| Loop Id: 256 | Module: exec | Source: pack_kernel.f90:62-66 | Coverage: 0.02% |
|---|
| Loop Id: 256 | Module: exec | Source: pack_kernel.f90:62-66 | Coverage: 0.02% |
|---|
0x432500 ADD -0x48(%RBP),%R14D |
0x432504 VPBROADCASTD %R14D,%YMM7 |
0x43250a LEA 0x1(%RBX),%RAX |
0x43250e IMUL %RAX,%R11 |
0x432512 LEA -0x1(%RBX,%RDX,1),%EAX |
0x432516 IMUL %EDX,%EAX |
0x432519 MOVSXD %EAX,%RBX |
0x43251c ADD %R12,%RBX |
0x43251f XOR %EAX,%EAX |
0x432521 VPBROADCASTQ %RAX,%ZMM8 |
0x432527 VPSUBQ %ZMM8,%ZMM0,%ZMM9 |
0x43252d VPCMPNLEUQ %ZMM1,%ZMM9,%K1 |
0x432534 VPMOVQD %ZMM8,%YMM8 |
0x43253a VPADDD %YMM7,%YMM8,%YMM7 |
0x43253e VPADDD %YMM2,%YMM7,%YMM7 |
0x432542 ADD %R11,%R9 |
0x432545 VPMOVSXDQ %YMM7,%ZMM7 |
0x43254b VPSUBQ %ZMM3,%ZMM7,%ZMM7 |
0x432551 VPMULLQ %ZMM7,%ZMM6,%ZMM6 |
0x432557 VPXOR %XMM7,%XMM7,%XMM7 |
0x43255b KMOVQ %K1,%K2 |
0x432560 VGATHERQPD (%R9,%ZMM6,1),%ZMM7{%K2} |
0x432567 ADD %RAX,%RBX |
0x43256a VPBROADCASTQ %RBX,%ZMM6 |
0x432570 VPADDQ %ZMM1,%ZMM6,%ZMM6 |
0x432576 VPMULLQ %ZMM6,%ZMM5,%ZMM5 |
0x43257c VSCATTERQPD %ZMM7,(%R10,%ZMM5,1){%K1} |
0x432583 JMP 432590 |
0x432590 LEA 0x1(%R8),%EAX |
0x432594 ADD %EDX,%EDI |
0x432596 CMP %R13D,%R8D |
0x432599 MOV %EAX,%R8D |
0x43259c JE 4323eb |
0x4325a2 TEST %EDX,%EDX |
0x4325a4 JLE 432590 |
0x4325a6 MOV -0x50(%RBP),%RAX |
0x4325aa ADD %R8D,%EAX |
0x4325ad MOV -0x70(%RBP),%RCX |
0x4325b1 MOVSXD (%RCX),%R12 |
0x4325b4 MOV -0x58(%RBP),%R11 |
0x4325b8 MOV (%R11),%R9 |
0x4325bb MOV 0x38(%R11),%R10 |
0x4325bf MOV -0x68(%RBP),%RCX |
0x4325c3 MOV (%RCX),%R14D |
0x4325c6 MOV 0x50(%R11),%R11 |
0x4325ca VPBROADCASTQ %R10,%ZMM6 |
0x4325d0 MOV -0x60(%RBP),%RCX |
0x4325d4 MOV 0x38(%RCX),%R10 |
0x4325d8 VPBROADCASTQ %R10,%ZMM5 |
0x4325de MOV (%RCX),%R10 |
0x4325e1 MOVSXD %EAX,%RBX |
0x4325e4 TEST %RSI,%RSI |
0x4325e7 JE 432500 |
0x4325ed MOVSXD %EDI,%RAX |
0x4325f0 LEA 0x1(%RBX),%R15 |
0x4325f4 IMUL %R15,%R11 |
0x4325f8 LEA (%R9,%R11,1),%R15 |
0x4325fc LEA -0x1(%RBX,%RDX,1),%EBX |
0x432600 IMUL %EDX,%EBX |
0x432603 MOVSXD %EBX,%RBX |
0x432606 ADD -0x48(%RBP),%R14D |
0x43260a ADD %R12,%RBX |
0x43260d ADD %R12,%RAX |
0x432610 XOR %R12D,%R12D |
0x432613 NOPW %CS:(%RAX,%RAX,1) |
(257) 0x432620 LEA (%R14,%R12,1),%ECX |
(257) 0x432624 VPBROADCASTD %ECX,%YMM7 |
(257) 0x43262a VPADDD %YMM2,%YMM7,%YMM7 |
(257) 0x43262e VPMOVSXDQ %YMM7,%ZMM7 |
(257) 0x432634 VPSUBQ %ZMM3,%ZMM7,%ZMM7 |
(257) 0x43263a VPMULLQ %ZMM7,%ZMM6,%ZMM7 |
(257) 0x432640 VXORPD %XMM8,%XMM8,%XMM8 |
(257) 0x432645 KXNORW %K0,%K0,%K1 |
(257) 0x432649 VGATHERQPD (%R15,%ZMM7,1),%ZMM8{%K1} |
(257) 0x432650 LEA (%RAX,%R12,1),%RCX |
(257) 0x432654 VPBROADCASTQ %RCX,%ZMM7 |
(257) 0x43265a VPADDQ %ZMM4,%ZMM7,%ZMM7 |
(257) 0x432660 VPMULLQ %ZMM7,%ZMM5,%ZMM7 |
(257) 0x432666 KXNORW %K0,%K0,%K1 |
(257) 0x43266a VSCATTERQPD %ZMM8,(%R10,%ZMM7,1){%K1} |
(257) 0x432671 ADD $0x8,%R12 |
(257) 0x432675 CMP %RSI,%R12 |
(257) 0x432678 JB 432620 |
0x43267a CMP %EDX,%ESI |
0x43267c JE 432590 |
0x432682 VPBROADCASTD %R14D,%YMM7 |
0x432688 MOV %RSI,%RAX |
0x43268b JMP 432521 |
/home/eoseret/qaas_runs_GNR/173-814-3702/intel/CloverLeaf1.3-FC/build/CloverLeaf1.3-FC/CloverLeaf_ref/kernels/pack_kernel.f90: 62 - 66 |
-------------------------------------------------------------------------------- |
62: DO k=y_min-depth,y_max+y_inc+depth |
63: !$OMP SIMD |
64: DO j=1,depth |
65: index= buffer_offset + j+(k+depth-1)*depth |
66: left_snd_buffer(index)=field(x_min+x_inc-1+j,k) |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.51 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.58 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.26 |
| Bottlenecks | |
| Function | pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source | pack_kernel.f90:62-66 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 9.04 |
| CQA cycles if no scalar integer | 6.00 |
| CQA cycles if FP arith vectorized | 9.04 |
| CQA cycles if fully vectorized | 5.71 |
| Front-end cycles | 9.04 |
| P0 cycles | 6.80 |
| P1 cycles | 5.50 |
| P2 cycles | 4.58 |
| P3 cycles | 4.58 |
| P4 cycles | 2.00 |
| P5 cycles | 6.78 |
| P6 cycles | 5.05 |
| P7 cycles | 2.00 |
| P8 cycles | 2.00 |
| P9 cycles | 2.00 |
| P10 cycles | 5.02 |
| P11 cycles | 4.58 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 40.00 |
| Nb uops | 54.25 |
| Nb loads | 10.25 |
| Nb stores | 0.50 |
| Nb stack references | 4.50 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 11.28 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 101.00 |
| Bytes stored | 32.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 24.11 |
| Vectorization ratio load | 15.00 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | 83.33 |
| Vectorization ratio add_sub | 33.48 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 18.54 |
| Vector-efficiency ratio all | 25.98 |
| Vector-efficiency ratio load | 21.77 |
| Vector-efficiency ratio store | 100.00 |
| Vector-efficiency ratio mul | 84.38 |
| Vector-efficiency ratio add_sub | 30.94 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 20.82 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 16.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.00 |
| Bottlenecks | micro-operation queue, P0, P1, P5, P6, P10, |
| Function | pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source | pack_kernel.f90:62-66 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 1.00 |
| CQA cycles if no scalar integer | 1.00 |
| CQA cycles if FP arith vectorized | 1.00 |
| CQA cycles if fully vectorized | 0.06 |
| Front-end cycles | 1.00 |
| P0 cycles | 1.00 |
| P1 cycles | 1.00 |
| P2 cycles | 0.00 |
| P3 cycles | 0.00 |
| P4 cycles | 0.00 |
| P5 cycles | 1.00 |
| P6 cycles | 1.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 1.00 |
| P11 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 7.00 |
| Nb uops | 6.00 |
| Nb loads | 0.00 |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | NA |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 6.25 |
| Vector-efficiency ratio load | NA |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 6.25 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 6.25 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.30 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.35 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.24 |
| Bottlenecks | micro-operation queue, |
| Function | pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source | pack_kernel.f90:62-66 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 13.67 |
| CQA cycles if no scalar integer | 10.50 |
| CQA cycles if FP arith vectorized | 13.67 |
| CQA cycles if fully vectorized | 10.10 |
| Front-end cycles | 13.67 |
| P0 cycles | 11.00 |
| P1 cycles | 6.80 |
| P2 cycles | 7.00 |
| P3 cycles | 7.00 |
| P4 cycles | 4.00 |
| P5 cycles | 11.00 |
| P6 cycles | 6.60 |
| P7 cycles | 4.00 |
| P8 cycles | 4.00 |
| P9 cycles | 4.00 |
| P10 cycles | 6.60 |
| P11 cycles | 7.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 53.00 |
| Nb uops | 82.00 |
| Nb loads | 14.00 |
| Nb stores | 1.00 |
| Nb stack references | 6.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 16.10 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 156.00 |
| Bytes stored | 64.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 46.43 |
| Vectorization ratio load | 20.00 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | 66.67 |
| Vectorization ratio add_sub | 62.50 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 38.46 |
| Vector-efficiency ratio all | 42.86 |
| Vector-efficiency ratio load | 26.25 |
| Vector-efficiency ratio store | 100.00 |
| Vector-efficiency ratio mul | 68.75 |
| Vector-efficiency ratio add_sub | 52.34 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 34.62 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.44 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.24 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.38 |
| Bottlenecks | micro-operation queue, |
| Function | pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source | pack_kernel.f90:62-66 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 15.17 |
| CQA cycles if no scalar integer | 10.50 |
| CQA cycles if FP arith vectorized | 15.17 |
| CQA cycles if fully vectorized | 12.20 |
| Front-end cycles | 15.17 |
| P0 cycles | 11.00 |
| P1 cycles | 8.40 |
| P2 cycles | 7.00 |
| P3 cycles | 7.00 |
| P4 cycles | 4.00 |
| P5 cycles | 11.00 |
| P6 cycles | 8.40 |
| P7 cycles | 4.00 |
| P8 cycles | 4.00 |
| P9 cycles | 4.00 |
| P10 cycles | 8.20 |
| P11 cycles | 7.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 61.00 |
| Nb uops | 91.00 |
| Nb loads | 14.00 |
| Nb stores | 1.00 |
| Nb stack references | 6.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 14.51 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 156.00 |
| Bytes stored | 64.00 |
| Stride 0 | 0.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 2.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 50.00 |
| Vectorization ratio load | 25.00 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | 100.00 |
| Vectorization ratio add_sub | 71.43 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 35.71 |
| Vector-efficiency ratio all | 45.67 |
| Vector-efficiency ratio load | 29.69 |
| Vector-efficiency ratio store | 100.00 |
| Vector-efficiency ratio mul | 100.00 |
| Vector-efficiency ratio add_sub | 58.93 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 33.04 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 3.17 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 13.87 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.09 |
| Bottlenecks | micro-operation queue, |
| Function | pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source | pack_kernel.f90:62-66 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 6.33 |
| CQA cycles if no scalar integer | 2.00 |
| CQA cycles if FP arith vectorized | 6.33 |
| CQA cycles if fully vectorized | 0.46 |
| Front-end cycles | 6.33 |
| P0 cycles | 4.20 |
| P1 cycles | 5.80 |
| P2 cycles | 4.33 |
| P3 cycles | 4.33 |
| P4 cycles | 0.00 |
| P5 cycles | 4.13 |
| P6 cycles | 4.20 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 4.27 |
| P11 cycles | 4.33 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 39.00 |
| Nb uops | 38.00 |
| Nb loads | 13.00 |
| Nb stores | 0.00 |
| Nb stack references | 6.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 14.53 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 92.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 0.00 |
| Stride n | 0.00 |
| Stride unknown | 2.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 9.13 |
| Vector-efficiency ratio load | 9.38 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 6.25 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 9.38 |
| Path / |
| Function | pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source file and lines | pack_kernel.f90:62-66 |
| Module | exec |
 |
| nb instructions | 40 |
| nb uops | 54.25 |
| loop length | 166.50 |
| used x86 registers | 12.25 |
| used mmx registers | 0 |
| used xmm registers | 0.50 |
| used ymm registers | 1.50 |
| used zmm registers | 4.50 |
| nb stack references | 4.50 |
| micro-operation queue | 9.04 cycles |
| front end | 9.04 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 6.80 | 5.10 | 4.58 | 4.58 | 2.00 | 6.78 | 5.05 | 2.00 | 2.00 | 2.00 | 5.02 | 4.58 |
| cycles | 6.80 | 5.50 | 4.58 | 4.58 | 2.00 | 6.78 | 5.05 | 2.00 | 2.00 | 2.00 | 5.02 | 4.58 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 9.04 |
| Dispatch | 7.20 |
| Data deps. | 1.00 |
| Overall L1 | 9.04 |
| all | 22% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 83% |
| add-sub | 33% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 16% |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 24% |
| load | 15% |
| store | 100% |
| mul | 83% |
| add-sub | 33% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 18% |
| all | 23% |
| load | 7% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 84% |
| add-sub | 30% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 18% |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 25% |
| load | 21% |
| store | 100% |
| mul | 84% |
| add-sub | 30% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 20% |
| Function | pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source file and lines | pack_kernel.f90:62-66 |
| Module | exec |
|
| nb instructions | 7 |
| nb uops | 6 |
| loop length | 22 |
| used x86 registers | 5 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 1.00 cycles |
| front end | 1.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.00 | 1.00 | 0.00 | 0.00 | 0.00 | 1.00 | 1.00 | 0.00 | 0.00 | 0.00 | 1.00 | 0.00 |
| cycles | 1.00 | 1.00 | 0.00 | 0.00 | 0.00 | 1.00 | 1.00 | 0.00 | 0.00 | 0.00 | 1.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 1.00 |
| Dispatch | 1.00 |
| Data deps. | 1.00 |
| Overall L1 | 1.00 |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 6% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 6% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 6% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LEA 0x1(%R8),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 | N/A |
| ADD %EDX,%EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (6.3%) |
| CMP %R13D,%R8D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (6.3%) |
| MOV %EAX,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| JE 4323eb <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x9b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| TEST %EDX,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 | N/A |
| JLE 432590 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x240> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| Function | pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source file and lines | pack_kernel.f90:62-66 |
| Module | exec |
|
| nb instructions | 53 |
| nb uops | 82 |
| loop length | 226 |
| used x86 registers | 14 |
| used mmx registers | 0 |
| used xmm registers | 1 |
| used ymm registers | 3 |
| used zmm registers | 8 |
| nb stack references | 6 |
| micro-operation queue | 13.67 cycles |
| front end | 13.67 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 11.00 | 6.80 | 7.00 | 7.00 | 4.00 | 11.00 | 6.60 | 4.00 | 4.00 | 4.00 | 6.60 | 7.00 |
| cycles | 11.00 | 6.80 | 7.00 | 7.00 | 4.00 | 11.00 | 6.60 | 4.00 | 4.00 | 4.00 | 6.60 | 7.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 13.67 |
| Dispatch | 11.00 |
| Data deps. | 1.00 |
| Overall L1 | 13.67 |
| all | 42% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 66% |
| add-sub | 62% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 33% |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 46% |
| load | 20% |
| store | 100% |
| mul | 66% |
| add-sub | 62% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 38% |
| all | 38% |
| load | 7% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 68% |
| add-sub | 52% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 29% |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 42% |
| load | 26% |
| store | 100% |
| mul | 68% |
| add-sub | 52% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 34% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD -0x48(%RBP),%R14D | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 | scal (6.3%) |
| VPBROADCASTD %R14D,%YMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (6.3%) |
| LEA 0x1(%RBX),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| IMUL %RAX,%R11 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| LEA -0x1(%RBX,%RDX,1),%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| IMUL %EDX,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (6.3%) |
| MOVSXD %EAX,%RBX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| ADD %R12,%RBX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | scal (6.3%) |
| VPBROADCASTQ %RAX,%ZMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (12.5%) |
| VPSUBQ %ZMM8,%ZMM0,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.50 | vect (100.0%) |
| VPCMPNLEUQ %ZMM1,%ZMM9,%K1 | vect (100.0%) | |||||||||||||||
| VPMOVQD %ZMM8,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
| VPADDD %YMM7,%YMM8,%YMM7 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| VPADDD %YMM2,%YMM7,%YMM7 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| ADD %R11,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| VPMOVSXDQ %YMM7,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| VPSUBQ %ZMM3,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.50 | vect (100.0%) |
| VPMULLQ %ZMM7,%ZMM6,%ZMM6 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 | vect (100.0%) |
| VPXOR %XMM7,%XMM7,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
| KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | N/A |
| VGATHERQPD (%R9,%ZMM6,1),%ZMM7{%K2} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 28 | 3 | vect (100.0%) |
| ADD %RAX,%RBX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| VPBROADCASTQ %RBX,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (12.5%) |
| VPADDQ %ZMM1,%ZMM6,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | vect (100.0%) |
| VPMULLQ %ZMM6,%ZMM5,%ZMM5 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 | vect (100.0%) |
| VSCATTERQPD %ZMM7,(%R10,%ZMM5,1){%K1} | 20 | 2.20 | 0.20 | 0 | 0 | 4 | 0.20 | 0.20 | 4 | 4 | 4 | 0.20 | 0 | 2-12 | 7 | vect (100.0%) |
| JMP 432590 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x240> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 | N/A |
| LEA 0x1(%R8),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 | N/A |
| ADD %EDX,%EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (6.3%) |
| CMP %R13D,%R8D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (6.3%) |
| MOV %EAX,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| JE 4323eb <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x9b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| TEST %EDX,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 | scal (6.3%) |
| JLE 432590 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x240> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| ADD %R8D,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (6.3%) |
| MOV -0x70(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOVSXD (%RCX),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (6.3%) |
| MOV -0x58(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV (%R11),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV 0x38(%R11),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV (%RCX),%R14D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (6.3%) |
| MOV 0x50(%R11),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| VPBROADCASTQ %R10,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (12.5%) |
| MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV 0x38(%RCX),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| VPBROADCASTQ %R10,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (12.5%) |
| MOV (%RCX),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOVSXD %EAX,%RBX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| TEST %RSI,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 | N/A |
| JE 432500 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x1b0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| Function | pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source file and lines | pack_kernel.f90:62-66 |
| Module | exec |
|
| nb instructions | 61 |
| nb uops | 91 |
| loop length | 266 |
| used x86 registers | 15 |
| used mmx registers | 0 |
| used xmm registers | 1 |
| used ymm registers | 3 |
| used zmm registers | 8 |
| nb stack references | 6 |
| micro-operation queue | 15.17 cycles |
| front end | 15.17 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 11.00 | 8.40 | 7.00 | 7.00 | 4.00 | 11.00 | 8.40 | 4.00 | 4.00 | 4.00 | 8.20 | 7.00 |
| cycles | 11.00 | 8.40 | 7.00 | 7.00 | 4.00 | 11.00 | 8.40 | 4.00 | 4.00 | 4.00 | 8.20 | 7.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 15.17 |
| Dispatch | 11.00 |
| Data deps. | 1.00 |
| Overall L1 | 15.17 |
| all | 45% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 100% |
| add-sub | 71% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 30% |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 50% |
| load | 25% |
| store | 100% |
| mul | 100% |
| add-sub | 71% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 35% |
| all | 41% |
| load | 6% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 100% |
| add-sub | 58% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 27% |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 45% |
| load | 29% |
| store | 100% |
| mul | 100% |
| add-sub | 58% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 33% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VPBROADCASTQ %RAX,%ZMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (12.5%) |
| VPSUBQ %ZMM8,%ZMM0,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.50 | vect (100.0%) |
| VPCMPNLEUQ %ZMM1,%ZMM9,%K1 | vect (100.0%) | |||||||||||||||
| VPMOVQD %ZMM8,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (100.0%) |
| VPADDD %YMM7,%YMM8,%YMM7 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| VPADDD %YMM2,%YMM7,%YMM7 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| ADD %R11,%R9 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| VPMOVSXDQ %YMM7,%ZMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| VPSUBQ %ZMM3,%ZMM7,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0-1 | 0.50 | vect (100.0%) |
| VPMULLQ %ZMM7,%ZMM6,%ZMM6 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 | vect (100.0%) |
| VPXOR %XMM7,%XMM7,%XMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | vect (25.0%) |
| KMOVQ %K1,%K2 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | N/A |
| VGATHERQPD (%R9,%ZMM6,1),%ZMM7{%K2} | 5 | 1 | 0 | 2.67 | 2.67 | 0 | 2 | 0 | 0 | 0 | 0 | 0 | 2.67 | 28 | 3 | vect (100.0%) |
| ADD %RAX,%RBX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| VPBROADCASTQ %RBX,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (12.5%) |
| VPADDQ %ZMM1,%ZMM6,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | vect (100.0%) |
| VPMULLQ %ZMM6,%ZMM5,%ZMM5 | 5 | 1.50 | 0 | 0 | 0 | 0 | 1.50 | 0 | 0 | 0 | 0 | 0 | 0 | 15 | 1.50 | vect (100.0%) |
| VSCATTERQPD %ZMM7,(%R10,%ZMM5,1){%K1} | 20 | 2.20 | 0.20 | 0 | 0 | 4 | 0.20 | 0.20 | 4 | 4 | 4 | 0.20 | 0 | 2-12 | 7 | vect (100.0%) |
| JMP 432590 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x240> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 | N/A |
| LEA 0x1(%R8),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 | N/A |
| ADD %EDX,%EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (6.3%) |
| CMP %R13D,%R8D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (6.3%) |
| MOV %EAX,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| JE 4323eb <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x9b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| TEST %EDX,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 | scal (6.3%) |
| JLE 432590 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x240> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| ADD %R8D,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| MOV -0x70(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOVSXD (%RCX),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (6.3%) |
| MOV -0x58(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV (%R11),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV 0x38(%R11),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV (%RCX),%R14D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (6.3%) |
| MOV 0x50(%R11),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| VPBROADCASTQ %R10,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (12.5%) |
| MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV 0x38(%RCX),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| VPBROADCASTQ %R10,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (12.5%) |
| MOV (%RCX),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOVSXD %EAX,%RBX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| TEST %RSI,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 | scal (12.5%) |
| JE 432500 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x1b0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| MOVSXD %EDI,%RAX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| LEA 0x1(%RBX),%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| IMUL %R15,%R11 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| LEA (%R9,%R11,1),%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| LEA -0x1(%RBX,%RDX,1),%EBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| IMUL %EDX,%EBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| MOVSXD %EBX,%RBX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| ADD -0x48(%RBP),%R14D | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 | scal (6.3%) |
| ADD %R12,%RBX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| ADD %R12,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| XOR %R12D,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | scal (6.3%) |
| NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| CMP %EDX,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| JE 432590 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x240> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| VPBROADCASTD %R14D,%YMM7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (6.3%) |
| MOV %RSI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| JMP 432521 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x1d1> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 | N/A |
| Function | pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101 |
| Source file and lines | pack_kernel.f90:62-66 |
| Module | exec |
|
| nb instructions | 39 |
| nb uops | 38 |
| loop length | 152 |
| used x86 registers | 15 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 2 |
| nb stack references | 6 |
| micro-operation queue | 6.33 cycles |
| front end | 6.33 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 4.20 | 4.20 | 4.33 | 4.33 | 0.00 | 4.13 | 4.20 | 0.00 | 0.00 | 0.00 | 4.27 | 4.33 |
| cycles | 4.20 | 5.80 | 4.33 | 4.33 | 0.00 | 4.13 | 4.20 | 0.00 | 0.00 | 0.00 | 4.27 | 4.33 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| Front-end | 6.33 |
| Dispatch | 5.80 |
| Data deps. | 1.00 |
| Overall L1 | 6.33 |
| all | 0% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 9% |
| load | 9% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 6% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 9% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LEA 0x1(%R8),%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 | N/A |
| ADD %EDX,%EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (6.3%) |
| CMP %R13D,%R8D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | scal (6.3%) |
| MOV %EAX,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| JE 4323eb <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x9b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| TEST %EDX,%EDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 | scal (6.3%) |
| JLE 432590 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x240> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| ADD %R8D,%EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| MOV -0x70(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOVSXD (%RCX),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (6.3%) |
| MOV -0x58(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV (%R11),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV 0x38(%R11),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| MOV -0x68(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV (%RCX),%R14D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (6.3%) |
| MOV 0x50(%R11),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| VPBROADCASTQ %R10,%ZMM6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (12.5%) |
| MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| MOV 0x38(%RCX),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VPBROADCASTQ %R10,%ZMM5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (12.5%) |
| MOV (%RCX),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| MOVSXD %EAX,%RBX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| TEST %RSI,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 | scal (12.5%) |
| JE 432500 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x1b0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| MOVSXD %EDI,%RAX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| LEA 0x1(%RBX),%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| IMUL %R15,%R11 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| LEA (%R9,%R11,1),%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| LEA -0x1(%RBX,%RDX,1),%EBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| IMUL %EDX,%EBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| MOVSXD %EBX,%RBX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| ADD -0x48(%RBP),%R14D | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 | scal (6.3%) |
| ADD %R12,%RBX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| ADD %R12,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| XOR %R12D,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | scal (6.3%) |
| NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| CMP %EDX,%ESI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| JE 432590 <pack_kernel_module_mp_clover_pack_message_left_.DIR.OMP.PARALLEL.LOOP.2.split101+0x240> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |