ADD (M8, I8) - Port Usage (IACA 2.3)


With blocking instructions for port 4:

Throughput Analysis Report
--------------------------
Block Throughput: 11.00 Cycles       Throughput Bottleneck: Backend. Port4

Port Binding In Cycles Per Iteration:
---------------------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |  6   |  7   |
---------------------------------------------------------------------------------------
| Cycles | 0.2    0.0  | 0.2  | 4.0    0.5  | 4.0    0.5  | 11.0 | 0.2  | 0.2  | 4.0  |
---------------------------------------------------------------------------------------


| Num Of |                    Ports pressure in cycles                     |    |
|  Uops  |  0  - DV  |  1  |  2  -  D  |  3  -  D  |  4  |  5  |  6  |  7  |    |
---------------------------------------------------------------------------------
|   2^   |           |     |           |           | 1.0 |     |     | 1.0 | CP | mov qword ptr [r14+0x40], r8
|   2^   |           |     | 1.0       |           | 1.0 |     |     |     | CP | mov qword ptr [r14+0x48], r8
|   2^   |           |     |           | 1.0       | 1.0 |     |     |     | CP | mov qword ptr [r14+0x50], r8
|   2^   |           |     |           |           | 1.0 |     |     | 1.0 | CP | mov qword ptr [r14+0x58], r8
|   2^   |           |     | 1.0       |           | 1.0 |     |     |     | CP | mov qword ptr [r14+0x60], r8
|   2^   |           |     |           | 1.0       | 1.0 |     |     |     | CP | mov qword ptr [r14+0x68], r8
|   2^   |           |     |           |           | 1.0 |     |     | 1.0 | CP | mov qword ptr [r14+0x70], r8
|   2^   |           |     | 1.0       |           | 1.0 |     |     |     | CP | mov qword ptr [r14+0x78], r8
|   2^   |           |     |           | 1.0       | 1.0 |     |     |     | CP | mov qword ptr [r14+0x80], r8
|   2^   |           |     |           |           | 1.0 |     |     | 1.0 | CP | mov qword ptr [r14+0x88], r8
|   4^   | 0.2       | 0.2 | 1.0   0.5 | 1.0   0.5 | 1.0 | 0.2 | 0.2 |     | CP | add byte ptr [r14], 0x2
Total Num Of Uops: 24
⇨ One μop that can only use port 4

With blocking instructions for ports {2, 3}:

Throughput Analysis Report
--------------------------
Block Throughput: 5.50 Cycles       Throughput Bottleneck: Backend. PORT2_AGU, Port2_DATA, PORT3_AGU, Port3_DATA

Port Binding In Cycles Per Iteration:
---------------------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |  6   |  7   |
---------------------------------------------------------------------------------------
| Cycles | 0.2    0.0  | 0.2  | 5.5    5.5  | 5.5    5.5  | 1.0  | 0.2  | 0.2  | 1.0  |
---------------------------------------------------------------------------------------


| 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 |     |     |     |     | CP | lddqu xmm0, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm1, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm2, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm3, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm4, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm5, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm6, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm7, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm8, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm9, xmmword ptr [r14+0x40]
|   4^   | 0.2       | 0.2 | 0.5   0.5 | 0.5   0.5 | 1.0 | 0.2 | 0.2 | 1.0 | CP | add byte ptr [r14], 0x2
Total Num Of Uops: 14
⇨ One μop that can only use ports {2, 3}

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

Throughput Analysis Report
--------------------------
Block Throughput: 13.00 Cycles       Throughput Bottleneck: Backend. Port4

Port Binding In Cycles Per Iteration:
---------------------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |  6   |  7   |
---------------------------------------------------------------------------------------
| Cycles | 0.2    0.0  | 0.2  | 4.7    0.5  | 4.7    0.5  | 13.0 | 0.2  | 0.2  | 4.7  |
---------------------------------------------------------------------------------------


| Num Of |                    Ports pressure in cycles                     |    |
|  Uops  |  0  - DV  |  1  |  2  -  D  |  3  -  D  |  4  |  5  |  6  |  7  |    |
---------------------------------------------------------------------------------
|   2^   |           |     | 0.3       | 0.2       | 1.0 |     |     | 0.4 | CP | mov qword ptr [r14+0x40], r8
|   2^   |           |     | 0.3       | 0.3       | 1.0 |     |     | 0.3 | CP | mov qword ptr [r14+0x48], r8
|   2^   |           |     | 0.3       | 0.3       | 1.0 |     |     | 0.3 | CP | mov qword ptr [r14+0x50], r8
|   2^   |           |     | 0.3       | 0.3       | 1.0 |     |     | 0.3 | CP | mov qword ptr [r14+0x58], r8
|   2^   |           |     | 0.3       | 0.3       | 1.0 |     |     | 0.3 | CP | mov qword ptr [r14+0x60], r8
|   2^   |           |     | 0.2       | 0.4       | 1.0 |     |     | 0.3 | CP | mov qword ptr [r14+0x68], r8
|   2^   |           |     | 0.4       | 0.2       | 1.0 |     |     | 0.3 | CP | mov qword ptr [r14+0x70], r8
|   2^   |           |     | 0.3       | 0.3       | 1.0 |     |     | 0.3 | CP | mov qword ptr [r14+0x78], r8
|   2^   |           |     | 0.3       | 0.3       | 1.0 |     |     | 0.3 | CP | mov qword ptr [r14+0x80], r8
|   2^   |           |     | 0.3       | 0.3       | 1.0 |     |     | 0.3 | CP | mov qword ptr [r14+0x88], r8
|   2^   |           |     | 0.3       | 0.3       | 1.0 |     |     | 0.3 | CP | mov qword ptr [r14+0x90], r8
|   2^   |           |     | 0.3       | 0.3       | 1.0 |     |     | 0.3 | CP | mov qword ptr [r14+0x98], r8
|   4^   | 0.2       | 0.2 | 0.6   0.5 | 0.9   0.5 | 1.0 | 0.2 | 0.2 | 0.5 | CP | add byte ptr [r14], 0x2
Total Num Of Uops: 28
⇨ One μop that can only use ports {2, 3, 7}

With blocking instructions for ports {0, 1, 5, 6}:

Throughput Analysis Report
--------------------------
Block Throughput: 4.48 Cycles       Throughput Bottleneck: FrontEnd

Port Binding In Cycles Per Iteration:
---------------------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |  6   |  7   |
---------------------------------------------------------------------------------------
| Cycles | 4.1    0.0  | 4.2  | 0.6    0.5  | 0.7    0.5  | 1.0  | 4.3  | 4.4  | 0.6  |
---------------------------------------------------------------------------------------


| Num Of |                    Ports pressure in cycles                     |    |
|  Uops  |  0  - DV  |  1  |  2  -  D  |  3  -  D  |  4  |  5  |  6  |  7  |    |
---------------------------------------------------------------------------------
|   1    | 0.2       | 0.3 |           |           |     | 0.2 | 0.3 |     | CP | mov r8w, 0x100
|   1    | 0.4       | 0.2 |           |           |     | 0.2 | 0.2 |     | CP | mov r9w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     | CP | mov r10w, 0x100
|   1    | 0.1       | 0.2 |           |           |     | 0.3 | 0.4 |     | CP | mov r11w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.3 | 0.2 |     | CP | mov r12w, 0x100
|   1    | 0.3       | 0.3 |           |           |     | 0.2 | 0.2 |     | CP | mov bx, 0x100
|   1    | 0.3       | 0.2 |           |           |     | 0.2 | 0.3 |     | CP | mov cx, 0x100
|   1    | 0.1       | 0.3 |           |           |     | 0.3 | 0.2 |     | CP | mov dx, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.3 | 0.2 |     | CP | mov di, 0x100
|   1    | 0.3       | 0.2 |           |           |     | 0.1 | 0.3 |     | CP | mov si, 0x100
|   1    | 0.3       | 0.2 |           |           |     | 0.2 | 0.2 |     | CP | mov r8w, 0x100
|   1    | 0.1       | 0.4 |           |           |     | 0.3 | 0.2 |     | CP | mov r9w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.3 | 0.2 |     | CP | mov r10w, 0x100
|   1    | 0.3       | 0.2 |           |           |     | 0.2 | 0.2 |     | CP | mov r11w, 0x100
|   1    | 0.3       | 0.2 |           |           |     | 0.2 | 0.2 |     | CP | mov r12w, 0x100
|   1    | 0.1       | 0.3 |           |           |     | 0.3 | 0.2 |     | CP | mov bx, 0x100
|   4^   | 0.2       | 0.2 | 0.6   0.5 | 0.7   0.5 | 1.0 | 0.3 | 0.2 | 0.6 | CP | add byte ptr [r14], 0x2
Total Num Of Uops: 20
⇨ One μop that can only use ports {0, 1, 5, 6}

With an indexed addressing mode


With blocking instructions for port 4:

Throughput Analysis Report
--------------------------
Block Throughput: 11.00 Cycles       Throughput Bottleneck: Backend. Port4

Port Binding In Cycles Per Iteration:
---------------------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |  6   |  7   |
---------------------------------------------------------------------------------------
| Cycles | 0.2    0.0  | 0.2  | 4.0    0.5  | 4.0    0.5  | 11.0 | 0.2  | 0.2  | 4.0  |
---------------------------------------------------------------------------------------


| Num Of |                    Ports pressure in cycles                     |    |
|  Uops  |  0  - DV  |  1  |  2  -  D  |  3  -  D  |  4  |  5  |  6  |  7  |    |
---------------------------------------------------------------------------------
|   2^   |           |     |           |           | 1.0 |     |     | 1.0 | CP | mov qword ptr [r14+0x40], r8
|   2^   |           |     | 1.0       |           | 1.0 |     |     |     | CP | mov qword ptr [r14+0x48], r8
|   2^   |           |     |           | 1.0       | 1.0 |     |     |     | CP | mov qword ptr [r14+0x50], r8
|   2^   |           |     |           |           | 1.0 |     |     | 1.0 | CP | mov qword ptr [r14+0x58], r8
|   2^   |           |     | 1.0       |           | 1.0 |     |     |     | CP | mov qword ptr [r14+0x60], r8
|   2^   |           |     |           | 1.0       | 1.0 |     |     |     | CP | mov qword ptr [r14+0x68], r8
|   2^   |           |     |           |           | 1.0 |     |     | 1.0 | CP | mov qword ptr [r14+0x70], r8
|   2^   |           |     | 1.0       |           | 1.0 |     |     |     | CP | mov qword ptr [r14+0x78], r8
|   2^   |           |     |           | 1.0       | 1.0 |     |     |     | CP | mov qword ptr [r14+0x80], r8
|   2^   |           |     |           |           | 1.0 |     |     | 1.0 | CP | mov qword ptr [r14+0x88], r8
|   4    | 0.2       | 0.2 | 1.0   0.5 | 1.0   0.5 | 1.0 | 0.2 | 0.2 |     | CP | add byte ptr [r14+r13*1], 0x2
Total Num Of Uops: 24
⇨ One μop that can only use port 4

With blocking instructions for ports {2, 3}:

Throughput Analysis Report
--------------------------
Block Throughput: 6.00 Cycles       Throughput Bottleneck: Backend. PORT2_AGU, PORT3_AGU

Port Binding In Cycles Per Iteration:
---------------------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |  6   |  7   |
---------------------------------------------------------------------------------------
| Cycles | 0.2    0.0  | 0.2  | 6.0    5.5  | 6.0    5.5  | 1.0  | 0.2  | 0.2  | 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 |     |     |     |     | CP | lddqu xmm0, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm1, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm2, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm3, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm4, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm5, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm6, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm7, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm8, xmmword ptr [r14+0x40]
|   1    |           |     | 0.5   0.5 | 0.5   0.5 |     |     |     |     | CP | lddqu xmm9, xmmword ptr [r14+0x40]
|   4    | 0.2       | 0.2 | 1.0   0.5 | 1.0   0.5 | 1.0 | 0.2 | 0.2 |     | CP | add byte ptr [r14+r13*1], 0x2
Total Num Of Uops: 14
⇨ 2 μops that can only use ports {2, 3}

With blocking instructions for ports {0, 1, 5, 6}:

Throughput Analysis Report
--------------------------
Block Throughput: 5.00 Cycles       Throughput Bottleneck: FrontEnd

Port Binding In Cycles Per Iteration:
---------------------------------------------------------------------------------------
|  Port  |  0   -  DV  |  1   |  2   -  D   |  3   -  D   |  4   |  5   |  6   |  7   |
---------------------------------------------------------------------------------------
| Cycles | 4.2    0.0  | 4.2  | 1.0    0.5  | 1.0    0.5  | 1.0  | 4.2  | 4.2  | 0.0  |
---------------------------------------------------------------------------------------


| Num Of |                    Ports pressure in cycles                     |    |
|  Uops  |  0  - DV  |  1  |  2  -  D  |  3  -  D  |  4  |  5  |  6  |  7  |    |
---------------------------------------------------------------------------------
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov r8w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov r9w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov r10w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov r11w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov r12w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov bx, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov cx, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov dx, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov di, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov si, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov r8w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov r9w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov r10w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov r11w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov r12w, 0x100
|   1    | 0.2       | 0.2 |           |           |     | 0.2 | 0.2 |     |    | mov bx, 0x100
|   4    | 0.2       | 0.2 | 1.0   0.5 | 1.0   0.5 | 1.0 | 0.2 | 0.2 |     |    | add byte ptr [r14+r13*1], 0x2
Total Num Of Uops: 20
⇨ One μop that can only use ports {0, 1, 5, 6}