| Loop Id: 1987 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 5.06% |
|---|
| Loop Id: 1987 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 5.06% |
|---|
0x4b41d0 VMOVUPD (%RCX,%RDX,1),%YMM10 [3] |
0x4b41d5 VFMADD213PD (%RAX,%RDX,1),%YMM2,%YMM10 [2] |
0x4b41db VMOVUPD %YMM10,(%RAX,%RDX,1) [2] |
0x4b41e0 VMOVUPD 0x20(%RDX,%RCX,1),%YMM11 [1] |
0x4b41e6 VFMADD213PD 0x20(%RAX,%RDX,1),%YMM2,%YMM11 [2] |
0x4b41ed VMOVUPD %YMM11,0x20(%RAX,%RDX,1) [2] |
0x4b41f3 VMOVUPD 0x40(%RDX,%RCX,1),%YMM12 [1] |
0x4b41f9 VFMADD213PD 0x40(%RAX,%RDX,1),%YMM2,%YMM12 [2] |
0x4b4200 VMOVUPD %YMM12,0x40(%RAX,%RDX,1) [2] |
0x4b4206 VMOVUPD 0x60(%RDX,%RCX,1),%YMM13 [1] |
0x4b420c VFMADD213PD 0x60(%RAX,%RDX,1),%YMM2,%YMM13 [2] |
0x4b4213 VMOVUPD %YMM13,0x60(%RAX,%RDX,1) [2] |
0x4b4219 VMOVUPD 0x80(%RDX,%RCX,1),%YMM14 [1] |
0x4b4222 VFMADD213PD 0x80(%RAX,%RDX,1),%YMM2,%YMM14 [2] |
0x4b422c VMOVUPD %YMM14,0x80(%RAX,%RDX,1) [2] |
0x4b4235 VMOVUPD 0xa0(%RDX,%RCX,1),%YMM15 [1] |
0x4b423e VFMADD213PD 0xa0(%RAX,%RDX,1),%YMM2,%YMM15 [2] |
0x4b4248 VMOVUPD %YMM15,0xa0(%RAX,%RDX,1) [2] |
0x4b4251 VMOVUPD 0xc0(%RDX,%RCX,1),%YMM0 [1] |
0x4b425a VFMADD213PD 0xc0(%RAX,%RDX,1),%YMM2,%YMM0 [2] |
0x4b4264 VMOVUPD %YMM0,0xc0(%RAX,%RDX,1) [2] |
0x4b426d VMOVUPD 0xe0(%RDX,%RCX,1),%YMM4 [1] |
0x4b4276 VFMADD213PD 0xe0(%RAX,%RDX,1),%YMM2,%YMM4 [2] |
0x4b4280 VMOVUPD %YMM4,0xe0(%RAX,%RDX,1) [2] |
0x4b4289 ADD $0x100,%RDX |
0x4b4290 CMP %RDX,0xb8(%RSP) [4] |
0x4b4298 JNE 4b41d0 |
/scratch_na/users/xoserete/qaas_runs/171-319-6990/intel/Kripke/build/Kripke/src/Kripke/Kernel/LTimes.cpp: 62 - 62 |
-------------------------------------------------------------------------------- |
62: phi(nm,g,z) += ell(nm, d) * psi(d, g, z); |
/scratch_na/users/xoserete/qaas_runs/171-319-6990/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/loop/forall.hpp: 59 - 59 |
-------------------------------------------------------------------------------- |
59: for (decltype(distance_it) i = 0; i < distance_it; ++i) { |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.03 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.42 |
| Bottlenecks | micro-operation queue, |
| Function | void RAJA::internal::StatementExecutor |
| Source | LTimes.cpp:62-62,forall.hpp:59-59 |
| Source loop unroll info | unrolled by 4 |
| Source loop unroll confidence level | high |
| Unroll/vectorization loop type | main |
| Unroll factor | 4 |
| CQA cycles | 5.67 |
| CQA cycles if no scalar integer | 5.67 |
| CQA cycles if FP arith vectorized | 5.50 |
| CQA cycles if fully vectorized | 2.83 |
| Front-end cycles | 5.67 |
| DIV/SQRT cycles | 4.00 |
| P0 cycles | 4.00 |
| P1 cycles | 5.67 |
| P2 cycles | 5.67 |
| P3 cycles | 4.00 |
| P4 cycles | 0.60 |
| P5 cycles | 1.00 |
| P6 cycles | 4.00 |
| P7 cycles | 4.00 |
| P8 cycles | 4.00 |
| P9 cycles | 0.40 |
| P10 cycles | 5.67 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 5.83 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 27.00 |
| Nb uops | 26.00 |
| Nb loads | 17.00 |
| Nb stores | 8.00 |
| Nb stack references | 1.00 |
| FLOP/cycle | 11.29 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 32.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 136.94 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 520.00 |
| Bytes stored | 256.00 |
| Stride 0 | 1.00 |
| Stride 1 | 1.00 |
| Stride n | 2.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 100.00 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | 100.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 50.00 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | 50.00 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | 50.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.03 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.42 |
| Bottlenecks | micro-operation queue, |
| Function | void RAJA::internal::StatementExecutor |
| Source | LTimes.cpp:62-62,forall.hpp:59-59 |
| Source loop unroll info | unrolled by 4 |
| Source loop unroll confidence level | high |
| Unroll/vectorization loop type | main |
| Unroll factor | 4 |
| CQA cycles | 5.67 |
| CQA cycles if no scalar integer | 5.67 |
| CQA cycles if FP arith vectorized | 5.50 |
| CQA cycles if fully vectorized | 2.83 |
| Front-end cycles | 5.67 |
| DIV/SQRT cycles | 4.00 |
| P0 cycles | 4.00 |
| P1 cycles | 5.67 |
| P2 cycles | 5.67 |
| P3 cycles | 4.00 |
| P4 cycles | 0.60 |
| P5 cycles | 1.00 |
| P6 cycles | 4.00 |
| P7 cycles | 4.00 |
| P8 cycles | 4.00 |
| P9 cycles | 0.40 |
| P10 cycles | 5.67 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 5.83 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 27.00 |
| Nb uops | 26.00 |
| Nb loads | 17.00 |
| Nb stores | 8.00 |
| Nb stack references | 1.00 |
| FLOP/cycle | 11.29 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 32.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 136.94 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 520.00 |
| Bytes stored | 256.00 |
| Stride 0 | 1.00 |
| Stride 1 | 1.00 |
| Stride n | 2.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 100.00 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | 100.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 50.00 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | 50.00 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | 50.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Path / |
 |
 |
| nb instructions | 27 |
| nb uops | 26 |
| loop length | 206 |
| used x86 registers | 4 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 9 |
| used zmm registers | 0 |
| nb stack references | 1 |
| micro-operation queue | 5.67 cycles |
| front end | 5.67 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 4.00 | 4.00 | 5.67 | 5.67 | 4.00 | 0.60 | 1.00 | 4.00 | 4.00 | 4.00 | 0.40 | 5.67 |
| cycles | 4.00 | 4.00 | 5.67 | 5.67 | 4.00 | 0.60 | 1.00 | 4.00 | 4.00 | 4.00 | 0.40 | 5.67 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 5.83 |
| Stall cycles | 0.00 |
| Front-end | 5.67 |
| Dispatch | 5.67 |
| Data deps. | 1.00 |
| Overall L1 | 5.67 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 100% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 50% |
| load | 50% |
| store | 50% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 50% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%RCX,%RDX,1),%YMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD (%RAX,%RDX,1),%YMM2,%YMM10 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM10,(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x20(%RDX,%RCX,1),%YMM11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0x20(%RAX,%RDX,1),%YMM2,%YMM11 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM11,0x20(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x40(%RDX,%RCX,1),%YMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0x40(%RAX,%RDX,1),%YMM2,%YMM12 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM12,0x40(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x60(%RDX,%RCX,1),%YMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0x60(%RAX,%RDX,1),%YMM2,%YMM13 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM13,0x60(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x80(%RDX,%RCX,1),%YMM14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0x80(%RAX,%RDX,1),%YMM2,%YMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM14,0x80(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0xa0(%RDX,%RCX,1),%YMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0xa0(%RAX,%RDX,1),%YMM2,%YMM15 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM15,0xa0(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0xc0(%RDX,%RCX,1),%YMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0xc0(%RAX,%RDX,1),%YMM2,%YMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM0,0xc0(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0xe0(%RDX,%RCX,1),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0xe0(%RAX,%RDX,1),%YMM2,%YMM4 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM4,0xe0(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| ADD $0x100,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| CMP %RDX,0xb8(%RSP) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
| JNE 4b41d0 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPSS_EESS_EENSO_INSQ_INSR_9DirectionElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK10LTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x3d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
|
|
| nb instructions | 27 |
| nb uops | 26 |
| loop length | 206 |
| used x86 registers | 4 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 9 |
| used zmm registers | 0 |
| nb stack references | 1 |
| micro-operation queue | 5.67 cycles |
| front end | 5.67 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 4.00 | 4.00 | 5.67 | 5.67 | 4.00 | 0.60 | 1.00 | 4.00 | 4.00 | 4.00 | 0.40 | 5.67 |
| cycles | 4.00 | 4.00 | 5.67 | 5.67 | 4.00 | 0.60 | 1.00 | 4.00 | 4.00 | 4.00 | 0.40 | 5.67 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 5.83 |
| Stall cycles | 0.00 |
| Front-end | 5.67 |
| Dispatch | 5.67 |
| Data deps. | 1.00 |
| Overall L1 | 5.67 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 100% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 50% |
| load | 50% |
| store | 50% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 50% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%RCX,%RDX,1),%YMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD (%RAX,%RDX,1),%YMM2,%YMM10 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM10,(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x20(%RDX,%RCX,1),%YMM11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0x20(%RAX,%RDX,1),%YMM2,%YMM11 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM11,0x20(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x40(%RDX,%RCX,1),%YMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0x40(%RAX,%RDX,1),%YMM2,%YMM12 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM12,0x40(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x60(%RDX,%RCX,1),%YMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0x60(%RAX,%RDX,1),%YMM2,%YMM13 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM13,0x60(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0x80(%RDX,%RCX,1),%YMM14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0x80(%RAX,%RDX,1),%YMM2,%YMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM14,0x80(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0xa0(%RDX,%RCX,1),%YMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0xa0(%RAX,%RDX,1),%YMM2,%YMM15 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM15,0xa0(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0xc0(%RDX,%RCX,1),%YMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0xc0(%RAX,%RDX,1),%YMM2,%YMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM0,0xc0(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| VMOVUPD 0xe0(%RDX,%RCX,1),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD 0xe0(%RAX,%RDX,1),%YMM2,%YMM4 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM4,0xe0(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| ADD $0x100,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| CMP %RDX,0xb8(%RSP) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
| JNE 4b41d0 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl2EEEEJNS2_3ForILl1ENS_6policy4loop9loop_execEJNS8_ILl3ESB_JNS2_6LambdaILl0EJEEEEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSG_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke6MomentElPSS_EESS_EENSO_INSQ_INSR_9DirectionElPSW_EESW_EENSO_INSQ_INSR_5GroupElPS10_EES10_EENSO_INSQ_INSR_4ZoneElPS14_EES14_EEEEENSM_IJEEEJZNK10LTimesSdomclINSR_11ArchLayoutTINSR_12ArchT_OpenMPENSR_11LayoutT_DGZEEEEEvT_NSR_6SdomIdERKNSR_4Core3SetES1L_S1L_S1L_RNS1I_5FieldIdJSW_S10_S14_EEERNS1M_IdJSS_S10_S14_EEERNS1M_IdJSS_SW_EEEEUlSS_SW_S10_S14_E_EEEEEvOS1G_._omp_fn.0+0x3d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |