| Loop Id: 1969 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 0.46% |
|---|
| Loop Id: 1969 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 0.46% |
|---|
0x4a2a25 VMOVSD (%RCX,%RAX,8),%XMM1 [2] |
0x4a2a2a VMOVSD 0x8(%RCX,%RAX,8),%XMM4 [2] |
0x4a2a30 VMULSD (%RSI,%RAX,8),%XMM1,%XMM3 [1] |
0x4a2a35 VMULSD 0x8(%RSI,%RAX,8),%XMM4,%XMM5 [1] |
0x4a2a3b VMOVSD 0x18(%RCX,%RAX,8),%XMM7 [2] |
0x4a2a41 VMOVSD 0x20(%RCX,%RAX,8),%XMM9 [2] |
0x4a2a47 VMULSD 0x18(%RSI,%RAX,8),%XMM7,%XMM8 [1] |
0x4a2a4d VFMADD231SD %XMM3,%XMM2,%XMM0 |
0x4a2a52 VMULSD 0x20(%RSI,%RAX,8),%XMM9,%XMM10 [1] |
0x4a2a58 VMOVSD 0x28(%RCX,%RAX,8),%XMM11 [2] |
0x4a2a5e VMOVSD 0x30(%RCX,%RAX,8),%XMM13 [2] |
0x4a2a64 VMULSD 0x28(%RSI,%RAX,8),%XMM11,%XMM12 [1] |
0x4a2a6a VFMADD132SD %XMM2,%XMM0,%XMM5 |
0x4a2a6f VMOVSD 0x10(%RCX,%RAX,8),%XMM0 [2] |
0x4a2a75 VMULSD 0x30(%RSI,%RAX,8),%XMM13,%XMM14 [1] |
0x4a2a7b VMULSD 0x10(%RSI,%RAX,8),%XMM0,%XMM6 [1] |
0x4a2a81 VMOVSD 0x38(%RCX,%RAX,8),%XMM15 [2] |
0x4a2a87 VMULSD 0x38(%RSI,%RAX,8),%XMM15,%XMM0 [1] |
0x4a2a8d ADD $0x8,%RAX |
0x4a2a91 VFMADD231SD %XMM6,%XMM2,%XMM5 |
0x4a2a96 VFMADD231SD %XMM8,%XMM2,%XMM5 |
0x4a2a9b VFMADD231SD %XMM10,%XMM2,%XMM5 |
0x4a2aa0 VFMADD231SD %XMM12,%XMM2,%XMM5 |
0x4a2aa5 VFMADD231SD %XMM14,%XMM2,%XMM5 |
0x4a2aaa VFMADD132SD %XMM2,%XMM5,%XMM0 |
0x4a2aaf CMP %RAX,%RDI |
0x4a2ab2 JNE 4a2a25 |
/home/eoseret/qaas_runs_GNR/173-926-6874/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp: 307 - 307 |
-------------------------------------------------------------------------------- |
307: return Ret{lhs} + rhs; |
/home/eoseret/qaas_runs_GNR/173-926-6874/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) { |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ○98.35 | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
| ○1.65 | GOMP_parallel | libgomp.h:982 | libgomp.so.1.0.0 |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.95 |
| CQA speedup if fully vectorized | 8.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 4.00 |
| Bottlenecks | |
| Function | void RAJA::internal::StatementExecutor |
| Source | Operators.hpp:307-307,forall.hpp:59-59 |
| Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 32.00 |
| CQA cycles if no scalar integer | 32.00 |
| CQA cycles if FP arith vectorized | 16.44 |
| CQA cycles if fully vectorized | 4.00 |
| Front-end cycles | 5.67 |
| P0 cycles | 8.00 |
| P1 cycles | 8.00 |
| P2 cycles | 5.33 |
| P3 cycles | 5.33 |
| P4 cycles | 0.00 |
| P5 cycles | 0.00 |
| P6 cycles | 1.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.00 |
| P11 cycles | 5.33 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 32 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 27.00 |
| Nb uops | 26.00 |
| Nb loads | 16.00 |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.75 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 8.00 |
| Nb FLOP fma | 8.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 4.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 128.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 2.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | 0.00 |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 12.50 |
| Vector-efficiency ratio load | 12.50 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | 12.50 |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | 12.50 |
| 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 | 1.95 |
| CQA speedup if fully vectorized | 8.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 4.00 |
| Bottlenecks | |
| Function | void RAJA::internal::StatementExecutor |
| Source | Operators.hpp:307-307,forall.hpp:59-59 |
| Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 32.00 |
| CQA cycles if no scalar integer | 32.00 |
| CQA cycles if FP arith vectorized | 16.44 |
| CQA cycles if fully vectorized | 4.00 |
| Front-end cycles | 5.67 |
| P0 cycles | 8.00 |
| P1 cycles | 8.00 |
| P2 cycles | 5.33 |
| P3 cycles | 5.33 |
| P4 cycles | 0.00 |
| P5 cycles | 0.00 |
| P6 cycles | 1.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 0.00 |
| P11 cycles | 5.33 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 32 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 27.00 |
| Nb uops | 26.00 |
| Nb loads | 16.00 |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.75 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 8.00 |
| Nb FLOP fma | 8.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 4.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 128.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 2.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | 0.00 |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 12.50 |
| Vector-efficiency ratio load | 12.50 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | 12.50 |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | 12.50 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Path / |
 |
 |
| nb instructions | 27 |
| nb uops | 26 |
| loop length | 147 |
| used x86 registers | 4 |
| used mmx registers | 0 |
| used xmm registers | 16 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 5.67 cycles |
| front end | 5.67 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 8.00 | 8.00 | 5.33 | 5.33 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 5.33 |
| cycles | 8.00 | 8.00 | 5.33 | 5.33 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 5.33 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 32.00 |
| Front-end | 5.67 |
| Dispatch | 8.00 |
| Data deps. | 32.00 |
| Overall L1 | 32.00 |
| all | 0% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 0% |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 12% |
| load | 12% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 12% |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 12% |
| 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 | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVSD (%RCX,%RAX,8),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMOVSD 0x8(%RCX,%RAX,8),%XMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMULSD (%RSI,%RAX,8),%XMM1,%XMM3 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VMULSD 0x8(%RSI,%RAX,8),%XMM4,%XMM5 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VMOVSD 0x18(%RCX,%RAX,8),%XMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMOVSD 0x20(%RCX,%RAX,8),%XMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMULSD 0x18(%RSI,%RAX,8),%XMM7,%XMM8 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VFMADD231SD %XMM3,%XMM2,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VMULSD 0x20(%RSI,%RAX,8),%XMM9,%XMM10 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VMOVSD 0x28(%RCX,%RAX,8),%XMM11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMOVSD 0x30(%RCX,%RAX,8),%XMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMULSD 0x28(%RSI,%RAX,8),%XMM11,%XMM12 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VFMADD132SD %XMM2,%XMM0,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VMOVSD 0x10(%RCX,%RAX,8),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMULSD 0x30(%RSI,%RAX,8),%XMM13,%XMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VMULSD 0x10(%RSI,%RAX,8),%XMM0,%XMM6 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VMOVSD 0x38(%RCX,%RAX,8),%XMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMULSD 0x38(%RSI,%RAX,8),%XMM15,%XMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| ADD $0x8,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| VFMADD231SD %XMM6,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VFMADD231SD %XMM8,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VFMADD231SD %XMM10,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VFMADD231SD %XMM12,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VFMADD231SD %XMM14,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VFMADD132SD %XMM2,%XMM5,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| CMP %RAX,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| JNE 4a2a25 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy4loop9loop_execEJNS2_6LambdaILl0EJEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSF_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSR_EESR_EENSN_INSP_INSQ_5GroupElPSV_EESV_EENSN_INSP_INSQ_4ZoneElPSZ_EESZ_EEEEENSL_IJEEEJZNK14PopulationSdomclINSQ_11ArchLayoutTINSQ_12ArchT_OpenMPENSQ_11LayoutT_DGZEEEEEvT_NSQ_6SdomIdERKNSQ_4Core3SetES1G_S1G_RNS1D_5FieldIdJSR_SV_SZ_EEERNS1H_IdJSR_EEERNS1H_IdJSZ_EEEPdEUlSR_SV_SZ_E_EEEEEvOS1B_._omp_fn.0+0x1e5> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |
|
|
| nb instructions | 27 |
| nb uops | 26 |
| loop length | 147 |
| used x86 registers | 4 |
| used mmx registers | 0 |
| used xmm registers | 16 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 5.67 cycles |
| front end | 5.67 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 8.00 | 8.00 | 5.33 | 5.33 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 5.33 |
| cycles | 8.00 | 8.00 | 5.33 | 5.33 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 5.33 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 32.00 |
| Front-end | 5.67 |
| Dispatch | 8.00 |
| Data deps. | 32.00 |
| Overall L1 | 32.00 |
| all | 0% |
| load | 0% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 0% |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 12% |
| load | 12% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 12% |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 12% |
| 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 | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVSD (%RCX,%RAX,8),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMOVSD 0x8(%RCX,%RAX,8),%XMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMULSD (%RSI,%RAX,8),%XMM1,%XMM3 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VMULSD 0x8(%RSI,%RAX,8),%XMM4,%XMM5 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VMOVSD 0x18(%RCX,%RAX,8),%XMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMOVSD 0x20(%RCX,%RAX,8),%XMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMULSD 0x18(%RSI,%RAX,8),%XMM7,%XMM8 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VFMADD231SD %XMM3,%XMM2,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VMULSD 0x20(%RSI,%RAX,8),%XMM9,%XMM10 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VMOVSD 0x28(%RCX,%RAX,8),%XMM11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMOVSD 0x30(%RCX,%RAX,8),%XMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMULSD 0x28(%RSI,%RAX,8),%XMM11,%XMM12 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VFMADD132SD %XMM2,%XMM0,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VMOVSD 0x10(%RCX,%RAX,8),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMULSD 0x30(%RSI,%RAX,8),%XMM13,%XMM14 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VMULSD 0x10(%RSI,%RAX,8),%XMM0,%XMM6 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| VMOVSD 0x38(%RCX,%RAX,8),%XMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 | scal (12.5%) |
| VMULSD 0x38(%RSI,%RAX,8),%XMM15,%XMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 | scal (12.5%) |
| ADD $0x8,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| VFMADD231SD %XMM6,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VFMADD231SD %XMM8,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VFMADD231SD %XMM10,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VFMADD231SD %XMM12,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VFMADD231SD %XMM14,%XMM2,%XMM5 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| VFMADD132SD %XMM2,%XMM5,%XMM0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 | scal (12.5%) |
| CMP %RAX,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 | N/A |
| JNE 4a2a25 <_ZN4RAJA8internal17StatementExecutorINS_9statement8CollapseINS_26omp_parallel_collapse_execEN4camp7int_seqIlJLl0ELl1EEEEJNS2_3ForILl2ENS_6policy4loop9loop_execEJNS2_6LambdaILl0EJEEEEEEEEEE4execIRNS0_8LoopDataINS5_4listIJSF_EEENS5_5tupleIJNS_4impl4SpanINS_9Iterators16numeric_iteratorIN6Kripke9DirectionElPSR_EESR_EENSN_INSP_INSQ_5GroupElPSV_EESV_EENSN_INSP_INSQ_4ZoneElPSZ_EESZ_EEEEENSL_IJEEEJZNK14PopulationSdomclINSQ_11ArchLayoutTINSQ_12ArchT_OpenMPENSQ_11LayoutT_DGZEEEEEvT_NSQ_6SdomIdERKNSQ_4Core3SetES1G_S1G_RNS1D_5FieldIdJSR_SV_SZ_EEERNS1H_IdJSR_EEERNS1H_IdJSZ_EEEPdEUlSR_SV_SZ_E_EEEEEvOS1B_._omp_fn.0+0x1e5> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | N/A |