| Loop Id: 410 | Module: exec | Source: BsplineFunctor.h:236-241 [...] | Coverage: 1.95% |
|---|
| Loop Id: 410 | Module: exec | Source: BsplineFunctor.h:236-241 [...] | Coverage: 1.95% |
|---|
0x42c2a0 VMOVUPD (%R13,%RSI,8),%YMM4 [2] |
0x42c2a7 VMOVUPD 0x20(%R13,%RSI,8),%YMM5 [2] |
0x42c2ae VMOVUPD 0x40(%R13,%RSI,8),%YMM6 [2] |
0x42c2b5 VMOVUPD 0x60(%R13,%RSI,8),%YMM7 [2] |
0x42c2bc LEA (%R12,%RSI,1),%EDI |
0x42c2c0 VPBROADCASTD %EDI,%YMM8 |
0x42c2c6 VPADDD %YMM12,%YMM8,%YMM9 |
0x42c2cb VPADDD %YMM11,%YMM8,%YMM8 |
0x42c2d0 VPCMPNEQD %YMM1,%YMM8,%K0 |
0x42c2d7 VPCMPNEQD %YMM1,%YMM9,%K2 |
0x42c2de VCMPPD $0x1,%YMM3,%YMM4,%K5 |
0x42c2e5 VCMPPD $0x1,%YMM3,%YMM5,%K1 |
0x42c2ec KMOVW %K1,0x20(%RSP) [4] |
0x42c2f2 KSHIFTLB $0x4,%K1,%K3 |
0x42c2f8 KORB %K3,%K5,%K3 |
0x42c2fc VCMPPD $0x1,%YMM3,%YMM6,%K6 |
0x42c303 VCMPPD $0x1,%YMM3,%YMM7,%K4 |
0x42c30a MOVSXD %R11D,%R11 |
0x42c30d LEA (%RDX,%R11,8),%RDI |
0x42c311 KANDB %K0,%K3,%K7 |
0x42c315 KMOVB %K7,%EAX |
0x42c319 KANDW %K2,%K6,%K7 |
0x42c31d POPCNT %EAX,%EAX |
0x42c321 VCOMPRESSPD %YMM6,(%RDI,%RAX,8){%K7} [3] |
0x42c328 KANDW %K0,%K5,%K5 |
0x42c32c VCOMPRESSPD %YMM4,(%RDX,%R11,8){%K5} [5] |
0x42c333 KSHIFTLB $0x4,%K4,%K1 |
0x42c339 KORB %K1,%K6,%K1 |
0x42c33d KMOVB %K7,0x16(%RSP) [4] |
0x42c343 KSHIFTRB $0x4,%K2,%K6 |
0x42c349 KANDW %K6,%K4,%K4 |
0x42c34d LEA (%RDI,%RAX,8),%RAX |
0x42c351 MOVZX 0x16(%RSP),%R8D [4] |
0x42c357 POPCNT %R8D,%R8D |
0x42c35c VCOMPRESSPD %YMM7,(%RAX,%R8,8){%K4} [1] |
0x42c363 KUNPCKBW %K3,%K1,%K1 |
0x42c367 KMOVB %K5,0x17(%RSP) [4] |
0x42c36d KUNPCKBW %K0,%K2,%K2 |
0x42c371 KSHIFTRB $0x4,%K0,%K0 |
0x42c377 KMOVW 0x20(%RSP),%K3 [4] |
0x42c37d KANDW %K0,%K3,%K3 |
0x42c381 MOVZX 0x17(%RSP),%EAX [4] |
0x42c386 POPCNT %EAX,%EAX |
0x42c38a VCOMPRESSPD %YMM5,(%RDI,%RAX,8){%K3} [3] |
0x42c391 KANDW %K2,%K1,%K0 |
0x42c395 KMOVW %K0,%EAX |
0x42c399 POPCNT %EAX,%EAX |
0x42c39d ADD %EAX,%R11D |
0x42c3a0 ADD $0x10,%RSI |
0x42c3a4 CMP %RBX,%RSI |
0x42c3a7 JB 42c2a0 |
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 236 - 241 |
-------------------------------------------------------------------------------- |
236: for (int jat = 0; jat < iLimit; jat++) |
237: { |
238: real_type r = distArray[jat]; |
239: // pick the distances smaller than the cutoff and avoid the reference atom |
240: if (r < cutoff_radius && iStart + jat != iat) |
241: distArrayCompressed[iCount++] = distArray[jat]; |
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 107 - 107 |
-------------------------------------------------------------------------------- |
107: for (int k = 0; k < ratios.size(); ++k) |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | qmcplusplus::WaveFunction::eva[...] | stl_vector.h:919 | exec |
| ○ | qmcplusplus::NonLocalPP<double[...] | NonLocalPP.hpp:135 | exec |
| ○ | main.extracted.107 | NewTimer.h:249 | exec |
| ○ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.54 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 3.08 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 2.00 |
| Bottlenecks | P5, |
| Function | miniqmcreference::TwoBodyJastrowRef |
| Source | BsplineFunctor.h:236-241,TwoBodyJastrowRef.h:107-107 |
| Source loop unroll info | unrolled by 16 |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | main |
| Unroll factor | 16 |
| CQA cycles | 20.00 |
| CQA cycles if no scalar integer | 13.00 |
| CQA cycles if FP arith vectorized | 20.00 |
| CQA cycles if fully vectorized | 6.50 |
| Front-end cycles | 9.67 |
| P0 cycles | 10.00 |
| P1 cycles | 6.00 |
| P2 cycles | 2.33 |
| P3 cycles | 2.33 |
| P4 cycles | 3.50 |
| P5 cycles | 20.00 |
| P6 cycles | 2.00 |
| P7 cycles | 3.50 |
| P8 cycles | 3.50 |
| P9 cycles | 3.50 |
| P10 cycles | 2.00 |
| P11 cycles | 2.33 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 2 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 51.00 |
| Nb uops | 58.00 |
| Nb loads | 7.00 |
| Nb stores | 7.00 |
| Nb stack references | 3.00 |
| 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 | 13.20 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 132.00 |
| Bytes stored | 132.00 |
| Stride 0 | 1.00 |
| Stride 1 | 1.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 3.00 |
| Vectorization ratio all | 94.12 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 100.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 85.71 |
| Vector-efficiency ratio all | 47.43 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | 50.00 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 43.75 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.54 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 3.08 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 2.00 |
| Bottlenecks | P5, |
| Function | miniqmcreference::TwoBodyJastrowRef |
| Source | BsplineFunctor.h:236-241,TwoBodyJastrowRef.h:107-107 |
| Source loop unroll info | unrolled by 16 |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | main |
| Unroll factor | 16 |
| CQA cycles | 20.00 |
| CQA cycles if no scalar integer | 13.00 |
| CQA cycles if FP arith vectorized | 20.00 |
| CQA cycles if fully vectorized | 6.50 |
| Front-end cycles | 9.67 |
| P0 cycles | 10.00 |
| P1 cycles | 6.00 |
| P2 cycles | 2.33 |
| P3 cycles | 2.33 |
| P4 cycles | 3.50 |
| P5 cycles | 20.00 |
| P6 cycles | 2.00 |
| P7 cycles | 3.50 |
| P8 cycles | 3.50 |
| P9 cycles | 3.50 |
| P10 cycles | 2.00 |
| P11 cycles | 2.33 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 2 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 51.00 |
| Nb uops | 58.00 |
| Nb loads | 7.00 |
| Nb stores | 7.00 |
| Nb stack references | 3.00 |
| 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 | 13.20 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 132.00 |
| Bytes stored | 132.00 |
| Stride 0 | 1.00 |
| Stride 1 | 1.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 3.00 |
| Vectorization ratio all | 94.12 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 100.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 85.71 |
| Vector-efficiency ratio all | 47.43 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | 50.00 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 43.75 |
| Path / |
| Function | miniqmcreference::TwoBodyJastrowRef |
| Source file and lines | BsplineFunctor.h:236-241 |
| Module | exec |
 |
| nb instructions | 51 |
| nb uops | 58 |
| loop length | 269 |
| used x86 registers | 10 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 10 |
| used zmm registers | 0 |
| nb stack references | 3 |
| micro-operation queue | 9.67 cycles |
| front end | 9.67 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 10.00 | 6.00 | 2.33 | 2.33 | 3.50 | 20.00 | 2.00 | 3.50 | 3.50 | 3.50 | 2.00 | 2.33 |
| cycles | 10.00 | 6.00 | 2.33 | 2.33 | 3.50 | 20.00 | 2.00 | 3.50 | 3.50 | 3.50 | 2.00 | 2.33 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 2.00 |
| Front-end | 9.67 |
| Dispatch | 20.00 |
| Data deps. | 2.00 |
| Overall L1 | 20.00 |
| all | 80% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 66% |
| 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 | 94% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 85% |
| all | 41% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 35% |
| all | 50% |
| load | 50% |
| store | 50% |
| 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 | 50% |
| all | 47% |
| load | 50% |
| store | 50% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 43% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%R13,%RSI,8),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| VMOVUPD 0x20(%R13,%RSI,8),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| VMOVUPD 0x40(%R13,%RSI,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| VMOVUPD 0x60(%R13,%RSI,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| LEA (%R12,%RSI,1),%EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 | N/A |
| VPBROADCASTD %EDI,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (6.3%) |
| VPADDD %YMM12,%YMM8,%YMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| VPADDD %YMM11,%YMM8,%YMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| VPCMPNEQD %YMM1,%YMM8,%K0 | vect (50.0%) | |||||||||||||||
| VPCMPNEQD %YMM1,%YMM9,%K2 | vect (50.0%) | |||||||||||||||
| VCMPPD $0x1,%YMM3,%YMM4,%K5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| VCMPPD $0x1,%YMM3,%YMM5,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| KMOVW %K1,0x20(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | N/A |
| KSHIFTLB $0x4,%K1,%K3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KORB %K3,%K5,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VCMPPD $0x1,%YMM3,%YMM6,%K6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| VCMPPD $0x1,%YMM3,%YMM7,%K4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| MOVSXD %R11D,%R11 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| LEA (%RDX,%R11,8),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| KANDB %K0,%K3,%K7 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| KMOVB %K7,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| KANDW %K2,%K6,%K7 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| POPCNT %EAX,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| VCOMPRESSPD %YMM6,(%RDI,%RAX,8){%K7} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KANDW %K0,%K5,%K5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VCOMPRESSPD %YMM4,(%RDX,%R11,8){%K5} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KSHIFTLB $0x4,%K4,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KORB %K1,%K6,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| KMOVB %K7,0x16(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | N/A |
| KSHIFTRB $0x4,%K2,%K6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KANDW %K6,%K4,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| LEA (%RDI,%RAX,8),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| MOVZX 0x16(%RSP),%R8D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| POPCNT %R8D,%R8D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| VCOMPRESSPD %YMM7,(%RAX,%R8,8){%K4} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KUNPCKBW %K3,%K1,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KMOVB %K5,0x17(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | N/A |
| KUNPCKBW %K0,%K2,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KSHIFTRB $0x4,%K0,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KMOVW 0x20(%RSP),%K3 | 3 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 | N/A |
| KANDW %K0,%K3,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| MOVZX 0x17(%RSP),%EAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| POPCNT %EAX,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| VCOMPRESSPD %YMM5,(%RDI,%RAX,8){%K3} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KANDW %K2,%K1,%K0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| KMOVW %K0,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| POPCNT %EAX,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| ADD %EAX,%R11D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| ADD $0x10,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| CMP %RBX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| JB 42c2a0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| Function | miniqmcreference::TwoBodyJastrowRef |
| Source file and lines | BsplineFunctor.h:236-241 |
| Module | exec |
|
| nb instructions | 51 |
| nb uops | 58 |
| loop length | 269 |
| used x86 registers | 10 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 10 |
| used zmm registers | 0 |
| nb stack references | 3 |
| micro-operation queue | 9.67 cycles |
| front end | 9.67 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 10.00 | 6.00 | 2.33 | 2.33 | 3.50 | 20.00 | 2.00 | 3.50 | 3.50 | 3.50 | 2.00 | 2.33 |
| cycles | 10.00 | 6.00 | 2.33 | 2.33 | 3.50 | 20.00 | 2.00 | 3.50 | 3.50 | 3.50 | 2.00 | 2.33 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 2.00 |
| Front-end | 9.67 |
| Dispatch | 20.00 |
| Data deps. | 2.00 |
| Overall L1 | 20.00 |
| all | 80% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 66% |
| 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 | 94% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 85% |
| all | 41% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 35% |
| all | 50% |
| load | 50% |
| store | 50% |
| 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 | 50% |
| all | 47% |
| load | 50% |
| store | 50% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 43% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%R13,%RSI,8),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| VMOVUPD 0x20(%R13,%RSI,8),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| VMOVUPD 0x40(%R13,%RSI,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| VMOVUPD 0x60(%R13,%RSI,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| LEA (%R12,%RSI,1),%EDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1-2 | 0.20 | N/A |
| VPBROADCASTD %EDI,%YMM8 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (6.3%) |
| VPADDD %YMM12,%YMM8,%YMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| VPADDD %YMM11,%YMM8,%YMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| VPCMPNEQD %YMM1,%YMM8,%K0 | vect (50.0%) | |||||||||||||||
| VPCMPNEQD %YMM1,%YMM9,%K2 | vect (50.0%) | |||||||||||||||
| VCMPPD $0x1,%YMM3,%YMM4,%K5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| VCMPPD $0x1,%YMM3,%YMM5,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| KMOVW %K1,0x20(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | N/A |
| KSHIFTLB $0x4,%K1,%K3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KORB %K3,%K5,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VCMPPD $0x1,%YMM3,%YMM6,%K6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| VCMPPD $0x1,%YMM3,%YMM7,%K4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| MOVSXD %R11D,%R11 | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| LEA (%RDX,%R11,8),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| KANDB %K0,%K3,%K7 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| KMOVB %K7,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| KANDW %K2,%K6,%K7 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| POPCNT %EAX,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| VCOMPRESSPD %YMM6,(%RDI,%RAX,8){%K7} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KANDW %K0,%K5,%K5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VCOMPRESSPD %YMM4,(%RDX,%R11,8){%K5} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KSHIFTLB $0x4,%K4,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KORB %K1,%K6,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| KMOVB %K7,0x16(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | N/A |
| KSHIFTRB $0x4,%K2,%K6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KANDW %K6,%K4,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| LEA (%RDI,%RAX,8),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| MOVZX 0x16(%RSP),%R8D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| POPCNT %R8D,%R8D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| VCOMPRESSPD %YMM7,(%RAX,%R8,8){%K4} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KUNPCKBW %K3,%K1,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KMOVB %K5,0x17(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 0.50 | N/A |
| KUNPCKBW %K0,%K2,%K2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KSHIFTRB $0x4,%K0,%K0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KMOVW 0x20(%RSP),%K3 | 3 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 | N/A |
| KANDW %K0,%K3,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| MOVZX 0x17(%RSP),%EAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| POPCNT %EAX,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| VCOMPRESSPD %YMM5,(%RDI,%RAX,8){%K3} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KANDW %K2,%K1,%K0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| KMOVW %K0,%EAX | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| POPCNT %EAX,%EAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| ADD %EAX,%R11D | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| ADD $0x10,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| CMP %RBX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| JB 42c2a0 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE14evaluateRatiosERNS1_18VirtualParticleSetERSt6vectorIdSaIdEE+0x2a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |