Loop Id: 2542 | Module: exec | Source: par_strength.c:1731-1765 | Coverage: 0.08% |
---|
Loop Id: 2542 | Module: exec | Source: par_strength.c:1731-1765 | Coverage: 0.08% |
---|
0x48ebb0 INC %R9 |
0x48ebb3 MOV -0x50(%RBP),%R10 |
0x48ebb7 MOV -0x40(%RBP),%RDI |
0x48ebbb CMP 0x8(%R10,%RDI,8),%R9 |
0x48ebc0 MOV -0x90(%RBP),%RBX |
0x48ebc7 JGE 48ecc0 |
0x48ebcd MOV (%R12,%R9,8),%R10 |
0x48ebd1 MOV -0x58(%RBP),%R11 |
0x48ebd5 CMPQ $0,(%R11,%R10,8) |
0x48ebda JLE 48ebf7 |
0x48ebdc MOV 0x78(%RBP),%RDI |
0x48ebe0 MOV (%RDI,%R10,8),%R11 |
0x48ebe4 CMP %RCX,(%R13,%R11,8) |
0x48ebe9 JGE 48ebf7 |
0x48ebeb MOV %R8,(%R13,%R11,8) |
0x48ebf0 INC %R8 |
0x48ebf3 MOV %R8,-0x30(%RBP) |
0x48ebf7 MOV -0x50(%RBP),%RBX |
0x48ebfb MOV (%RBX,%R10,8),%R11 |
0x48ebff MOV 0x8(%RBX,%R10,8),%RBX |
0x48ec04 JMP 48ec13 |
(2544) 0x48ec10 INC %R11 |
(2544) 0x48ec13 CMP %RBX,%R11 |
(2544) 0x48ec16 JGE 48ec60 |
(2544) 0x48ec18 MOV (%R12,%R11,8),%R15 |
(2544) 0x48ec1c MOV -0x58(%RBP),%RDI |
(2544) 0x48ec20 CMPQ $0,(%RDI,%R15,8) |
(2544) 0x48ec25 JLE 48ec10 |
(2544) 0x48ec27 MOV 0x78(%RBP),%RDI |
(2544) 0x48ec2b MOV (%RDI,%R15,8),%R15 |
(2544) 0x48ec2f CMP %RAX,%R15 |
(2544) 0x48ec32 JE 48ec10 |
(2544) 0x48ec34 CMP %RCX,(%R13,%R15,8) |
(2544) 0x48ec39 JGE 48ec10 |
(2544) 0x48ec3b MOV %R8,(%R13,%R15,8) |
(2544) 0x48ec40 INC %R8 |
(2544) 0x48ec43 MOV %R8,-0x30(%RBP) |
(2544) 0x48ec47 MOV -0x50(%RBP),%RBX |
(2544) 0x48ec4b MOV 0x8(%RBX,%R10,8),%RBX |
(2544) 0x48ec50 JMP 48ec10 |
0x48ec60 MOV 0x10(%RBP),%RDI |
0x48ec64 MOV (%RDI,%R10,8),%R11 |
0x48ec68 MOV 0x8(%RDI,%R10,8),%RBX |
0x48ec6d JMP 48ec73 |
(2543) 0x48ec70 INC %R11 |
(2543) 0x48ec73 CMP %RBX,%R11 |
(2543) 0x48ec76 JGE 48ebb0 |
(2543) 0x48ec7c MOV 0x18(%RBP),%RDI |
(2543) 0x48ec80 MOV (%RDI,%R11,8),%R15 |
(2543) 0x48ec84 MOV 0x70(%RBP),%RDI |
(2543) 0x48ec88 CMPQ $0,(%RDI,%R15,8) |
(2543) 0x48ec8d JLE 48ec70 |
(2543) 0x48ec8f MOV 0x80(%RBP),%RDI |
(2543) 0x48ec96 MOV (%RDI,%R15,8),%R15 |
(2543) 0x48ec9a CMP %RDX,(%R14,%R15,8) |
(2543) 0x48ec9e JGE 48ec70 |
(2543) 0x48eca0 MOV %RSI,(%R14,%R15,8) |
(2543) 0x48eca4 INC %RSI |
(2543) 0x48eca7 MOV %RSI,-0x38(%RBP) |
(2543) 0x48ecab MOV 0x10(%RBP),%RDI |
(2543) 0x48ecaf MOV 0x8(%RDI,%R10,8),%RBX |
(2543) 0x48ecb4 JMP 48ec70 |
/scratch_na/users/xoserete/qaas_runs/171-415-3872/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c: 1731 - 1765 |
-------------------------------------------------------------------------------- |
1731: for (jj1 = S_diag_i[i1]; jj1 < S_diag_i[i1+1]; jj1++) |
1732: { |
1733: i2 = S_diag_j[jj1]; |
1734: if (CF_marker[i2] > 0) |
1735: { |
1736: index = fine_to_coarse[i2]; |
1737: if (S_marker[index] < jj_row_begin_diag) |
1738: { |
1739: S_marker[index] = num_nonzeros_diag; |
1740: num_nonzeros_diag++; |
1741: } |
1742: } |
1743: for (jj2 = S_diag_i[i2]; jj2 < S_diag_i[i2+1]; jj2++) |
1744: { |
1745: i3 = S_diag_j[jj2]; |
1746: if (CF_marker[i3] > 0) |
1747: { |
1748: index = fine_to_coarse[i3]; |
1749: if (index != ic && S_marker[index] < jj_row_begin_diag) |
1750: { |
1751: S_marker[index] = num_nonzeros_diag; |
1752: num_nonzeros_diag++; |
1753: } |
1754: } |
1755: } |
1756: for (jj2 = S_offd_i[i2]; jj2 < S_offd_i[i2+1]; jj2++) |
1757: { |
1758: i3 = S_offd_j[jj2]; |
1759: if (CF_marker_offd[i3] > 0) |
1760: { |
1761: index = map_S_to_C[i3]; |
1762: if (S_marker_offd[index] < jj_row_begin_offd) |
1763: { |
1764: S_marker_offd[index] = num_nonzeros_offd; |
1765: num_nonzeros_offd++; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
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 | 1.19 |
Bottlenecks | P2, P3, P11, |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source | par_strength.c:1731-1740,par_strength.c:1743-1743,par_strength.c:1756-1756 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.33 |
CQA cycles if no scalar integer | 5.33 |
CQA cycles if FP arith vectorized | 5.33 |
CQA cycles if fully vectorized | 0.67 |
Front-end cycles | 4.50 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.00 |
P1 cycles | 5.33 |
P2 cycles | 5.33 |
P3 cycles | 1.00 |
P4 cycles | 1.00 |
P5 cycles | 1.50 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 1.00 |
P10 cycles | 5.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.54 |
Stall cycles (UFS) | 1.89 |
Nb insns | 25.00 |
Nb uops | 25.00 |
Nb loads | 16.00 |
Nb stores | 2.00 |
Nb stack references | 7.00 |
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 | 27.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 16.00 |
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 | 1.19 |
Bottlenecks | P2, P3, P11, |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source | par_strength.c:1731-1740,par_strength.c:1743-1743,par_strength.c:1756-1756 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.33 |
CQA cycles if no scalar integer | 5.33 |
CQA cycles if FP arith vectorized | 5.33 |
CQA cycles if fully vectorized | 0.67 |
Front-end cycles | 4.50 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.00 |
P1 cycles | 5.33 |
P2 cycles | 5.33 |
P3 cycles | 1.00 |
P4 cycles | 1.00 |
P5 cycles | 1.50 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 1.00 |
P10 cycles | 5.33 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.54 |
Stall cycles (UFS) | 1.89 |
Nb insns | 25.00 |
Nb uops | 25.00 |
Nb loads | 16.00 |
Nb stores | 2.00 |
Nb stack references | 7.00 |
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 | 27.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 16.00 |
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:1731-1765 |
Module | exec |
nb instructions | 25 |
nb uops | 25 |
loop length | 101 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 4.50 cycles |
front end | 4.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.00 | 5.33 | 5.33 | 1.00 | 1.00 | 1.50 | 1.00 | 1.00 | 1.00 | 1.00 | 5.33 |
cycles | 1.50 | 1.00 | 5.33 | 5.33 | 1.00 | 1.00 | 1.50 | 1.00 | 1.00 | 1.00 | 1.00 | 5.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.54 |
Stall cycles | 1.89 |
LM full (events) | 4.83 |
Front-end | 4.50 |
Dispatch | 5.33 |
Overall L1 | 5.33 |
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 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x50(%RBP),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x40(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%R10,%RDI,8),%R9 | 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 -0x90(%RBP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JGE 48ecc0 <hypre_BoomerAMGCreate2ndS.extracted.17+0x310> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV (%R12,%R9,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x58(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMPQ $0,(%R11,%R10,8) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JLE 48ebf7 <hypre_BoomerAMGCreate2ndS.extracted.17+0x247> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x78(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI,%R10,8),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP %RCX,(%R13,%R11,8) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JGE 48ebf7 <hypre_BoomerAMGCreate2ndS.extracted.17+0x247> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,(%R13,%R11,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R8,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x50(%RBP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RBX,%R10,8),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RBX,%R10,8),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 48ec13 <hypre_BoomerAMGCreate2ndS.extracted.17+0x263> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
MOV 0x10(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI,%R10,8),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RDI,%R10,8),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 48ec73 <hypre_BoomerAMGCreate2ndS.extracted.17+0x2c3> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source file and lines | par_strength.c:1731-1765 |
Module | exec |
nb instructions | 25 |
nb uops | 25 |
loop length | 101 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 4.50 cycles |
front end | 4.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.00 | 5.33 | 5.33 | 1.00 | 1.00 | 1.50 | 1.00 | 1.00 | 1.00 | 1.00 | 5.33 |
cycles | 1.50 | 1.00 | 5.33 | 5.33 | 1.00 | 1.00 | 1.50 | 1.00 | 1.00 | 1.00 | 1.00 | 5.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.54 |
Stall cycles | 1.89 |
LM full (events) | 4.83 |
Front-end | 4.50 |
Dispatch | 5.33 |
Overall L1 | 5.33 |
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 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x50(%RBP),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x40(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%R10,%RDI,8),%R9 | 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 -0x90(%RBP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JGE 48ecc0 <hypre_BoomerAMGCreate2ndS.extracted.17+0x310> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV (%R12,%R9,8),%R10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x58(%RBP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMPQ $0,(%R11,%R10,8) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JLE 48ebf7 <hypre_BoomerAMGCreate2ndS.extracted.17+0x247> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x78(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI,%R10,8),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP %RCX,(%R13,%R11,8) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JGE 48ebf7 <hypre_BoomerAMGCreate2ndS.extracted.17+0x247> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,(%R13,%R11,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R8,-0x30(%RBP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x50(%RBP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RBX,%R10,8),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RBX,%R10,8),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 48ec13 <hypre_BoomerAMGCreate2ndS.extracted.17+0x263> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
MOV 0x10(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI,%R10,8),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RDI,%R10,8),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 48ec73 <hypre_BoomerAMGCreate2ndS.extracted.17+0x2c3> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |