Loop Id: 2531 | Module: libparcsr_ls.so | Source: par_strength.c:2000-2083 [...] | Coverage: 0.04% |
---|
Loop Id: 2531 | Module: libparcsr_ls.so | Source: par_strength.c:2000-2083 [...] | Coverage: 0.04% |
---|
0xb9380 INC %RBX |
0xb9383 CMP -0x78(%RBP),%RBX |
0xb9387 JE b9c6b |
0xb938d MOV 0xa0(%RBP),%RAX |
0xb9394 MOV (%RAX,%RBX,8),%RAX |
0xb9398 MOV -0x30(%RBP),%RCX |
0xb939c MOV -0x38(%RBP),%RDX |
0xb93a0 MOV -0x50(%RBP),%RDI |
0xb93a4 MOV (%RDI,%RAX,8),%RSI |
0xb93a8 CMP 0x8(%RDI,%RAX,8),%RSI |
0xb93ad MOV 0x40(%RBP),%R12 |
0xb93b1 JL b93ce |
0xb93b3 MOV 0x10(%RBP),%RDI |
0xb93b7 MOV (%RDI,%RAX,8),%RSI |
0xb93bb JMP b94e7 |
(2535) 0xb93c0 INC %RSI |
(2535) 0xb93c3 MOV -0x50(%RBP),%RDI |
(2535) 0xb93c7 CMP 0x8(%RDI,%RAX,8),%RSI |
(2535) 0xb93cc JGE b93b3 |
(2535) 0xb93ce MOV (%R15,%RSI,8),%RDI |
(2535) 0xb93d2 MOV -0x68(%RBP),%R8 |
(2535) 0xb93d6 CMPQ $0,(%R8,%RDI,8) |
(2535) 0xb93db JLE b9402 |
(2535) 0xb93dd MOV 0x78(%RBP),%R8 |
(2535) 0xb93e1 MOV (%R8,%RDI,8),%R8 |
(2535) 0xb93e5 CMP %RCX,(%R14,%R8,8) |
(2535) 0xb93e9 JGE b9402 |
(2535) 0xb93eb MOV -0x30(%RBP),%R9 |
(2535) 0xb93ef MOV %R9,(%R14,%R8,8) |
(2535) 0xb93f3 MOV 0x30(%RBP),%R10 |
(2535) 0xb93f7 MOV (%R10),%R10 |
(2535) 0xb93fa MOV %R8,(%R10,%R9,8) |
(2535) 0xb93fe INCQ -0x30(%RBP) |
(2535) 0xb9402 MOV -0x50(%RBP),%R9 |
(2535) 0xb9406 MOV (%R9,%RDI,8),%R8 |
(2535) 0xb940a MOV 0x8(%R9,%RDI,8),%R9 |
(2535) 0xb940f JMP b9423 |
(2537) 0xb9420 INC %R8 |
(2537) 0xb9423 CMP %R9,%R8 |
(2537) 0xb9426 JGE b9470 |
(2537) 0xb9428 MOV (%R15,%R8,8),%R10 |
(2537) 0xb942c MOV -0x68(%RBP),%R11 |
(2537) 0xb9430 CMPQ $0,(%R11,%R10,8) |
(2537) 0xb9435 JLE b9420 |
(2537) 0xb9437 MOV 0x78(%RBP),%R11 |
(2537) 0xb943b MOV (%R11,%R10,8),%R10 |
(2537) 0xb943f CMP %RBX,%R10 |
(2537) 0xb9442 JE b9420 |
(2537) 0xb9444 CMP %RCX,(%R14,%R10,8) |
(2537) 0xb9448 JGE b9420 |
(2537) 0xb944a MOV -0x30(%RBP),%R9 |
(2537) 0xb944e MOV %R9,(%R14,%R10,8) |
(2537) 0xb9452 MOV 0x30(%RBP),%R11 |
(2537) 0xb9456 MOV (%R11),%R11 |
(2537) 0xb9459 MOV %R10,(%R11,%R9,8) |
(2537) 0xb945d INCQ -0x30(%RBP) |
(2537) 0xb9461 MOV -0x50(%RBP),%R9 |
(2537) 0xb9465 MOV 0x8(%R9,%RDI,8),%R9 |
(2537) 0xb946a JMP b9420 |
(2535) 0xb9470 MOV 0x10(%RBP),%R9 |
(2535) 0xb9474 MOV (%R9,%RDI,8),%R8 |
(2535) 0xb9478 MOV 0x8(%R9,%RDI,8),%R9 |
(2535) 0xb947d JMP b9483 |
(2536) 0xb9480 INC %R8 |
(2536) 0xb9483 CMP %R9,%R8 |
(2536) 0xb9486 JGE b93c0 |
(2536) 0xb948c MOV 0x18(%RBP),%R10 |
(2536) 0xb9490 MOV (%R10,%R8,8),%R10 |
(2536) 0xb9494 MOV 0x70(%RBP),%R11 |
(2536) 0xb9498 CMPQ $0,(%R11,%R10,8) |
(2536) 0xb949d JLE b9480 |
(2536) 0xb949f MOV 0x80(%RBP),%R11 |
(2536) 0xb94a6 MOV (%R11,%R10,8),%R10 |
(2536) 0xb94aa CMP %RDX,(%R13,%R10,8) |
(2536) 0xb94af JGE b9480 |
(2536) 0xb94b1 MOV -0x38(%RBP),%R9 |
(2536) 0xb94b5 MOV %R9,(%R13,%R10,8) |
(2536) 0xb94ba MOV (%R12),%R11 |
(2536) 0xb94be MOV %R10,(%R11,%R9,8) |
(2536) 0xb94c2 INCQ -0x38(%RBP) |
(2536) 0xb94c6 MOV 0x10(%RBP),%R9 |
(2536) 0xb94ca MOV 0x8(%R9,%RDI,8),%R9 |
(2536) 0xb94cf JMP b9480 |
(2532) 0xb94e0 INC %RSI |
(2532) 0xb94e3 MOV 0x10(%RBP),%RDI |
(2532) 0xb94e7 CMP 0x8(%RDI,%RAX,8),%RSI |
(2532) 0xb94ec JGE b9380 |
(2532) 0xb94f2 MOV 0x18(%RBP),%RDI |
(2532) 0xb94f6 MOV (%RDI,%RSI,8),%RDI |
(2532) 0xb94fa MOV 0x70(%RBP),%R8 |
(2532) 0xb94fe CMPQ $0,(%R8,%RDI,8) |
(2532) 0xb9503 JLE b952c |
(2532) 0xb9505 MOV 0x80(%RBP),%R8 |
(2532) 0xb950c MOV (%R8,%RDI,8),%R8 |
(2532) 0xb9510 CMP %RDX,(%R13,%R8,8) |
(2532) 0xb9515 JGE b952c |
(2532) 0xb9517 MOV -0x38(%RBP),%R9 |
(2532) 0xb951b MOV %R9,(%R13,%R8,8) |
(2532) 0xb9520 MOV (%R12),%R10 |
(2532) 0xb9524 MOV %R8,(%R10,%R9,8) |
(2532) 0xb9528 INCQ -0x38(%RBP) |
(2532) 0xb952c MOV 0x50(%RBP),%R9 |
(2532) 0xb9530 MOV (%R9,%RDI,8),%R8 |
(2532) 0xb9534 MOV 0x8(%R9,%RDI,8),%R9 |
(2532) 0xb9539 JMP b9543 |
(2534) 0xb9540 INC %R8 |
(2534) 0xb9543 CMP %R9,%R8 |
(2534) 0xb9546 JGE b9580 |
(2534) 0xb9548 MOV 0x58(%RBP),%R10 |
(2534) 0xb954c MOV (%R10,%R8,8),%R10 |
(2534) 0xb9550 CMP %RBX,%R10 |
(2534) 0xb9553 JE b9540 |
(2534) 0xb9555 CMP %RCX,(%R14,%R10,8) |
(2534) 0xb9559 JGE b9540 |
(2534) 0xb955b MOV -0x30(%RBP),%R9 |
(2534) 0xb955f MOV %R9,(%R14,%R10,8) |
(2534) 0xb9563 MOV 0x30(%RBP),%R11 |
(2534) 0xb9567 MOV (%R11),%R11 |
(2534) 0xb956a MOV %R10,(%R11,%R9,8) |
(2534) 0xb956e INCQ -0x30(%RBP) |
(2534) 0xb9572 MOV 0x50(%RBP),%R9 |
(2534) 0xb9576 MOV 0x8(%R9,%RDI,8),%R9 |
(2534) 0xb957b JMP b9540 |
(2532) 0xb9580 MOV 0x60(%RBP),%R9 |
(2532) 0xb9584 MOV (%R9,%RDI,8),%R8 |
(2532) 0xb9588 MOV 0x8(%R9,%RDI,8),%R9 |
(2532) 0xb958d JMP b9593 |
(2533) 0xb9590 INC %R8 |
(2533) 0xb9593 CMP %R9,%R8 |
(2533) 0xb9596 JGE b94e0 |
(2533) 0xb959c MOV 0x68(%RBP),%R10 |
(2533) 0xb95a0 MOV (%R10,%R8,8),%R10 |
(2533) 0xb95a4 CMP %RDX,(%R13,%R10,8) |
(2533) 0xb95a9 JGE b9590 |
(2533) 0xb95ab MOV -0x38(%RBP),%R9 |
(2533) 0xb95af MOV %R9,(%R13,%R10,8) |
(2533) 0xb95b4 MOV (%R12),%R11 |
(2533) 0xb95b8 MOV %R10,(%R11,%R9,8) |
(2533) 0xb95bc INCQ -0x38(%RBP) |
(2533) 0xb95c0 MOV 0x60(%RBP),%R9 |
(2533) 0xb95c4 MOV 0x8(%R9,%RDI,8),%R9 |
(2533) 0xb95c9 JMP b9590 |
/home/eoseret/qaas_runs_CPU_9468/172-019-1763/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c: 2000 - 2083 |
-------------------------------------------------------------------------------- |
2000: for (ic = ic_begin; ic < ic_end; ic++) |
[...] |
2006: HYPRE_Int i1 = coarse_to_fine[ic]; |
2007: |
2008: HYPRE_Int jj_row_begin_diag = num_nonzeros_diag; |
2009: HYPRE_Int jj_row_begin_offd = num_nonzeros_offd; |
2010: |
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++; |
2049: } |
2050: } |
2051: } |
2052: } |
2053: for (jj1 = S_offd_i[i1]; jj1 < S_offd_i[i1+1]; jj1++) |
2054: { |
2055: i2 = S_offd_j[jj1]; |
2056: if (CF_marker_offd[i2] > 0) |
2057: { |
2058: index = map_S_to_C[i2]; |
2059: if (S_marker_offd[index] < jj_row_begin_offd) |
2060: { |
2061: S_marker_offd[index] = num_nonzeros_offd; |
2062: C_offd_j[num_nonzeros_offd] = index; |
2063: num_nonzeros_offd++; |
2064: } |
2065: } |
2066: for (jj2 = S_ext_diag_i[i2]; jj2 < S_ext_diag_i[i2+1]; jj2++) |
2067: { |
2068: i3 = S_ext_diag_j[jj2]; |
2069: if (i3 != ic && S_marker[i3] < jj_row_begin_diag) |
2070: { |
2071: S_marker[i3] = num_nonzeros_diag; |
2072: C_diag_j[num_nonzeros_diag] = i3; |
2073: num_nonzeros_diag++; |
2074: } |
2075: } |
2076: for (jj2 = S_ext_offd_i[i2]; jj2 < S_ext_offd_i[i2+1]; jj2++) |
2077: { |
2078: i3 = S_ext_offd_j[jj2]; |
2079: if (S_marker_offd[i3] < jj_row_begin_offd) |
2080: { |
2081: S_marker_offd[i3] = num_nonzeros_offd; |
2082: C_offd_j[num_nonzeros_offd] = i3; |
2083: 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.A | ams.c:3855 | libparcsr_ls.so |
○ | hypre_BoomerAMGSetup.A | ams.c:3855 | libparcsr_ls.so |
○ | hypre_BoomerAMGSetup | ams.c:3550 | libparcsr_ls.so |
○ | hypre_PCGSetup | gmres.c:1245 | libkrylov.so |
○ | main.A | amg.c:398 | exec |
○ | __libc_start_call_main | libc.so.6 |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
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 | 4.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.47 |
Bottlenecks | P5, P6, P7, |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source | par_strength.c:2000-2000,par_strength.c:2006-2011,par_strength.c:2053-2053 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.67 |
CQA cycles if no scalar integer | 3.67 |
CQA cycles if FP arith vectorized | 3.67 |
CQA cycles if fully vectorized | 0.92 |
Front-end cycles | 2.50 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.00 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 1.50 |
P4 cycles | 3.67 |
P5 cycles | 3.67 |
P6 cycles | 3.67 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
P12 cycles | 0.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 15.00 |
Nb uops | 15.00 |
Nb loads | 11.00 |
Nb stores | 0.00 |
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 | 24.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 88.00 |
Bytes stored | 0.00 |
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 | NA |
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 | NA |
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 | 4.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.47 |
Bottlenecks | P5, P6, P7, |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source | par_strength.c:2000-2000,par_strength.c:2006-2011,par_strength.c:2053-2053 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.67 |
CQA cycles if no scalar integer | 3.67 |
CQA cycles if FP arith vectorized | 3.67 |
CQA cycles if fully vectorized | 0.92 |
Front-end cycles | 2.50 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.00 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 1.50 |
P4 cycles | 3.67 |
P5 cycles | 3.67 |
P6 cycles | 3.67 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
P12 cycles | 0.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 15.00 |
Nb uops | 15.00 |
Nb loads | 11.00 |
Nb stores | 0.00 |
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 | 24.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 88.00 |
Bytes stored | 0.00 |
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 | NA |
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 | NA |
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:2000-2083 |
Module | libparcsr_ls.so |
nb instructions | 15 |
nb uops | 15 |
loop length | 64 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 2.50 cycles |
front end | 2.50 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.00 | 1.00 | 1.00 | 1.50 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 1.50 | 1.00 | 1.00 | 1.00 | 1.50 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Front-end | 2.50 |
Dispatch | 3.67 |
Overall L1 | 3.67 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
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 | NA (no store vectorizable/vectorized instructions) |
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 | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %RBX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP -0x78(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (12.5%) |
JE b9c6b <hypre_BoomerAMGCreate2ndS.extracted.17+0x165b> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV 0xa0(%RBP),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV (%RAX,%RBX,8),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (12.5%) |
MOV -0x38(%RBP),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (12.5%) |
MOV -0x50(%RBP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV (%RDI,%RAX,8),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP 0x8(%RDI,%RAX,8),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
MOV 0x40(%RBP),%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (12.5%) |
JL b93ce <hypre_BoomerAMGCreate2ndS.extracted.17+0xdbe> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV 0x10(%RBP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV (%RDI,%RAX,8),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
JMP b94e7 <hypre_BoomerAMGCreate2ndS.extracted.17+0xed7> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | N/A |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source file and lines | par_strength.c:2000-2083 |
Module | libparcsr_ls.so |
nb instructions | 15 |
nb uops | 15 |
loop length | 64 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 2.50 cycles |
front end | 2.50 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.00 | 1.00 | 1.00 | 1.50 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 1.50 | 1.00 | 1.00 | 1.00 | 1.50 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Front-end | 2.50 |
Dispatch | 3.67 |
Overall L1 | 3.67 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
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 | NA (no store vectorizable/vectorized instructions) |
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 | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %RBX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP -0x78(%RBP),%RBX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (12.5%) |
JE b9c6b <hypre_BoomerAMGCreate2ndS.extracted.17+0x165b> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV 0xa0(%RBP),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV (%RAX,%RBX,8),%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (12.5%) |
MOV -0x38(%RBP),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (12.5%) |
MOV -0x50(%RBP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV (%RDI,%RAX,8),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP 0x8(%RDI,%RAX,8),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
MOV 0x40(%RBP),%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | scal (12.5%) |
JL b93ce <hypre_BoomerAMGCreate2ndS.extracted.17+0xdbe> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV 0x10(%RBP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
MOV (%RDI,%RAX,8),%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
JMP b94e7 <hypre_BoomerAMGCreate2ndS.extracted.17+0xed7> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | N/A |
Run 8x1 | Number processes: 8Number nodes: 1Run Command: <executable> -n 400 400 400MPI Command: mpirun -n <number_processes>Dataset: Run Directory: /home/eoseret/qaas_runs_CPU_9468/172-019-1763/intel/AMG/run/oneview_runs/multicore/icx_9/oneview_run_1720211326OMP_PROC_BIND: spreadI_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threadsOMP_NUM_THREADS: 1 |
---|---|
Run 8x2 | Number processes: 8OMP_NUM_THREADS: 2OMP_PROC_BIND: spreadI_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threads |
Run 8x4 | Number processes: 8OMP_NUM_THREADS: 4OMP_PROC_BIND: spreadI_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threads |
Run 8x8 | Number processes: 8OMP_NUM_THREADS: 8OMP_PROC_BIND: spreadI_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threads |
Run 8x16 | Number processes: 8OMP_NUM_THREADS: 16OMP_PROC_BIND: spreadI_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threads |
Run 8x24 | Number processes: 8OMP_NUM_THREADS: 24OMP_PROC_BIND: spreadI_MPI_PIN_DOMAIN: auto:scatterOMP_PLACES: threads |
(8x1) Efficiency | (8x1) Potential Speed-Up (%) | (8x2) Efficiency | (8x2) Potential Speed-Up (%) | (8x4) Efficiency | (8x4) Potential Speed-Up (%) | (8x8) Efficiency | (8x8) Potential Speed-Up (%) | (8x16) Efficiency | (8x16) Potential Speed-Up (%) | (8x24) Efficiency | (8x24) Potential Speed-Up (%) |
---|---|---|---|---|---|---|---|---|---|---|---|
1 | 0 | 1.94 | 0 | 4.19 | 0 | 6.45 | 0 | 12.44 | 0 | 16.93 | 0 |
Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
---|---|---|---|---|---|---|
8x1 | 8 | 1 | 1 | 1 | 0.15999998152256 | 0.038184456527233 |
8x2 | 16 | 1.94 | 1.94 | 2 | 0.099999979138374 | 0.038664542138577 |
8x4 | 32 | 4.19 | 4.19 | 4 | 0.049999989569187 | 0.025303054600954 |
8x8 | 61 | 6.45 | 6.45 | 8 | 0.059999983757734 | 0.022553943097591 |
8x16 | 107 | 12.44 | 12.44 | 16 | 0.025000000372529 | 0.012690607458353 |
8x24 | 142 | 16.93 | 16.93 | 24 | 0.029999997466803 | 0.010219923220575 |