| Loop Id: 348 | Module: exec | Source: BsplineFunctor.h:291-297 | Coverage: 0.45% |
|---|
| Loop Id: 348 | Module: exec | Source: BsplineFunctor.h:291-297 | Coverage: 0.45% |
|---|
0x41fc50 VMOVUPD (%R12,%R13,8),%YMM7 [3] |
0x41fc56 VMOVUPD 0x20(%R12,%R13,8),%YMM6 [3] |
0x41fc5d VMOVUPD 0x40(%R12,%R13,8),%YMM8 [3] |
0x41fc64 VMOVUPD 0x60(%R12,%R13,8),%YMM9 [3] |
0x41fc6b LEA (%RDX,%R13,1),%R11D |
0x41fc6f VPBROADCASTD %R11D,%YMM10 |
0x41fc75 VPADDD %YMM4,%YMM10,%YMM11 |
0x41fc79 VPADDD %YMM5,%YMM10,%YMM10 |
0x41fc7d VPCMPNEQD %YMM2,%YMM10,%K0 |
0x41fc84 VPCMPNEQD %YMM2,%YMM11,%K2 |
0x41fc8b VCMPPD $0x1,%YMM3,%YMM7,%K4 |
0x41fc92 VCMPPD $0x1,%YMM3,%YMM6,%K1 |
0x41fc99 KMOVW %K1,0x20(%RSP) [4] |
0x41fc9f KSHIFTLB $0x4,%K1,%K3 |
0x41fca5 KORB %K3,%K4,%K3 |
0x41fca9 VCMPPD $0x1,%YMM3,%YMM8,%K6 |
0x41fcb0 VPBROADCASTD %R13D,%YMM10 |
0x41fcb6 VPADDD %YMM5,%YMM10,%YMM11 |
0x41fcba MOVSXD %EBX,%RBX |
0x41fcbd KANDB %K0,%K3,%K5 |
0x41fcc1 VPCOMPRESSD %YMM11,(%R10,%RBX,4){%K5} [1] |
0x41fcc8 VCMPPD $0x1,%YMM3,%YMM9,%K7 |
0x41fccf KMOVB %K5,%R11D |
0x41fcd3 KSHIFTLB $0x4,%K7,%K5 |
0x41fcd9 KORB %K5,%K6,%K5 |
0x41fcdd VPADDD %YMM4,%YMM10,%YMM10 |
0x41fce1 LEA (%R10,%RBX,4),%RAX |
0x41fce5 POPCNT %R11D,%R9D |
0x41fcea KANDB %K2,%K5,%K1 |
0x41fcee VPCOMPRESSD %YMM10,(%RAX,%R9,4){%K1} [6] |
0x41fcf5 LEA (%RCX,%RBX,8),%R11 |
0x41fcf9 KANDW %K2,%K6,%K1 |
0x41fcfd VCOMPRESSPD %YMM8,(%R11,%R9,8){%K1} [2] |
0x41fd04 KANDW %K0,%K4,%K4 |
0x41fd08 VCOMPRESSPD %YMM7,(%RCX,%RBX,8){%K4} [7] |
0x41fd0f KMOVB %K1,0x1f(%RSP) [4] |
0x41fd15 KSHIFTRB $0x4,%K2,%K1 |
0x41fd1b KANDW %K1,%K7,%K1 |
0x41fd1f LEA (%R11,%R9,8),%RAX |
0x41fd23 MOVZX 0x1f(%RSP),%R9D [4] |
0x41fd29 POPCNT %R9D,%R9D |
0x41fd2e VCOMPRESSPD %YMM9,(%RAX,%R9,8){%K1} [5] |
0x41fd35 KUNPCKBW %K3,%K5,%K1 |
0x41fd39 KMOVB %K4,0x1e(%RSP) [4] |
0x41fd3f KUNPCKBW %K0,%K2,%K2 |
0x41fd43 KSHIFTRB $0x4,%K0,%K0 |
0x41fd49 KMOVW 0x20(%RSP),%K3 [4] |
0x41fd4f KANDW %K0,%K3,%K3 |
0x41fd53 MOVZX 0x1e(%RSP),%EAX [4] |
0x41fd58 POPCNT %EAX,%EAX |
0x41fd5c VCOMPRESSPD %YMM6,(%R11,%RAX,8){%K3} [2] |
0x41fd63 KANDW %K2,%K1,%K0 |
0x41fd67 KMOVW %K0,%EAX |
0x41fd6b POPCNT %EAX,%EAX |
0x41fd6f ADD %EAX,%EBX |
0x41fd71 ADD $0x10,%R13 |
0x41fd75 CMP %R14,%R13 |
0x41fd78 JB 41fc50 |
/home/eoseret/qaas_runs_GNR/173-773-5521/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/BsplineFunctor.h: 291 - 297 |
-------------------------------------------------------------------------------- |
291: for (int jat = 0; jat < iLimit; jat++) |
292: { |
293: real_type r = distArray[jat]; |
294: if (r < cutoff_radius && iStart + jat != iat) |
295: { |
296: distIndices[iCount] = jat; |
297: distArrayCompressed[iCount] = r; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►52.87+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:274 | exec |
| ○ | qmcplusplus::WaveFunction::acc[...] | NewTimer.h:249 | exec |
| ○ | main.extracted.107 | refwrap.h:338 | exec |
| ○ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so | |
| ►40.72+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:274 | exec |
| ○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:201 | exec |
| ○ | main.extracted.107 | refwrap.h:338 | exec |
| ○ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so | |
| ►5.98+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:274 | exec |
| ○ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:411 | exec |
| ○ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:175 | exec |
| ○ | main.extracted.112 | miniqmc.cpp:397 | exec |
| ○ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_invoke_task_func | libiomp5.so |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.39 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 2.92 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 2.17 |
| Bottlenecks | P5, |
| Function | qmcplusplus::BsplineFunctor |
| Source | BsplineFunctor.h:291-297 |
| Source loop unroll info | unrolled by 16 |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | main |
| Unroll factor | 16 |
| CQA cycles | 25.00 |
| CQA cycles if no scalar integer | 18.00 |
| CQA cycles if FP arith vectorized | 25.00 |
| CQA cycles if fully vectorized | 8.56 |
| Front-end cycles | 11.50 |
| P0 cycles | 11.00 |
| P1 cycles | 8.00 |
| P2 cycles | 2.33 |
| P3 cycles | 2.33 |
| P4 cycles | 4.50 |
| P5 cycles | 25.00 |
| P6 cycles | 2.00 |
| P7 cycles | 4.50 |
| P8 cycles | 4.50 |
| P9 cycles | 4.50 |
| 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 | 58.00 |
| Nb uops | 69.00 |
| Nb loads | 7.00 |
| Nb stores | 9.00 |
| 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 | 13.12 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 132.00 |
| Bytes stored | 196.00 |
| Stride 0 | 1.00 |
| Stride 1 | 1.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 5.00 |
| Vectorization ratio all | 90.91 |
| 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 | 75.00 |
| Vector-efficiency ratio all | 46.02 |
| 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 | 39.06 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.39 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 2.92 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 2.17 |
| Bottlenecks | P5, |
| Function | qmcplusplus::BsplineFunctor |
| Source | BsplineFunctor.h:291-297 |
| Source loop unroll info | unrolled by 16 |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | main |
| Unroll factor | 16 |
| CQA cycles | 25.00 |
| CQA cycles if no scalar integer | 18.00 |
| CQA cycles if FP arith vectorized | 25.00 |
| CQA cycles if fully vectorized | 8.56 |
| Front-end cycles | 11.50 |
| P0 cycles | 11.00 |
| P1 cycles | 8.00 |
| P2 cycles | 2.33 |
| P3 cycles | 2.33 |
| P4 cycles | 4.50 |
| P5 cycles | 25.00 |
| P6 cycles | 2.00 |
| P7 cycles | 4.50 |
| P8 cycles | 4.50 |
| P9 cycles | 4.50 |
| 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 | 58.00 |
| Nb uops | 69.00 |
| Nb loads | 7.00 |
| Nb stores | 9.00 |
| 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 | 13.12 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 132.00 |
| Bytes stored | 196.00 |
| Stride 0 | 1.00 |
| Stride 1 | 1.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 5.00 |
| Vectorization ratio all | 90.91 |
| 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 | 75.00 |
| Vector-efficiency ratio all | 46.02 |
| 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 | 39.06 |
| Path / |
| Function | qmcplusplus::BsplineFunctor |
| Source file and lines | BsplineFunctor.h:291-297 |
| Module | exec |
 |
| nb instructions | 58 |
| nb uops | 69 |
| loop length | 302 |
| used x86 registers | 11 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 10 |
| used zmm registers | 0 |
| nb stack references | 3 |
| micro-operation queue | 11.50 cycles |
| front end | 11.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 11.00 | 8.00 | 2.33 | 2.33 | 4.50 | 25.00 | 2.00 | 4.50 | 4.50 | 4.50 | 2.00 | 2.33 |
| cycles | 11.00 | 8.00 | 2.33 | 2.33 | 4.50 | 25.00 | 2.00 | 4.50 | 4.50 | 4.50 | 2.00 | 2.33 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 2.00 |
| Front-end | 11.50 |
| Dispatch | 25.00 |
| Data deps. | 2.00 |
| Overall L1 | 25.00 |
| all | 80% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 50% |
| 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 | 90% |
| 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 | 75% |
| all | 41% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | 50% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 28% |
| 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 | 46% |
| 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 | 39% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%R12,%R13,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| VMOVUPD 0x20(%R12,%R13,8),%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 0x40(%R12,%R13,8),%YMM8 | 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(%R12,%R13,8),%YMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| LEA (%RDX,%R13,1),%R11D | 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 %R11D,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (6.3%) |
| VPADDD %YMM4,%YMM10,%YMM11 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| VPADDD %YMM5,%YMM10,%YMM10 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| VPCMPNEQD %YMM2,%YMM10,%K0 | vect (50.0%) | |||||||||||||||
| VPCMPNEQD %YMM2,%YMM11,%K2 | 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%) |
| VCMPPD $0x1,%YMM3,%YMM6,%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,%K4,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VCMPPD $0x1,%YMM3,%YMM8,%K6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| VPBROADCASTD %R13D,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (6.3%) |
| VPADDD %YMM5,%YMM10,%YMM11 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| MOVSXD %EBX,%RBX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| KANDB %K0,%K3,%K5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VPCOMPRESSD %YMM11,(%R10,%RBX,4){%K5} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| VCMPPD $0x1,%YMM3,%YMM9,%K7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| KMOVB %K5,%R11D | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| KSHIFTLB $0x4,%K7,%K5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KORB %K5,%K6,%K5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VPADDD %YMM4,%YMM10,%YMM10 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| LEA (%R10,%RBX,4),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| POPCNT %R11D,%R9D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| KANDB %K2,%K5,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VPCOMPRESSD %YMM10,(%RAX,%R9,4){%K1} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| LEA (%RCX,%RBX,8),%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| KANDW %K2,%K6,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VCOMPRESSPD %YMM8,(%R11,%R9,8){%K1} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KANDW %K0,%K4,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VCOMPRESSPD %YMM7,(%RCX,%RBX,8){%K4} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KMOVB %K1,0x1f(%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,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KANDW %K1,%K7,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| LEA (%R11,%R9,8),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| MOVZX 0x1f(%RSP),%R9D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| POPCNT %R9D,%R9D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| VCOMPRESSPD %YMM9,(%RAX,%R9,8){%K1} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KUNPCKBW %K3,%K5,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KMOVB %K4,0x1e(%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 0x1e(%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 %YMM6,(%R11,%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,%EBX | 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,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| CMP %R14,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| JB 41fc50 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0xb0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
| Function | qmcplusplus::BsplineFunctor |
| Source file and lines | BsplineFunctor.h:291-297 |
| Module | exec |
|
| nb instructions | 58 |
| nb uops | 69 |
| loop length | 302 |
| used x86 registers | 11 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 10 |
| used zmm registers | 0 |
| nb stack references | 3 |
| micro-operation queue | 11.50 cycles |
| front end | 11.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 11.00 | 8.00 | 2.33 | 2.33 | 4.50 | 25.00 | 2.00 | 4.50 | 4.50 | 4.50 | 2.00 | 2.33 |
| cycles | 11.00 | 8.00 | 2.33 | 2.33 | 4.50 | 25.00 | 2.00 | 4.50 | 4.50 | 4.50 | 2.00 | 2.33 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 2.00 |
| Front-end | 11.50 |
| Dispatch | 25.00 |
| Data deps. | 2.00 |
| Overall L1 | 25.00 |
| all | 80% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 50% |
| 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 | 90% |
| 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 | 75% |
| all | 41% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | 50% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 28% |
| 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 | 46% |
| 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 | 39% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%R12,%R13,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| VMOVUPD 0x20(%R12,%R13,8),%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 0x40(%R12,%R13,8),%YMM8 | 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(%R12,%R13,8),%YMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 | vect (50.0%) |
| LEA (%RDX,%R13,1),%R11D | 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 %R11D,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (6.3%) |
| VPADDD %YMM4,%YMM10,%YMM11 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| VPADDD %YMM5,%YMM10,%YMM10 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| VPCMPNEQD %YMM2,%YMM10,%K0 | vect (50.0%) | |||||||||||||||
| VPCMPNEQD %YMM2,%YMM11,%K2 | 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%) |
| VCMPPD $0x1,%YMM3,%YMM6,%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,%K4,%K3 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VCMPPD $0x1,%YMM3,%YMM8,%K6 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| VPBROADCASTD %R13D,%YMM10 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | scal (6.3%) |
| VPADDD %YMM5,%YMM10,%YMM11 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| MOVSXD %EBX,%RBX | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 | N/A |
| KANDB %K0,%K3,%K5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VPCOMPRESSD %YMM11,(%R10,%RBX,4){%K5} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| VCMPPD $0x1,%YMM3,%YMM9,%K7 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | vect (50.0%) |
| KMOVB %K5,%R11D | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| KSHIFTLB $0x4,%K7,%K5 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KORB %K5,%K6,%K5 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VPADDD %YMM4,%YMM10,%YMM10 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | vect (50.0%) |
| LEA (%R10,%RBX,4),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| POPCNT %R11D,%R9D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| KANDB %K2,%K5,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VPCOMPRESSD %YMM10,(%RAX,%R9,4){%K1} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| LEA (%RCX,%RBX,8),%R11 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| KANDW %K2,%K6,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VCOMPRESSPD %YMM8,(%R11,%R9,8){%K1} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KANDW %K0,%K4,%K4 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| VCOMPRESSPD %YMM7,(%RCX,%RBX,8){%K4} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KMOVB %K1,0x1f(%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,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KANDW %K1,%K7,%K1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | N/A |
| LEA (%R11,%R9,8),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 | N/A |
| MOVZX 0x1f(%RSP),%R9D | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | N/A |
| POPCNT %R9D,%R9D | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 | N/A |
| VCOMPRESSPD %YMM9,(%RAX,%R9,8){%K1} | 3 | 0 | 0 | 0 | 0 | 0.50 | 2 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 3 | 2 | vect (50.0%) |
| KUNPCKBW %K3,%K5,%K1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 | N/A |
| KMOVB %K4,0x1e(%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 0x1e(%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 %YMM6,(%R11,%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,%EBX | 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,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| CMP %R14,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| JB 41fc50 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi+0xb0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |