PANDN (XMM, M128) - Port Usage (IACA 2.2)
With blocking instructions for port '2':
Throughput Analysis Report
--------------------------
Block Throughput: 11.00 Cycles Throughput Bottleneck: PORT2_AGU, Port2_DATA
Port Binding In Cycles Per Iteration:
-------------------------------------------------------------------------
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 |
-------------------------------------------------------------------------
| Cycles | 0.3 0.0 | 0.3 | 11.0 11.0 | 0.0 0.0 | 0.0 | 0.3 |
-------------------------------------------------------------------------
| Num Of | Ports pressure in cycles | |
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | |
---------------------------------------------------------------------
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm1, dword ptr [r14+0x40]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm2, dword ptr [r14+0x44]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm3, dword ptr [r14+0x48]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm4, dword ptr [r14+0x4c]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm5, dword ptr [r14+0x50]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm6, dword ptr [r14+0x54]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm7, dword ptr [r14+0x58]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm8, dword ptr [r14+0x5c]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm9, dword ptr [r14+0x60]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm10, dword ptr [r14+0x64]
| 2^ | 0.3 | 0.3 | 1.0 1.0 | | | 0.3 | CP | pandn xmm0, xmmword ptr [r14]
Total Num Of Uops: 22
⇨ One μop that can only use port '2'
With blocking instructions for ports {'0', '1', '5'}:
Throughput Analysis Report
--------------------------
Block Throughput: 3.70 Cycles Throughput Bottleneck: Port0, Port1, Port5
Port Binding In Cycles Per Iteration:
-------------------------------------------------------------------------
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 |
-------------------------------------------------------------------------
| Cycles | 3.7 0.0 | 3.7 | 1.0 1.0 | 0.0 0.0 | 0.0 | 3.7 |
-------------------------------------------------------------------------
| Num Of | Ports pressure in cycles | |
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | |
---------------------------------------------------------------------
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm1, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm3, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm4, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm5, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm6, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm7, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm8, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm9, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm10, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm11, xmm2
| 2^ | 0.3 | 0.3 | 1.0 1.0 | | | 0.3 | CP | pandn xmm0, xmmword ptr [r14]
Total Num Of Uops: 12
⇨ One μop that can only use ports {'0', '1', '5'}
With an indexed addressing mode
With blocking instructions for port '2':
Throughput Analysis Report
--------------------------
Block Throughput: 11.00 Cycles Throughput Bottleneck: PORT2_AGU, Port2_DATA
Port Binding In Cycles Per Iteration:
-------------------------------------------------------------------------
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 |
-------------------------------------------------------------------------
| Cycles | 0.3 0.0 | 0.3 | 11.0 11.0 | 0.0 0.0 | 0.0 | 0.3 |
-------------------------------------------------------------------------
| Num Of | Ports pressure in cycles | |
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | |
---------------------------------------------------------------------
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm1, dword ptr [r14+0x40]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm2, dword ptr [r14+0x44]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm3, dword ptr [r14+0x48]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm4, dword ptr [r14+0x4c]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm5, dword ptr [r14+0x50]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm6, dword ptr [r14+0x54]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm7, dword ptr [r14+0x58]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm8, dword ptr [r14+0x5c]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm9, dword ptr [r14+0x60]
| 2*^ | | | 1.0 1.0 | | | | CP | cvtss2sd xmm10, dword ptr [r14+0x64]
| 2 | 0.3 | 0.3 | 1.0 1.0 | | | 0.3 | CP | pandn xmm0, xmmword ptr [r14+r13*1]
Total Num Of Uops: 22
⇨ One μop that can only use port '2'
With blocking instructions for ports {'0', '1', '5'}:
Throughput Analysis Report
--------------------------
Block Throughput: 3.70 Cycles Throughput Bottleneck: Port0, Port1, Port5
Port Binding In Cycles Per Iteration:
-------------------------------------------------------------------------
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 |
-------------------------------------------------------------------------
| Cycles | 3.7 0.0 | 3.7 | 1.0 1.0 | 0.0 0.0 | 0.0 | 3.7 |
-------------------------------------------------------------------------
| Num Of | Ports pressure in cycles | |
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | |
---------------------------------------------------------------------
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm1, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm3, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm4, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm5, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm6, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm7, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm8, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm9, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm10, xmm2
| 1 | 0.3 | 0.3 | | | | 0.3 | CP | movq xmm11, xmm2
| 2 | 0.3 | 0.3 | 1.0 1.0 | | | 0.3 | CP | pandn xmm0, xmmword ptr [r14+r13*1]
Total Num Of Uops: 12
⇨ One μop that can only use ports {'0', '1', '5'}