Loop Id: 238 | Module: exec | Source: par_coarsen.c:2232-2243 | Coverage: 0.03% |
---|
Loop Id: 238 | Module: exec | Source: par_coarsen.c:2232-2243 | Coverage: 0.03% |
---|
0x425c80 MOV %RDX,(%RCX,%RAX,8) [3] |
0x425c84 INC %RAX |
0x425c87 LEA (%RSI,%RDX,1),%RDI |
0x425c8b ADD $0x2,%RDI |
0x425c8f ADD $0x2,%RDX |
0x425c93 CMP $0x1,%RDI |
0x425c97 JE 425d3c |
0x425c9d MOVQ $0,-0x8(%R15,%RDX,8) [6] |
0x425ca6 MOV -0x78(%RBP),%RBX [7] |
0x425caa MOV (%RBX,%RDX,8),%RDI [1] |
0x425cae CMP -0x8(%RBX,%RDX,8),%RDI [1] |
0x425cb3 JNE 425ce0 |
0x425cb5 MOV -0x80(%RBP),%RBX [7] |
0x425cb9 MOV (%RBX,%RDX,8),%RDI [2] |
0x425cbd CMP -0x8(%RBX,%RDX,8),%RDI [2] |
0x425cc2 JNE 425ce0 |
0x425cc4 MOV %R9,-0x8(%R15,%RDX,8) [6] |
0x425cc9 MOVQ $0,-0x8(%R13,%RDX,8) [5] |
0x425cd2 JMP 425ceb |
0x425ce0 LEA -0x1(%RDX),%RDI |
0x425ce4 MOV %RDI,(%RCX,%RAX,8) [4] |
0x425ce8 INC %RAX |
0x425ceb MOVQ $0,(%R15,%RDX,8) [6] |
0x425cf3 MOV -0x78(%RBP),%RBX [7] |
0x425cf7 MOV 0x8(%RBX,%RDX,8),%RDI [1] |
0x425cfc CMP (%RBX,%RDX,8),%RDI [1] |
0x425d00 JNE 425c80 |
0x425d06 MOV -0x80(%RBP),%RBX [7] |
0x425d0a MOV 0x8(%RBX,%RDX,8),%RDI [2] |
0x425d0f CMP (%RBX,%RDX,8),%RDI [2] |
0x425d13 JNE 425c80 |
0x425d19 MOV %R9,(%R15,%RDX,8) [6] |
0x425d1d MOVQ $0,(%R13,%RDX,8) [5] |
0x425d26 LEA (%RSI,%RDX,1),%RDI |
0x425d2a ADD $0x2,%RDI |
0x425d2e ADD $0x2,%RDX |
0x425d32 CMP $0x1,%RDI |
0x425d36 JNE 425c9d |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_coarsen.c: 2232 - 2243 |
-------------------------------------------------------------------------------- |
2232: for (i=0; i < num_variables; i++) |
2233: { |
2234: CF_marker[i] = 0; |
2235: if ( (S_diag_i[i+1]-S_diag_i[i]) == 0 |
2236: && (S_offd_i[i+1]-S_offd_i[i]) == 0) |
2237: { |
2238: CF_marker[i] = SF_PT; /* an isolated fine grid */ |
2239: if (CF_init == 3 || CF_init == 4) CF_marker[i] = C_PT; |
2240: measure_array[i] = 0; |
2241: } |
2242: else |
2243: graph_array[cnt++] = i; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | hypre_BoomerAMGSetup | par_amg_setup.c:601 | 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 | 12.94 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.28 |
Bottlenecks | micro-operation queue, |
Function | hypre_BoomerAMGCoarsenPMIS |
Source | par_coarsen.c:2232-2243 |
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 | 10.25 |
CQA cycles if no scalar integer | 10.25 |
CQA cycles if FP arith vectorized | 10.25 |
CQA cycles if fully vectorized | 0.79 |
Front-end cycles | 10.25 |
DIV/SQRT cycles | 5.25 |
P0 cycles | 5.25 |
P1 cycles | 6.67 |
P2 cycles | 6.67 |
P3 cycles | 8.00 |
P4 cycles | 5.25 |
P5 cycles | 5.25 |
P6 cycles | 6.67 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 10.40 |
Stall cycles (UFS) | 0.00 |
Nb insns | 38.00 |
Nb uops | 37.00 |
Nb loads | 12.00 |
Nb stores | 8.00 |
Nb stack references | 2.00 |
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 | 15.61 |
Bytes prefetched | 0.00 |
Bytes loaded | 96.00 |
Bytes stored | 64.00 |
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 | 10.58 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 9.38 |
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 | 12.94 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.28 |
Bottlenecks | micro-operation queue, |
Function | hypre_BoomerAMGCoarsenPMIS |
Source | par_coarsen.c:2232-2243 |
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 | 10.25 |
CQA cycles if no scalar integer | 10.25 |
CQA cycles if FP arith vectorized | 10.25 |
CQA cycles if fully vectorized | 0.79 |
Front-end cycles | 10.25 |
DIV/SQRT cycles | 5.25 |
P0 cycles | 5.25 |
P1 cycles | 6.67 |
P2 cycles | 6.67 |
P3 cycles | 8.00 |
P4 cycles | 5.25 |
P5 cycles | 5.25 |
P6 cycles | 6.67 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 10.40 |
Stall cycles (UFS) | 0.00 |
Nb insns | 38.00 |
Nb uops | 37.00 |
Nb loads | 12.00 |
Nb stores | 8.00 |
Nb stack references | 2.00 |
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 | 15.61 |
Bytes prefetched | 0.00 |
Bytes loaded | 96.00 |
Bytes stored | 64.00 |
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 | 10.58 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 9.38 |
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_BoomerAMGCoarsenPMIS |
Source file and lines | par_coarsen.c:2232-2243 |
Module | exec |
nb instructions | 38 |
nb uops | 37 |
loop length | 176 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 10.25 cycles |
front end | 10.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 5.25 | 5.25 | 6.67 | 6.67 | 8.00 | 5.25 | 5.25 | 6.67 |
cycles | 5.25 | 5.25 | 6.67 | 6.67 | 8.00 | 5.25 | 5.25 | 6.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 10.40 |
Stall cycles | 0.00 |
Front-end | 10.25 |
Dispatch | 8.00 |
Overall L1 | 10.25 |
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 | 10% |
load | 12% |
store | 9% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV %RDX,(%RCX,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RSI,%RDX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x2,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD $0x2,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x1,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 425d3c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVQ $0,-0x8(%R15,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV -0x78(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RDX,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP -0x8(%RBX,%RDX,8),%RDI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 425ce0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x80(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RDX,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP -0x8(%RBX,%RDX,8),%RDI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 425ce0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R9,-0x8(%R15,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVQ $0,-0x8(%R13,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
JMP 425ceb | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
LEA -0x1(%RDX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RDI,(%RCX,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOVQ $0,(%R15,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV -0x78(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RBX,%RDX,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP (%RBX,%RDX,8),%RDI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 425c80 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x80(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RBX,%RDX,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP (%RBX,%RDX,8),%RDI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 425c80 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R9,(%R15,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVQ $0,(%R13,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
LEA (%RSI,%RDX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x2,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD $0x2,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x1,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 425c9d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | hypre_BoomerAMGCoarsenPMIS |
Source file and lines | par_coarsen.c:2232-2243 |
Module | exec |
nb instructions | 38 |
nb uops | 37 |
loop length | 176 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 10.25 cycles |
front end | 10.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 5.25 | 5.25 | 6.67 | 6.67 | 8.00 | 5.25 | 5.25 | 6.67 |
cycles | 5.25 | 5.25 | 6.67 | 6.67 | 8.00 | 5.25 | 5.25 | 6.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 10.40 |
Stall cycles | 0.00 |
Front-end | 10.25 |
Dispatch | 8.00 |
Overall L1 | 10.25 |
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 | 10% |
load | 12% |
store | 9% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|
MOV %RDX,(%RCX,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RSI,%RDX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x2,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD $0x2,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x1,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 425d3c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVQ $0,-0x8(%R15,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV -0x78(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RDX,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP -0x8(%RBX,%RDX,8),%RDI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 425ce0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x80(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RBX,%RDX,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP -0x8(%RBX,%RDX,8),%RDI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 425ce0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R9,-0x8(%R15,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVQ $0,-0x8(%R13,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
JMP 425ceb | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
LEA -0x1(%RDX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RDI,(%RCX,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOVQ $0,(%R15,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV -0x78(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RBX,%RDX,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP (%RBX,%RDX,8),%RDI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 425c80 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x80(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RBX,%RDX,8),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP (%RBX,%RDX,8),%RDI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 425c80 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R9,(%R15,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVQ $0,(%R13,%RDX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
LEA (%RSI,%RDX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $0x2,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD $0x2,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x1,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 425c9d | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |