| Loop Id: 1296 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 0.02% |
|---|
| Loop Id: 1296 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 0.02% |
|---|
0x46c950 MOV -0x90(%RBP),%RDX |
0x46c957 INC %RDX |
0x46c95a ADD -0x80(%RBP),%R15 |
0x46c95e MOV -0x88(%RBP),%RAX |
0x46c965 ADD %RAX,%RSI |
0x46c968 MOV %RSI,%RDI |
0x46c96b MOV -0x40(%RBP),%RSI |
0x46c96f ADD %RAX,%RSI |
0x46c972 MOV -0x38(%RBP),%RCX |
0x46c976 ADD %RAX,%RCX |
0x46c979 MOV -0x1d0(%RBP),%R11 |
0x46c980 MOV %RDX,%RAX |
0x46c983 MOV %RDX,-0x90(%RBP) |
0x46c98a CMP %R11,%RDX |
0x46c98d MOV -0x148(%RBP),%RAX |
0x46c994 MOV %RCX,%RDX |
0x46c997 JE 46c870 |
0x46c99d MOV %RDX,-0x38(%RBP) |
0x46c9a1 MOV %RSI,-0x40(%RBP) |
0x46c9a5 TEST %RAX,%RAX |
0x46c9a8 MOV %RDI,%RSI |
0x46c9ab MOV -0x1d8(%RBP),%R8 |
0x46c9b2 MOV -0x1c8(%RBP),%RCX |
0x46c9b9 MOV -0x1e8(%RBP),%RDX |
0x46c9c0 MOV -0x1f0(%RBP),%RDI |
0x46c9c7 MOV -0x140(%RBP),%R13 |
0x46c9ce JLE 46c950 |
0x46c9d0 MOV -0x90(%RBP),%R11 |
0x46c9d7 IMUL -0x138(%RBP),%R11 |
0x46c9df ADD -0x78(%RBP),%R11 |
0x46c9e3 MOV -0x1c0(%RBP),%RAX |
0x46c9ea MOV %R11,-0xa0(%RBP) |
0x46c9f1 ADD %R11,%RAX |
0x46c9f4 MOV %RAX,-0x98(%RBP) |
0x46c9fb XOR %R11D,%R11D |
0x46c9fe XOR %EBX,%EBX |
0x46ca00 MOV -0x148(%RBP),%RAX |
0x46ca07 NOPW (%RAX,%RAX,1) |
(1297) 0x46ca10 VMOVSD (%R14,%RDX,8),%XMM0 |
(1297) 0x46ca16 VADDSD %XMM0,%XMM0,%XMM0 |
(1297) 0x46ca1a VDIVSD (%RCX,%RBX,1),%XMM0,%XMM0 |
(1297) 0x46ca1f MOV -0x220(%RBP),%R9 |
(1297) 0x46ca26 VMOVSD (%R9,%RDX,8),%XMM1 |
(1297) 0x46ca2c MOV -0x210(%RBP),%R9 |
(1297) 0x46ca33 VMOVHPD (%R9,%RDX,8),%XMM1,%XMM1 |
(1297) 0x46ca39 VADDPD %XMM1,%XMM1,%XMM1 |
(1297) 0x46ca3d MOV -0x218(%RBP),%R9 |
(1297) 0x46ca44 MOV %R13,%R10 |
(1297) 0x46ca47 MOV -0xa0(%RBP),%R13 |
(1297) 0x46ca4e VMOVSD (%R9,%R13,8),%XMM2 |
(1297) 0x46ca54 MOV %R10,%R13 |
(1297) 0x46ca57 MOV -0x208(%RBP),%R9 |
(1297) 0x46ca5e VMOVHPD (%R9,%RDI,8),%XMM2,%XMM2 |
(1297) 0x46ca64 VDIVPD %XMM2,%XMM1,%XMM1 |
(1297) 0x46ca68 MOV -0x98(%RBP),%R12 |
(1297) 0x46ca6f VMOVSD (%R8,%R12,8),%XMM2 |
(1297) 0x46ca75 MOV -0x38(%RBP),%R9 |
(1297) 0x46ca79 VFMADD213SD (%R9,%R11,1),%XMM0,%XMM2 |
(1297) 0x46ca7f VFMADD231SD (%R10,%RBX,1),%XMM1,%XMM2 |
(1297) 0x46ca85 VSHUFPD $0x1,%XMM1,%XMM1,%XMM3 |
(1297) 0x46ca8a VFMADD231SD (%R15,%RBX,1),%XMM3,%XMM2 |
(1297) 0x46ca90 VADDSD %XMM0,%XMM1,%XMM0 |
(1297) 0x46ca94 MOV %RDI,%R9 |
(1297) 0x46ca97 MOV %R14,%RDI |
(1297) 0x46ca9a MOV %RSI,%R10 |
(1297) 0x46ca9d MOV -0x40(%RBP),%RSI |
(1297) 0x46caa1 VADDSD (%RSI,%R11,1),%XMM3,%XMM1 |
(1297) 0x46caa7 MOV %R10,%RSI |
(1297) 0x46caaa MOV %R9,%RDI |
(1297) 0x46caad MOV -0x1f8(%RBP),%R9 |
(1297) 0x46cab4 VADDSD %XMM0,%XMM1,%XMM0 |
(1297) 0x46cab8 VDIVSD %XMM0,%XMM2,%XMM0 |
(1297) 0x46cabc VMOVSD %XMM0,(%R10,%R11,1) |
(1297) 0x46cac2 VADDSD %XMM0,%XMM0,%XMM0 |
(1297) 0x46cac6 VSUBSD (%R8,%R12,8),%XMM0,%XMM1 |
(1297) 0x46cacc VMOVSD %XMM1,(%R8,%R12,8) |
(1297) 0x46cad2 VSUBSD (%R13,%RBX,1),%XMM0,%XMM1 |
(1297) 0x46cad9 VMOVSD %XMM1,(%R13,%RBX,1) |
(1297) 0x46cae0 VSUBSD (%R15,%RBX,1),%XMM0,%XMM0 |
(1297) 0x46cae6 VMOVSD %XMM0,(%R15,%RBX,1) |
(1297) 0x46caec ADD %R9,%RBX |
(1297) 0x46caef ADD -0x200(%RBP),%R11 |
(1297) 0x46caf6 DEC %RAX |
(1297) 0x46caf9 JNE 46ca10 |
0x46caff JMP 46c950 |
/home/eoseret/qaas_runs_CPU_9468/171-112-3942/intel/Kripke/build/Kripke/src/Kripke/Kernel/SweepSubdomain.cpp: 87 - 105 |
-------------------------------------------------------------------------------- |
87: double xcos_dxi = 2.0 * xcos(d) / dx(i); |
88: double ycos_dyj = 2.0 * ycos(d) / dy(j); |
89: double zcos_dzk = 2.0 * zcos(d) / dz(k); |
[...] |
95: + psi_lf(d, g, j, k) * xcos_dxi |
96: + psi_fr(d, g, i, k) * ycos_dyj |
97: + psi_bo(d, g, i, j) * zcos_dzk) |
98: / (xcos_dxi + ycos_dyj + zcos_dzk + sigt(g, z)); |
99: |
100: psi(d, g, z) = psi_d_g_z; |
101: |
102: /* Apply diamond-difference relationships */ |
103: psi_lf(d, g, j, k) = 2.0 * psi_d_g_z - psi_lf(d, g, j, k); |
104: psi_fr(d, g, i, k) = 2.0 * psi_d_g_z - psi_fr(d, g, i, k); |
105: psi_bo(d, g, i, j) = 2.0 * psi_d_g_z - psi_bo(d, g, i, j); |
/home/eoseret/qaas_runs_CPU_9468/171-112-3942/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) { |
/home/eoseret/qaas_runs_CPU_9468/171-112-3942/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/internal/Iterators.hpp: 310 - 310 |
-------------------------------------------------------------------------------- |
310: return value_type(val + rhs * stride); |
/home/eoseret/qaas_runs_CPU_9468/171-112-3942/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp: 307 - 307 |
-------------------------------------------------------------------------------- |
307: return Ret{lhs} + rhs; |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 9.28 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.13 |
| Bottlenecks | |
| Function | _ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted |
| Source | forall.hpp:59-59,Iterators.hpp:310-310,Operators.hpp:307-307 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 5.75 |
| CQA cycles if no scalar integer | 5.75 |
| CQA cycles if FP arith vectorized | 5.75 |
| CQA cycles if fully vectorized | 0.62 |
| Front-end cycles | 5.50 |
| DIV/SQRT cycles | 1.90 |
| P0 cycles | 2.10 |
| P1 cycles | 4.83 |
| P2 cycles | 4.83 |
| P3 cycles | 2.00 |
| P4 cycles | 1.90 |
| P5 cycles | 1.90 |
| P6 cycles | 2.00 |
| P7 cycles | 2.00 |
| P8 cycles | 2.00 |
| P9 cycles | 1.90 |
| P10 cycles | 4.83 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 5 |
| FE+BE cycles (UFS) | 5.63 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 33.00 |
| Nb uops | 33.00 |
| Nb loads | 14.50 |
| Nb stores | 4.00 |
| Nb stack references | 14.50 |
| 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 | 25.54 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 116.00 |
| Bytes stored | 32.00 |
| Stride 0 | 1.00 |
| Stride 1 | 0.50 |
| Stride n | 0.50 |
| Stride unknown | 3.50 |
| Stride indirect | 1.50 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| 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 | 12.37 |
| Vector-efficiency ratio load | 12.50 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 12.50 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 11.98 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 10.58 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.15 |
| Bottlenecks | micro-operation queue, |
| Function | _ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted |
| Source | forall.hpp:59-59,Iterators.hpp:310-310,Operators.hpp:307-307 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 6.50 |
| CQA cycles if no scalar integer | 6.50 |
| CQA cycles if FP arith vectorized | 6.50 |
| CQA cycles if fully vectorized | 0.61 |
| Front-end cycles | 6.50 |
| DIV/SQRT cycles | 2.20 |
| P0 cycles | 2.60 |
| P1 cycles | 5.67 |
| P2 cycles | 5.67 |
| P3 cycles | 2.50 |
| P4 cycles | 2.20 |
| P5 cycles | 2.20 |
| P6 cycles | 2.50 |
| P7 cycles | 2.50 |
| P8 cycles | 2.50 |
| P9 cycles | 2.20 |
| P10 cycles | 5.67 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 5 |
| FE+BE cycles (UFS) | 6.66 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 39.00 |
| Nb uops | 39.00 |
| Nb loads | 17.00 |
| Nb stores | 5.00 |
| Nb stack references | 17.00 |
| 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 | 27.08 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 136.00 |
| Bytes stored | 40.00 |
| Stride 0 | 1.00 |
| Stride 1 | 1.00 |
| Stride n | 1.00 |
| Stride unknown | 7.00 |
| Stride indirect | 3.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| 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 | 12.24 |
| Vector-efficiency ratio load | 12.50 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 12.50 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 11.46 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 8.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.11 |
| Bottlenecks | |
| Function | _ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted |
| Source | forall.hpp:59-59,Iterators.hpp:310-310,Operators.hpp:307-307 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 5.00 |
| CQA cycles if no scalar integer | 5.00 |
| CQA cycles if FP arith vectorized | 5.00 |
| CQA cycles if fully vectorized | 0.63 |
| Front-end cycles | 4.50 |
| DIV/SQRT cycles | 1.60 |
| P0 cycles | 1.60 |
| P1 cycles | 4.00 |
| P2 cycles | 4.00 |
| P3 cycles | 1.50 |
| P4 cycles | 1.60 |
| P5 cycles | 1.60 |
| P6 cycles | 1.50 |
| P7 cycles | 1.50 |
| P8 cycles | 1.50 |
| P9 cycles | 1.60 |
| P10 cycles | 4.00 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 5 |
| FE+BE cycles (UFS) | 4.61 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 27.00 |
| Nb uops | 27.00 |
| Nb loads | 12.00 |
| Nb stores | 3.00 |
| Nb stack references | 12.00 |
| 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 | 24.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 96.00 |
| Bytes stored | 24.00 |
| Stride 0 | 1.00 |
| Stride 1 | 0.00 |
| 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 | 0.00 |
| 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 | 12.50 |
| Vector-efficiency ratio load | 12.50 |
| Vector-efficiency ratio store | 12.50 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 12.50 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 12.50 |
| Path / |
| Function | _ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted |
| Source file and lines | forall.hpp:59-59 |
| Module | exec |
| nb instructions | 33 |
| nb uops | 33 |
| loop length | 162.50 |
| used x86 registers | 10.50 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 14.50 |
| micro-operation queue | 5.50 cycles |
| front end | 5.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.90 | 1.90 | 4.83 | 4.83 | 2.00 | 1.90 | 1.90 | 2.00 | 2.00 | 2.00 | 1.90 | 4.83 |
| cycles | 1.90 | 2.10 | 4.83 | 4.83 | 2.00 | 1.90 | 1.90 | 2.00 | 2.00 | 2.00 | 1.90 | 4.83 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 5.00 |
| FE+BE cycles | 5.63 |
| Stall cycles | 0.00 |
| Front-end | 5.50 |
| Dispatch | 4.83 |
| Data deps. | 5.00 |
| Overall L1 | 5.75 |
| all | 0% |
| load | 0% |
| store | 0% |
| 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 | 12% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 11% |
| Function | _ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted |
| Source file and lines | forall.hpp:59-59 |
| Module | exec |
| nb instructions | 39 |
| nb uops | 39 |
| loop length | 197 |
| used x86 registers | 11 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 17 |
| micro-operation queue | 6.50 cycles |
| front end | 6.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 2.20 | 2.20 | 5.67 | 5.67 | 2.50 | 2.20 | 2.20 | 2.50 | 2.50 | 2.50 | 2.20 | 5.67 |
| cycles | 2.20 | 2.60 | 5.67 | 5.67 | 2.50 | 2.20 | 2.20 | 2.50 | 2.50 | 2.50 | 2.20 | 5.67 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 5.00 |
| FE+BE cycles | 6.66 |
| Stall cycles | 0.00 |
| Front-end | 6.50 |
| Dispatch | 5.67 |
| Data deps. | 5.00 |
| Overall L1 | 6.50 |
| all | 0% |
| load | 0% |
| store | 0% |
| 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 | 12% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 11% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MOV -0x90(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| INC %RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| ADD -0x80(%RBP),%R15 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
| MOV -0x88(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| ADD %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV %RSI,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| MOV -0x40(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| ADD %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV -0x38(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| ADD %RAX,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV -0x1d0(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| MOV %RDX,-0x90(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| CMP %R11,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV -0x148(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV %RCX,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| JE 46c870 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x5a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| MOV %RDX,-0x38(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| MOV %RSI,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| TEST %RAX,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
| MOV %RDI,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| MOV -0x1d8(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x1c8(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x1e8(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x1f0(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x140(%RBP),%R13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| JLE 46c950 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x680> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| MOV -0x90(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| IMUL -0x138(%RBP),%R11 | 1 | 0 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
| ADD -0x78(%RBP),%R11 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
| MOV -0x1c0(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV %R11,-0xa0(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| ADD %R11,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV %RAX,-0x98(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| XOR %R11D,%R11D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| MOV -0x148(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
| JMP 46c950 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x680> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
| Function | _ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted |
| Source file and lines | forall.hpp:59-59 |
| Module | exec |
| nb instructions | 27 |
| nb uops | 27 |
| loop length | 128 |
| used x86 registers | 10 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 12 |
| micro-operation queue | 4.50 cycles |
| front end | 4.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.60 | 1.60 | 4.00 | 4.00 | 1.50 | 1.60 | 1.60 | 1.50 | 1.50 | 1.50 | 1.60 | 4.00 |
| cycles | 1.60 | 1.60 | 4.00 | 4.00 | 1.50 | 1.60 | 1.60 | 1.50 | 1.50 | 1.50 | 1.60 | 4.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 5.00 |
| FE+BE cycles | 4.61 |
| Stall cycles | 0.00 |
| Front-end | 4.50 |
| Dispatch | 4.00 |
| Data deps. | 5.00 |
| Overall L1 | 5.00 |
| all | 0% |
| load | 0% |
| store | 0% |
| 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 | 12% |
| load | 12% |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 12% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MOV -0x90(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| INC %RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| ADD -0x80(%RBP),%R15 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
| MOV -0x88(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| ADD %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV %RSI,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| MOV -0x40(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| ADD %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV -0x38(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| ADD %RAX,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV -0x1d0(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| MOV %RDX,-0x90(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| CMP %R11,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| MOV -0x148(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV %RCX,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| JE 46c870 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x5a0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| MOV %RDX,-0x38(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| MOV %RSI,-0x40(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
| TEST %RAX,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 2 | 0.20 |
| MOV %RDI,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| MOV -0x1d8(%RBP),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x1c8(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x1e8(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x1f0(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| MOV -0x140(%RBP),%R13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
| JLE 46c950 <_ZNK6Kripke14DispatchHelperINS_12ArchT_OpenMPEEclINS_11LayoutT_DGZE9SweepSdomJRNS_4Core9DataStoreERNS_6SdomIdEEEEvT_RKT0_DpOT1_.extracted+0x680> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
