, xmmword ptr [r14+0xc0]
Total Num Of Uops: 26

With an indexed addressing mode

With 1 independent instruction

Throughput Analysis Report
--------------------------
Block Throughput: 1.00 Cycles       Throughput Bottleneck: InterIteration

Port Binding In Cycles Per Iteration:
-------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |
-------------------------------------------------------------------------
| Cycles | 0.0    0.0  | 0.5  | 0.5    0.5  | 0.5    0.5  | 0.0  | 0.5  |
-------------------------------------------------------------------------


| Num Of |              Ports pressure in cycles               |    |
|  Uops  |  0  - DV  |  1  |  2  -  D  |  3  -  D  |  4  |  5  |    |
---------------------------------------------------------------------
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm0, xmmword ptr [r14+r13*1]
Total Num Of Uops: 2

With 13 independent instructions


Throughput Analysis Report
--------------------------
Block Throughput: 6.50 Cycles       Throughput Bottleneck: FrontEnd, Port1, PORT2_AGU, Port2_DATA, PORT3_AGU, Port3_DATA, Port5

Port Binding In Cycles Per Iteration:
-------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |
-------------------------------------------------------------------------
| Cycles | 0.0    0.0  | 6.5  | 6.5    6.5  | 6.5    6.5  | 0.0  | 6.5  |
-------------------------------------------------------------------------


| Num Of |              Ports pressure in cycles               |    |
|  Uops  |  0  - DV  |  1  |  2  -  D  |  3  -  D  |  4  |  5  |    |
---------------------------------------------------------------------
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm0, xmmword ptr [r14+r13*1]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm1, xmmword ptr [r14+r13*1+0x10]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm2, xmmword ptr [r14+r13*1+0x20]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm3, xmmword ptr [r14+r13*1+0x30]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm4, xmmword ptr [r14+r13*1+0x40]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm5, xmmword ptr [r14+r13*1+0x50]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm6, xmmword ptr [r14+r13*1+0x60]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm7, xmmword ptr [r14+r13*1+0x70]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm8, xmmword ptr [r14+r13*1+0x80]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm9, xmmword ptr [r14+r13*1+0x90]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm10, xmmword ptr [r14+r13*1+0xa0]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm11, xmmword ptr [r14+r13*1+0xb0]
|   2    |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm12, xmmword ptr [r14+r13*1+0xc0]
Total Num Of Uops: 26

With the -no_interiteration flag

Throughput Analysis Report
--------------------------
Block Throughput: 0.50 Cycles       Throughput Bottleneck: Port1, PORT2_AGU, Port2_DATA, PORT3_AGU, Port3_DATA, Port5

Port Binding In Cycles Per Iteration:
-------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |
-------------------------------------------------------------------------
| Cycles | 0.0    0.0  | 0.5  | 0.5    0.5  | 0.5    0.5  | 0.0  | 0.5  |
-------------------------------------------------------------------------


| Num Of |              Ports pressure in cycles               |    |
|  Uops  |  0  - DV  |  1  |  2  -  D  |  3  -  D  |  4  |  5  |    |
---------------------------------------------------------------------
|   2^   |           | 0.5 | 0.5   0.5 | 0.5   0.5 |     | 0.5 | CP | pcmpeqb xmm0, xmmword ptr [r14]
Total Num Of Uops: 2