VMOVDQA (M256, YMM) - Port Usage (IACA 3.0)


With blocking instructions for port '4':

Throughput Analysis Report
--------------------------
Block Throughput: 11.00 Cycles       Throughput Bottleneck: Backend
Loop Count:  22
Port Binding In Cycles Per Iteration:
--------------------------------------------------------------------------------------------------
|  Port  |   0   -  DV   |   1   |   2   -  D    |   3   -  D    |   4   |   5   |   6   |   7   |
--------------------------------------------------------------------------------------------------
| Cycles |  0.0     0.0  |  0.0  |  3.7     0.0  |  3.6     0.0  | 11.0  |  0.0  |  0.0  |  3.7  |
--------------------------------------------------------------------------------------------------

| Num Of   |                    Ports pressure in cycles                         |      |
|  Uops    |  0  - DV    |  1   |  2  -  D    |  3  -  D    |  4   |  5   |  6   |  7   |
-----------------------------------------------------------------------------------------
|   2^     |             |      | 0.3         | 0.3         | 1.0  |      |      | 0.4  | mov qword ptr [r14+0x40], r8
|   2^     |             |      | 0.4         | 0.3         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x48], r8
|   2^     |             |      | 0.3         | 0.4         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x50], r8
|   2^     |             |      | 0.3         | 0.3         | 1.0  |      |      | 0.4  | mov qword ptr [r14+0x58], r8
|   2^     |             |      | 0.4         | 0.3         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x60], r8
|   2^     |             |      | 0.3         | 0.4         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x68], r8
|   2^     |             |      | 0.3         | 0.3         | 1.0  |      |      | 0.4  | mov qword ptr [r14+0x70], r8
|   2^     |             |      | 0.4         | 0.3         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x78], r8
|   2^     |             |      | 0.3         | 0.4         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x80], r8
|   2^     |             |      | 0.3         | 0.3         | 1.0  |      |      | 0.4  | mov qword ptr [r14+0x88], r8
|   2^     |             |      | 0.4         | 0.3         | 1.0  |      |      | 0.3  | vmovdqa ymmword ptr [r14], ymm0
Total Num Of Uops: 22
⇨ One μop that can only use port '4'

With blocking instructions for ports {'2', '3', '7'}:

Throughput Analysis Report
--------------------------
Block Throughput: 11.00 Cycles       Throughput Bottleneck: Backend
Loop Count:  22
Port Binding In Cycles Per Iteration:
--------------------------------------------------------------------------------------------------
|  Port  |   0   -  DV   |   1   |   2   -  D    |   3   -  D    |   4   |   5   |   6   |   7   |
--------------------------------------------------------------------------------------------------
| Cycles |  0.0     0.0  |  0.0  |  3.7     0.0  |  3.6     0.0  | 11.0  |  0.0  |  0.0  |  3.7  |
--------------------------------------------------------------------------------------------------

| Num Of   |                    Ports pressure in cycles                         |      |
|  Uops    |  0  - DV    |  1   |  2  -  D    |  3  -  D    |  4   |  5   |  6   |  7   |
-----------------------------------------------------------------------------------------
|   2^     |             |      | 0.3         | 0.3         | 1.0  |      |      | 0.4  | mov qword ptr [r14+0x40], r8
|   2^     |             |      | 0.4         | 0.3         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x48], r8
|   2^     |             |      | 0.3         | 0.4         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x50], r8
|   2^     |             |      | 0.3         | 0.3         | 1.0  |      |      | 0.4  | mov qword ptr [r14+0x58], r8
|   2^     |             |      | 0.4         | 0.3         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x60], r8
|   2^     |             |      | 0.3         | 0.4         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x68], r8
|   2^     |             |      | 0.3         | 0.3         | 1.0  |      |      | 0.4  | mov qword ptr [r14+0x70], r8
|   2^     |             |      | 0.4         | 0.3         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x78], r8
|   2^     |             |      | 0.3         | 0.4         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x80], r8
|   2^     |             |      | 0.3         | 0.3         | 1.0  |      |      | 0.4  | mov qword ptr [r14+0x88], r8
|   2^     |             |      | 0.4         | 0.3         | 1.0  |      |      | 0.3  | vmovdqa ymmword ptr [r14], ymm0
Total Num Of Uops: 22
⇨ One μop that can only use ports {'2', '3', '7'}

With an indexed addressing mode


With blocking instructions for port '4':

Throughput Analysis Report
--------------------------
Block Throughput: 11.00 Cycles       Throughput Bottleneck: Backend
Loop Count:  22
Port Binding In Cycles Per Iteration:
--------------------------------------------------------------------------------------------------
|  Port  |   0   -  DV   |   1   |   2   -  D    |   3   -  D    |   4   |   5   |   6   |   7   |
--------------------------------------------------------------------------------------------------
| Cycles |  0.0     0.0  |  0.0  |  3.7     0.0  |  3.6     0.0  | 11.0  |  0.0  |  0.0  |  3.7  |
--------------------------------------------------------------------------------------------------

| Num Of   |                    Ports pressure in cycles                         |      |
|  Uops    |  0  - DV    |  1   |  2  -  D    |  3  -  D    |  4   |  5   |  6   |  7   |
-----------------------------------------------------------------------------------------
|   2^     |             |      |             | 0.3         | 1.0  |      |      | 0.7  | mov qword ptr [r14+0x40], r8
|   2^     |             |      | 0.4         | 0.3         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x48], r8
|   2^     |             |      | 0.3         | 0.4         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x50], r8
|   2^     |             |      | 0.3         | 0.3         | 1.0  |      |      | 0.4  | mov qword ptr [r14+0x58], r8
|   2^     |             |      | 0.4         | 0.3         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x60], r8
|   2^     |             |      | 0.3         | 0.4         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x68], r8
|   2^     |             |      | 0.3         | 0.3         | 1.0  |      |      | 0.4  | mov qword ptr [r14+0x70], r8
|   2^     |             |      | 0.4         | 0.3         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x78], r8
|   2^     |             |      | 0.3         | 0.4         | 1.0  |      |      | 0.3  | mov qword ptr [r14+0x80], r8
|   2^     |             |      | 0.3         | 0.3         | 1.0  |      |      | 0.4  | mov qword ptr [r14+0x88], r8
|   2      |             |      | 0.7         | 0.3         | 1.0  |      |      |      | vmovdqa ymmword ptr [r14+r13*1], ymm0
Total Num Of Uops: 22
⇨ One μop that can only use port '4'

With blocking instructions for ports {'2', '3'}:

Throughput Analysis Report
--------------------------
Block Throughput: 5.47 Cycles       Throughput Bottleneck: Backend
Loop Count:  22
Port Binding In Cycles Per Iteration:
--------------------------------------------------------------------------------------------------
|  Port  |   0   -  DV   |   1   |   2   -  D    |   3   -  D    |   4   |   5   |   6   |   7   |
--------------------------------------------------------------------------------------------------
| Cycles |  0.0     0.0  |  0.0  |  5.5     5.0  |  5.5     5.0  |  1.0  |  0.0  |  0.0  |  0.0  |
--------------------------------------------------------------------------------------------------

| Num Of   |                    Ports pressure in cycles                         |      |
|  Uops    |  0  - DV    |  1   |  2  -  D    |  3  -  D    |  4   |  5   |  6   |  7   |
-----------------------------------------------------------------------------------------
|   1      |             |      | 0.5     0.5 | 0.5     0.5 |      |      |      |      | mov bh, byte ptr [rdi+0x40]
|   1      |             |      | 0.5     0.5 | 0.5     0.5 |      |      |      |      | mov ch, byte ptr [rdi+0x41]
|   1      |             |      | 0.5     0.5 | 0.5     0.5 |      |      |      |      | mov dh, byte ptr [rdi+0x42]
|   1      |             |      | 0.5     0.5 | 0.5     0.5 |      |      |      |      | mov ah, byte ptr [rdi+0x43]
|   1      |             |      | 0.5     0.5 | 0.5     0.5 |      |      |      |      | mov bh, byte ptr [rdi+0x40]
|   1      |             |      | 0.5     0.5 | 0.5     0.5 |      |      |      |      | mov ch, byte ptr [rdi+0x41]
|   1      |             |      | 0.5     0.5 | 0.5     0.5 |      |      |      |      | mov dh, byte ptr [rdi+0x42]
|   1      |             |      | 0.5     0.5 | 0.5     0.5 |      |      |      |      | mov ah, byte ptr [rdi+0x43]
|   1      |             |      | 0.5     0.5 | 0.5     0.5 |      |      |      |      | mov bh, byte ptr [rdi+0x40]
|   1      |             |      | 0.5     0.5 | 0.5     0.5 |      |      |      |      | mov ch, byte ptr [rdi+0x41]
|   2      |             |      | 0.5         | 0.5         | 1.0  |      |      |      | vmovdqa ymmword ptr [r14+r13*1], ymm0
Total Num Of Uops: 12
⇨ One μop that can only use ports {'2', '3'}