| Loop Id: 2342 | Module: exec | Source: par_strength.c:2011-2048 | Coverage: 0.23% |
|---|
| Loop Id: 2342 | Module: exec | Source: par_strength.c:2011-2048 | Coverage: 0.23% |
|---|
0x48bf70 INC %R10 |
0x48bf73 MOV -0x50(%RBP),%RAX |
0x48bf77 CMP 0x8(%RAX,%R11,8),%R10 |
0x48bf7c JGE 48be67 |
0x48bf82 MOV -0x88(%RBP),%RAX |
0x48bf89 MOV (%RAX,%R10,8),%RDI |
0x48bf8d MOV -0x68(%RBP),%RAX |
0x48bf91 CMPQ $0,(%RAX,%RDI,8) |
0x48bf96 JLE 48bfb9 |
0x48bf98 MOV 0x78(%RBP),%RAX |
0x48bf9c MOV (%RAX,%RDI,8),%RAX |
0x48bfa0 CMP %R9,(%R14,%RAX,8) |
0x48bfa4 JGE 48bfb9 |
0x48bfa6 MOV -0x30(%RBP),%RCX |
0x48bfaa MOV %RCX,(%R14,%RAX,8) |
0x48bfae MOV (%R15),%RBX |
0x48bfb1 MOV %RAX,(%RBX,%RCX,8) |
0x48bfb5 INCQ -0x30(%RBP) |
0x48bfb9 MOV -0x50(%RBP),%RAX |
0x48bfbd MOV (%RAX,%RDI,8),%RBX |
0x48bfc1 MOV 0x8(%RAX,%RDI,8),%RAX |
0x48bfc6 JMP 48bfd3 |
(2344) 0x48bfd0 INC %RBX |
(2344) 0x48bfd3 CMP %RAX,%RBX |
(2344) 0x48bfd6 JGE 48c020 |
(2344) 0x48bfd8 MOV -0x88(%RBP),%RCX |
(2344) 0x48bfdf MOV (%RCX,%RBX,8),%RCX |
(2344) 0x48bfe3 MOV -0x68(%RBP),%RSI |
(2344) 0x48bfe7 CMPQ $0,(%RSI,%RCX,8) |
(2344) 0x48bfec JLE 48bfd0 |
(2344) 0x48bfee MOV 0x78(%RBP),%RSI |
(2344) 0x48bff2 MOV (%RSI,%RCX,8),%RCX |
(2344) 0x48bff6 CMP %R8,%RCX |
(2344) 0x48bff9 JE 48bfd0 |
(2344) 0x48bffb CMP %R9,(%R14,%RCX,8) |
(2344) 0x48bfff JGE 48bfd0 |
(2344) 0x48c001 MOV -0x30(%RBP),%RAX |
(2344) 0x48c005 MOV %RAX,(%R14,%RCX,8) |
(2344) 0x48c009 MOV (%R15),%RSI |
(2344) 0x48c00c MOV %RCX,(%RSI,%RAX,8) |
(2344) 0x48c010 INCQ -0x30(%RBP) |
(2344) 0x48c014 MOV -0x50(%RBP),%RAX |
(2344) 0x48c018 MOV 0x8(%RAX,%RDI,8),%RAX |
(2344) 0x48c01d JMP 48bfd0 |
0x48c020 MOV 0x10(%RBP),%RAX |
0x48c024 MOV (%RAX,%RDI,8),%RBX |
0x48c028 MOV 0x8(%RAX,%RDI,8),%RAX |
0x48c02d JMP 48c033 |
(2343) 0x48c030 INC %RBX |
(2343) 0x48c033 CMP %RAX,%RBX |
(2343) 0x48c036 JGE 48bf70 |
(2343) 0x48c03c MOV 0x18(%RBP),%RCX |
(2343) 0x48c040 MOV (%RCX,%RBX,8),%RCX |
(2343) 0x48c044 MOV 0x70(%RBP),%RSI |
(2343) 0x48c048 CMPQ $0,(%RSI,%RCX,8) |
(2343) 0x48c04d JLE 48c030 |
(2343) 0x48c04f MOV 0x80(%RBP),%RSI |
(2343) 0x48c056 MOV (%RSI,%RCX,8),%RCX |
(2343) 0x48c05a CMP %RDX,(%R12,%RCX,8) |
(2343) 0x48c05e JGE 48c030 |
(2343) 0x48c060 MOV -0x38(%RBP),%RAX |
(2343) 0x48c064 MOV %RAX,(%R12,%RCX,8) |
(2343) 0x48c068 MOV (%R13),%RSI |
(2343) 0x48c06c MOV %RCX,(%RSI,%RAX,8) |
(2343) 0x48c070 INCQ -0x38(%RBP) |
(2343) 0x48c074 MOV 0x10(%RBP),%RAX |
(2343) 0x48c078 MOV 0x8(%RAX,%RDI,8),%RAX |
(2343) 0x48c07d JMP 48c030 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c: 2011 - 2048 |
-------------------------------------------------------------------------------- |
2011: for (jj1 = S_diag_i[i1]; jj1 < S_diag_i[i1+1]; jj1++) |
2012: { |
2013: i2 = S_diag_j[jj1]; |
2014: if (CF_marker[i2] > 0) |
2015: { |
2016: index = fine_to_coarse[i2]; |
2017: if (S_marker[index] < jj_row_begin_diag) |
2018: { |
2019: S_marker[index] = num_nonzeros_diag; |
2020: C_diag_j[num_nonzeros_diag] = index; |
2021: num_nonzeros_diag++; |
2022: } |
2023: } |
2024: for (jj2 = S_diag_i[i2]; jj2 < S_diag_i[i2+1]; jj2++) |
2025: { |
2026: i3 = S_diag_j[jj2]; |
2027: if (CF_marker[i3] > 0) |
2028: { |
2029: index = fine_to_coarse[i3]; |
2030: if (index != ic && S_marker[index] < jj_row_begin_diag) |
2031: { |
2032: S_marker[index] = num_nonzeros_diag; |
2033: C_diag_j[num_nonzeros_diag] = index; |
2034: num_nonzeros_diag++; |
2035: } |
2036: } |
2037: } |
2038: for (jj2 = S_offd_i[i2]; jj2 < S_offd_i[i2+1]; jj2++) |
2039: { |
2040: i3 = S_offd_j[jj2]; |
2041: if (CF_marker_offd[i3] > 0) |
2042: { |
2043: index = map_S_to_C[i3]; |
2044: if (S_marker_offd[index] < jj_row_begin_offd) |
2045: { |
2046: S_marker_offd[index] = num_nonzeros_offd; |
2047: C_offd_j[num_nonzeros_offd] = index; |
2048: num_nonzeros_offd++; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
| ○ | __kmp_fork_call | libiomp5.so | |
| ○ | __kmpc_fork_call | libiomp5.so | |
| ○ | hypre_BoomerAMGCreate2ndS | par_strength.c:1668 | exec |
| ○ | hypre_BoomerAMGSetup | par_amg_setup.c:617 | exec |
| ○ | hypre_PCGSetup | pcg.c:234 | exec |
| ○ | main | amg.c:398 | exec |
| ○ | __libc_init_first | libc.so.6 |
| Path / |
| 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 | 1.20 |
| Bottlenecks | P2, P3, |
| Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
| Source | par_strength.c:2011-2048 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 9.00 |
| CQA cycles if no scalar integer | 9.00 |
| CQA cycles if FP arith vectorized | 9.00 |
| CQA cycles if fully vectorized | 1.13 |
| Front-end cycles | 7.50 |
| DIV/SQRT cycles | 2.50 |
| P0 cycles | 2.50 |
| P1 cycles | 9.00 |
| P2 cycles | 9.00 |
| P3 cycles | 3.00 |
| P4 cycles | 2.50 |
| P5 cycles | 2.50 |
| P6 cycles | 3.00 |
| P7 cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 9.18 |
| Stall cycles (UFS) | 1.73 |
| Nb insns | 26.00 |
| Nb uops | 28.00 |
| Nb loads | 18.00 |
| Nb stores | 3.00 |
| Nb stack references | 6.00 |
| 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 | 18.67 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 144.00 |
| Bytes stored | 24.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| 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 | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 12.50 |
| 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 | 1.20 |
| Bottlenecks | P2, P3, |
| Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
| Source | par_strength.c:2011-2048 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 9.00 |
| CQA cycles if no scalar integer | 9.00 |
| CQA cycles if FP arith vectorized | 9.00 |
| CQA cycles if fully vectorized | 1.13 |
| Front-end cycles | 7.50 |
| DIV/SQRT cycles | 2.50 |
| P0 cycles | 2.50 |
| P1 cycles | 9.00 |
| P2 cycles | 9.00 |
| P3 cycles | 3.00 |
| P4 cycles | 2.50 |
| P5 cycles | 2.50 |
| P6 cycles | 3.00 |
| P7 cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 9.18 |
| Stall cycles (UFS) | 1.73 |
| Nb insns | 26.00 |
| Nb uops | 28.00 |
| Nb loads | 18.00 |
| Nb stores | 3.00 |
| Nb stack references | 6.00 |
| 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 | 18.67 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 144.00 |
| Bytes stored | 24.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| 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 | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 12.50 |
| Path / |
| Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
| Source file and lines | par_strength.c:2011-2048 |
| Module | exec |
| nb instructions | 26 |
| nb uops | 28 |
| loop length | 103 |
| used x86 registers | 10 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 6 |
| micro-operation queue | 7.50 cycles |
| front end | 7.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 2.50 | 2.50 | 9.00 | 9.00 | 3.00 | 2.50 | 2.50 | 3.00 |
| cycles | 2.50 | 2.50 | 9.00 | 9.00 | 3.00 | 2.50 | 2.50 | 3.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 9.18 |
| Stall cycles | 1.73 |
| LM full (events) | 4.94 |
| Front-end | 7.50 |
| Dispatch | 9.00 |
| Overall L1 | 9.00 |
| all | 0% |
| load | 0% |
| store | 0% |
| 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 | 0% |
| all | 12% |
| load | 12% |
| store | 12% |
| 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 | 12% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|
| INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP 0x8(%RAX,%R11,8),%R10 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 48be67 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x88(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%R10,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMPQ $0,(%RAX,%RDI,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JLE 48bfb9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV 0x78(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %R9,(%R14,%RAX,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 48bfb9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV %RCX,(%R14,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV (%R15),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV %RAX,(%RBX,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| INCQ -0x30(%RBP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
| MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x8(%RAX,%RDI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JMP 48bfd3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x8(%RAX,%RDI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JMP 48c033 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
| Source file and lines | par_strength.c:2011-2048 |
| Module | exec |
| nb instructions | 26 |
| nb uops | 28 |
| loop length | 103 |
| used x86 registers | 10 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 0 |
| used zmm registers | 0 |
| nb stack references | 6 |
| micro-operation queue | 7.50 cycles |
| front end | 7.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 2.50 | 2.50 | 9.00 | 9.00 | 3.00 | 2.50 | 2.50 | 3.00 |
| cycles | 2.50 | 2.50 | 9.00 | 9.00 | 3.00 | 2.50 | 2.50 | 3.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 9.18 |
| Stall cycles | 1.73 |
| LM full (events) | 4.94 |
| Front-end | 7.50 |
| Dispatch | 9.00 |
| Overall L1 | 9.00 |
| all | 0% |
| load | 0% |
| store | 0% |
| 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 | 0% |
| all | 12% |
| load | 12% |
| store | 12% |
| 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 | 12% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|
| INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP 0x8(%RAX,%R11,8),%R10 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 48be67 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x88(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%R10,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMPQ $0,(%RAX,%RDI,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JLE 48bfb9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV 0x78(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| CMP %R9,(%R14,%RAX,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| JGE 48bfb9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV %RCX,(%R14,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| MOV (%R15),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV %RAX,(%RBX,%RCX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| INCQ -0x30(%RBP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
| MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x8(%RAX,%RDI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JMP 48bfd3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV (%RAX,%RDI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV 0x8(%RAX,%RDI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JMP 48c033 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
