Loop Id: 2292 | Module: exec | Source: par_strength.c:492-513 | Coverage: 0.01% |
---|
Loop Id: 2292 | Module: exec | Source: par_strength.c:492-513 | Coverage: 0.01% |
---|
0x4970a0 CMP %R10,%RCX |
0x4970a3 JE 497180 |
0x4970a9 MOV %RCX,%RDI |
0x4970ac MOV 0x50(%RBP),%RAX |
0x4970b0 ADD %R8,(%RAX,%RCX,8) |
0x4970b4 ADD %R9,(%R13,%RCX,8) |
0x4970b9 MOV 0x10(%RBP),%RAX |
0x4970bd MOV (%RAX,%RCX,8),%RBX |
0x4970c1 MOV 0x8(%RAX,%RCX,8),%RAX |
0x4970c6 INC %RCX |
0x4970c9 CMP %RAX,%RBX |
0x4970cc JGE 497120 |
0x4970ce MOV 0x50(%RBP),%RDX |
0x4970d2 MOV (%RDX,%RDI,8),%RDX |
0x4970d6 JMP 4970e8 |
(2294) 0x4970e0 INC %RBX |
(2294) 0x4970e3 CMP %RAX,%RBX |
(2294) 0x4970e6 JGE 497120 |
(2294) 0x4970e8 MOV (%R12,%RBX,8),%RSI |
(2294) 0x4970ec TEST %RSI,%RSI |
(2294) 0x4970ef JS 4970e0 |
(2294) 0x4970f1 MOV %RSI,(%R14,%RDX,8) |
(2294) 0x4970f5 INC %RDX |
(2294) 0x4970f8 MOV 0x10(%RBP),%RAX |
(2294) 0x4970fc MOV (%RAX,%RCX,8),%RAX |
(2294) 0x497100 JMP 4970e0 |
0x497120 MOV 0x20(%RBP),%RAX |
0x497124 MOV (%RAX,%RDI,8),%RBX |
0x497128 MOV (%RAX,%RCX,8),%RAX |
0x49712c CMP %RAX,%RBX |
0x49712f JGE 4970a0 |
0x497135 MOV (%R13,%RDI,8),%RDX |
0x49713a JMP 49714c |
(2293) 0x497140 INC %RBX |
(2293) 0x497143 CMP %RAX,%RBX |
(2293) 0x497146 JGE 4970a0 |
(2293) 0x49714c MOV (%R15,%RBX,8),%RSI |
(2293) 0x497150 TEST %RSI,%RSI |
(2293) 0x497153 JS 497140 |
(2293) 0x497155 MOV %RSI,(%R11,%RDX,8) |
(2293) 0x497159 INC %RDX |
(2293) 0x49715c MOV 0x20(%RBP),%RAX |
(2293) 0x497160 MOV (%RAX,%RCX,8),%RAX |
(2293) 0x497164 JMP 497140 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c: 492 - 513 |
-------------------------------------------------------------------------------- |
492: for (i = start; i < stop; i++) |
493: { |
494: S_diag_i[i] += jS_diag; |
495: S_offd_i[i] += jS_offd; |
496: |
497: jS = S_diag_i[i]; |
498: for (jA = A_diag_i[i]; jA < A_diag_i[i+1]; jA++) |
499: { |
500: if (S_temp_diag_j[jA] > -1) |
501: { |
502: S_diag_j[jS] = S_temp_diag_j[jA]; |
503: jS++; |
504: } |
505: } |
506: |
507: jS = S_offd_i[i]; |
508: for (jA = A_offd_i[i]; jA < A_offd_i[i+1]; jA++) |
509: { |
510: if (S_temp_offd_j[jA] > -1) |
511: { |
512: S_offd_j[jS] = S_temp_offd_j[jA]; |
513: jS++; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_BoomerAMGCreateS | par_strength.c:246 | exec |
○ | hypre_BoomerAMGSetup | par_amg_setup.c:577 | 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 | 2.18 |
Bottlenecks | micro-operation queue, P2, P3, |
Function | hypre_BoomerAMGCreateS.extracted |
Source | par_strength.c:492-513 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 6.00 |
CQA cycles if no scalar integer | 6.00 |
CQA cycles if FP arith vectorized | 6.00 |
CQA cycles if fully vectorized | 0.75 |
Front-end cycles | 6.00 |
DIV/SQRT cycles | 2.75 |
P0 cycles | 2.75 |
P1 cycles | 6.00 |
P2 cycles | 6.00 |
P3 cycles | 2.00 |
P4 cycles | 2.75 |
P5 cycles | 2.75 |
P6 cycles | 2.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 7.18 |
Stall cycles (UFS) | 0.00 |
Nb insns | 22.00 |
Nb uops | 24.00 |
Nb loads | 12.00 |
Nb stores | 2.00 |
Nb stack references | 3.00 |
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 | 96.00 |
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 | 2.18 |
Bottlenecks | micro-operation queue, P2, P3, |
Function | hypre_BoomerAMGCreateS.extracted |
Source | par_strength.c:492-513 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 6.00 |
CQA cycles if no scalar integer | 6.00 |
CQA cycles if FP arith vectorized | 6.00 |
CQA cycles if fully vectorized | 0.75 |
Front-end cycles | 6.00 |
DIV/SQRT cycles | 2.75 |
P0 cycles | 2.75 |
P1 cycles | 6.00 |
P2 cycles | 6.00 |
P3 cycles | 2.00 |
P4 cycles | 2.75 |
P5 cycles | 2.75 |
P6 cycles | 2.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 7.18 |
Stall cycles (UFS) | 0.00 |
Nb insns | 22.00 |
Nb uops | 24.00 |
Nb loads | 12.00 |
Nb stores | 2.00 |
Nb stack references | 3.00 |
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 | 96.00 |
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_BoomerAMGCreateS.extracted |
Source file and lines | par_strength.c:492-513 |
Module | exec |
nb instructions | 22 |
nb uops | 24 |
loop length | 84 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 3 |
micro-operation queue | 6.00 cycles |
front end | 6.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.75 | 2.75 | 6.00 | 6.00 | 2.00 | 2.75 | 2.75 | 2.00 |
cycles | 2.75 | 2.75 | 6.00 | 6.00 | 2.00 | 2.75 | 2.75 | 2.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 7.18 |
Stall cycles | 0.00 |
Front-end | 6.00 |
Dispatch | 6.00 |
Overall L1 | 6.00 |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|
CMP %R10,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 497180 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R8,(%RAX,%RCX,8) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
ADD %R9,(%R13,%RCX,8) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 497120 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x50(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX,%RDI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4970e8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV 0x20(%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 (%RAX,%RCX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RAX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 4970a0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV (%R13,%RDI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 49714c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
Function | hypre_BoomerAMGCreateS.extracted |
Source file and lines | par_strength.c:492-513 |
Module | exec |
nb instructions | 22 |
nb uops | 24 |
loop length | 84 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 3 |
micro-operation queue | 6.00 cycles |
front end | 6.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.75 | 2.75 | 6.00 | 6.00 | 2.00 | 2.75 | 2.75 | 2.00 |
cycles | 2.75 | 2.75 | 6.00 | 6.00 | 2.00 | 2.75 | 2.75 | 2.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 7.18 |
Stall cycles | 0.00 |
Front-end | 6.00 |
Dispatch | 6.00 |
Overall L1 | 6.00 |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|
CMP %R10,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 497180 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RCX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R8,(%RAX,%RCX,8) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
ADD %R9,(%R13,%RCX,8) | 2 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RCX,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RCX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
INC %RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 497120 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x50(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX,%RDI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4970e8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV 0x20(%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 (%RAX,%RCX,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RAX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JGE 4970a0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV (%R13,%RDI,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 49714c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |