VPERMT2W (YMM, K, YMM, YMM) - Throughput and Uops (IACA 3.0)
With different registers for different operands
With 1 independent instruction
Throughput Analysis Report
--------------------------
Block Throughput: 6.80 Cycles Throughput Bottleneck: Backend
Loop Count: 38
Port Binding In Cycles Per Iteration:
--------------------------------------------------------------------------------------------------
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
--------------------------------------------------------------------------------------------------
| Cycles | 0.5 0.0 | 0.5 | 0.0 0.0 | 0.0 0.0 | 0.0 | 2.0 | 0.0 | 0.0 |
--------------------------------------------------------------------------------------------------
| Num Of | Ports pressure in cycles | |
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
-----------------------------------------------------------------------------------------
| 3 | 0.5 | 0.5 | | | | 2.0 | | | vpermt2w ymm0{k1}, ymm1, ymm2
Total Num Of Uops: 3
With 16 independent instructions
Throughput Analysis Report
--------------------------
Block Throughput: 31.89 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 | 8.0 0.0 | 8.0 | 0.0 0.0 | 0.0 0.0 | 0.0 | 32.0 | 0.0 | 0.0 |
--------------------------------------------------------------------------------------------------
| Num Of | Ports pressure in cycles | |
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
-----------------------------------------------------------------------------------------
| 3 | 1.0 | | | | | 2.0 | | | vpermt2w ymm0{k1}, ymm1, ymm2
| 3 | | 1.0 | | | | 2.0 | | | vpermt2w ymm3{k1}, ymm1, ymm2
| 3 | 1.0 | | | | | 2.0 | | | vpermt2w ymm4{k1}, ymm1, ymm2
| 3 | | 1.0 | | | | 2.0 | | | vpermt2w ymm5{k1}, ymm1, ymm2
| 3 | 1.0 | | | | | 2.0 | | | vpermt2w ymm6{k1}, ymm1, ymm2
| 3 | | 1.0 | | | | 2.0 | | | vpermt2w ymm7{k1}, ymm1, ymm2
| 3 | 1.0 | | | | | 2.0 | | | vpermt2w ymm8{k1}, ymm1, ymm2
| 3 | | 1.0 | | | | 2.0 | | | vpermt2w ymm9{k1}, ymm1, ymm2
| 3 | 1.0 | | | | | 2.0 | | | vpermt2w ymm10{k1}, ymm1, ymm2
| 3 | | 1.0 | | | | 2.0 | | | vpermt2w ymm11{k1}, ymm1, ymm2
| 3 | 1.0 | | | | | 2.0 | | | vpermt2w ymm12{k1}, ymm1, ymm2
| 3 | | 1.0 | | | | 2.0 | | | vpermt2w ymm16{k1}, ymm1, ymm2
| 3 | 1.0 | | | | | 2.0 | | | vpermt2w ymm17{k1}, ymm1, ymm2
| 3 | | 1.0 | | | | 2.0 | | | vpermt2w ymm18{k1}, ymm1, ymm2
| 3 | 1.0 | | | | | 2.0 | | | vpermt2w ymm19{k1}, ymm1, ymm2
| 3 | | 1.0 | | | | 2.0 | | | vpermt2w ymm20{k1}, ymm1, ymm2
Total Num Of Uops: 48
With the same register for for different operands
Throughput Analysis Report
--------------------------
Block Throughput: 6.80 Cycles Throughput Bottleneck: Backend
Loop Count: 38
Port Binding In Cycles Per Iteration:
--------------------------------------------------------------------------------------------------
| Port | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
--------------------------------------------------------------------------------------------------
| Cycles | 0.5 0.0 | 0.5 | 0.0 0.0 | 0.0 0.0 | 0.0 | 2.0 | 0.0 | 0.0 |
--------------------------------------------------------------------------------------------------
| Num Of | Ports pressure in cycles | |
| Uops | 0 - DV | 1 | 2 - D | 3 - D | 4 | 5 | 6 | 7 |
-----------------------------------------------------------------------------------------
| 3 | 0.5 | 0.5 | | | | 2.0 | | | vpermt2w ymm0{k1}, ymm0, ymm0
Total Num Of Uops: 3