Loop Id: 2509 | Module: exec | Source: par_strength.c:2000-2083 [...] | Coverage: 0.01% |
---|
Loop Id: 2509 | Module: exec | Source: par_strength.c:2000-2083 [...] | Coverage: 0.01% |
---|
0x490090 INC %RBX |
0x490093 CMP -0x80(%RBP),%RBX |
0x490097 JE 4909ab |
0x49009d MOV 0xa0(%RBP),%RAX |
0x4900a4 MOV (%RAX,%RBX,8),%RAX |
0x4900a8 MOV -0x30(%RBP),%RCX |
0x4900ac MOV -0x38(%RBP),%RDX |
0x4900b0 MOV -0x58(%RBP),%RDI |
0x4900b4 MOV (%RDI,%RAX,8),%RSI |
0x4900b8 CMP 0x8(%RDI,%RAX,8),%RSI |
0x4900bd MOV 0x40(%RBP),%R12 |
0x4900c1 JL 4901f2 |
0x4900c7 MOV 0x10(%RBP),%RDI |
0x4900cb MOV (%RDI,%RAX,8),%RSI |
0x4900cf JMP 4900e7 |
(2510) 0x4900e0 INC %RSI |
(2510) 0x4900e3 MOV 0x10(%RBP),%RDI |
(2510) 0x4900e7 CMP 0x8(%RDI,%RAX,8),%RSI |
(2510) 0x4900ec JGE 490090 |
(2510) 0x4900ee MOV 0x18(%RBP),%RDI |
(2510) 0x4900f2 MOV (%RDI,%RSI,8),%RDI |
(2510) 0x4900f6 MOV 0x70(%RBP),%R8 |
(2510) 0x4900fa CMPQ $0,(%R8,%RDI,8) |
(2510) 0x4900ff JLE 490126 |
(2510) 0x490101 MOV 0x80(%RBP),%R8 |
(2510) 0x490108 MOV (%R8,%RDI,8),%R8 |
(2510) 0x49010c CMP %RDX,(%R14,%R8,8) |
(2510) 0x490110 JGE 490126 |
(2510) 0x490112 MOV -0x38(%RBP),%R9 |
(2510) 0x490116 MOV %R9,(%R14,%R8,8) |
(2510) 0x49011a MOV (%R12),%R10 |
(2510) 0x49011e MOV %R8,(%R10,%R9,8) |
(2510) 0x490122 INCQ -0x38(%RBP) |
(2510) 0x490126 MOV 0x50(%RBP),%R9 |
(2510) 0x49012a MOV (%R9,%RDI,8),%R8 |
(2510) 0x49012e MOV 0x8(%R9,%RDI,8),%R9 |
(2510) 0x490133 JMP 490143 |
(2512) 0x490140 INC %R8 |
(2512) 0x490143 CMP %R9,%R8 |
(2512) 0x490146 JGE 490190 |
(2512) 0x490148 MOV 0x58(%RBP),%R10 |
(2512) 0x49014c MOV (%R10,%R8,8),%R10 |
(2512) 0x490150 CMP %RBX,%R10 |
(2512) 0x490153 JE 490140 |
(2512) 0x490155 MOV -0x48(%RBP),%R11 |
(2512) 0x490159 CMP %RCX,(%R11,%R10,8) |
(2512) 0x49015d JGE 490140 |
(2512) 0x49015f MOV -0x30(%RBP),%R9 |
(2512) 0x490163 MOV -0x48(%RBP),%R11 |
(2512) 0x490167 MOV %R9,(%R11,%R10,8) |
(2512) 0x49016b MOV 0x30(%RBP),%R11 |
(2512) 0x49016f MOV (%R11),%R11 |
(2512) 0x490172 MOV %R10,(%R11,%R9,8) |
(2512) 0x490176 INCQ -0x30(%RBP) |
(2512) 0x49017a MOV 0x50(%RBP),%R9 |
(2512) 0x49017e MOV 0x8(%R9,%RDI,8),%R9 |
(2512) 0x490183 JMP 490140 |
(2510) 0x490190 MOV 0x60(%RBP),%R9 |
(2510) 0x490194 MOV (%R9,%RDI,8),%R8 |
(2510) 0x490198 MOV 0x8(%R9,%RDI,8),%R9 |
(2510) 0x49019d JMP 4901a3 |
(2511) 0x4901a0 INC %R8 |
(2511) 0x4901a3 CMP %R9,%R8 |
(2511) 0x4901a6 JGE 4900e0 |
(2511) 0x4901ac MOV 0x68(%RBP),%R10 |
(2511) 0x4901b0 MOV (%R10,%R8,8),%R10 |
(2511) 0x4901b4 CMP %RDX,(%R14,%R10,8) |
(2511) 0x4901b8 JGE 4901a0 |
(2511) 0x4901ba MOV -0x38(%RBP),%R9 |
(2511) 0x4901be MOV %R9,(%R14,%R10,8) |
(2511) 0x4901c2 MOV (%R12),%R11 |
(2511) 0x4901c6 MOV %R10,(%R11,%R9,8) |
(2511) 0x4901ca INCQ -0x38(%RBP) |
(2511) 0x4901ce MOV 0x60(%RBP),%R9 |
(2511) 0x4901d2 MOV 0x8(%R9,%RDI,8),%R9 |
(2511) 0x4901d7 JMP 4901a0 |
(2513) 0x4901e0 INC %RSI |
(2513) 0x4901e3 MOV -0x58(%RBP),%RDI |
(2513) 0x4901e7 CMP 0x8(%RDI,%RAX,8),%RSI |
(2513) 0x4901ec JGE 4900c7 |
(2513) 0x4901f2 MOV (%R15,%RSI,8),%RDI |
(2513) 0x4901f6 CMPQ $0,(%R13,%RDI,8) |
(2513) 0x4901fc JLE 49022b |
(2513) 0x4901fe MOV 0x78(%RBP),%R8 |
(2513) 0x490202 MOV (%R8,%RDI,8),%R8 |
(2513) 0x490206 MOV -0x48(%RBP),%R9 |
(2513) 0x49020a CMP %RCX,(%R9,%R8,8) |
(2513) 0x49020e JGE 49022b |
(2513) 0x490210 MOV -0x30(%RBP),%R9 |
(2513) 0x490214 MOV -0x48(%RBP),%R10 |
(2513) 0x490218 MOV %R9,(%R10,%R8,8) |
(2513) 0x49021c MOV 0x30(%RBP),%R10 |
(2513) 0x490220 MOV (%R10),%R10 |
(2513) 0x490223 MOV %R8,(%R10,%R9,8) |
(2513) 0x490227 INCQ -0x30(%RBP) |
(2513) 0x49022b MOV -0x58(%RBP),%R9 |
(2513) 0x49022f MOV (%R9,%RDI,8),%R8 |
(2513) 0x490233 MOV 0x8(%R9,%RDI,8),%R9 |
(2513) 0x490238 JMP 490243 |
(2515) 0x490240 INC %R8 |
(2515) 0x490243 CMP %R9,%R8 |
(2515) 0x490246 JGE 4902a0 |
(2515) 0x490248 MOV (%R15,%R8,8),%R10 |
(2515) 0x49024c CMPQ $0,(%R13,%R10,8) |
(2515) 0x490252 JLE 490240 |
(2515) 0x490254 MOV 0x78(%RBP),%R11 |
(2515) 0x490258 MOV (%R11,%R10,8),%R10 |
(2515) 0x49025c CMP %RBX,%R10 |
(2515) 0x49025f JE 490240 |
(2515) 0x490261 MOV -0x48(%RBP),%R11 |
(2515) 0x490265 CMP %RCX,(%R11,%R10,8) |
(2515) 0x490269 JGE 490240 |
(2515) 0x49026b MOV -0x30(%RBP),%R9 |
(2515) 0x49026f MOV -0x48(%RBP),%R11 |
(2515) 0x490273 MOV %R9,(%R11,%R10,8) |
(2515) 0x490277 MOV 0x30(%RBP),%R11 |
(2515) 0x49027b MOV (%R11),%R11 |
(2515) 0x49027e MOV %R10,(%R11,%R9,8) |
(2515) 0x490282 INCQ -0x30(%RBP) |
(2515) 0x490286 MOV -0x58(%RBP),%R9 |
(2515) 0x49028a MOV 0x8(%R9,%RDI,8),%R9 |
(2515) 0x49028f JMP 490240 |
(2513) 0x4902a0 MOV 0x10(%RBP),%R9 |
(2513) 0x4902a4 MOV (%R9,%RDI,8),%R8 |
(2513) 0x4902a8 MOV 0x8(%R9,%RDI,8),%R9 |
(2513) 0x4902ad JMP 4902b3 |
(2514) 0x4902b0 INC %R8 |
(2514) 0x4902b3 CMP %R9,%R8 |
(2514) 0x4902b6 JGE 4901e0 |
(2514) 0x4902bc MOV 0x18(%RBP),%R10 |
(2514) 0x4902c0 MOV (%R10,%R8,8),%R10 |
(2514) 0x4902c4 MOV 0x70(%RBP),%R11 |
(2514) 0x4902c8 CMPQ $0,(%R11,%R10,8) |
(2514) 0x4902cd JLE 4902b0 |
(2514) 0x4902cf MOV 0x80(%RBP),%R11 |
(2514) 0x4902d6 MOV (%R11,%R10,8),%R10 |
(2514) 0x4902da CMP %RDX,(%R14,%R10,8) |
(2514) 0x4902de JGE 4902b0 |
(2514) 0x4902e0 MOV -0x38(%RBP),%R9 |
(2514) 0x4902e4 MOV %R9,(%R14,%R10,8) |
(2514) 0x4902e8 MOV (%R12),%R11 |
(2514) 0x4902ec MOV %R10,(%R11,%R9,8) |
(2514) 0x4902f0 INCQ -0x38(%RBP) |
(2514) 0x4902f4 MOV 0x10(%RBP),%R9 |
(2514) 0x4902f8 MOV 0x8(%R9,%RDI,8),%R9 |
(2514) 0x4902fd JMP 4902b0 |
/home/eoseret/qaas_runs_CPU_9468/171-147-2675/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++; |
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 | 1.37 |
Bottlenecks | P2, P3, P11, |
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 | 0.46 |
Front-end cycles | 2.67 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 3.67 |
P2 cycles | 3.67 |
P3 cycles | 0.00 |
P4 cycles | 0.60 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.60 |
P10 cycles | 3.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 4.24 |
Stall cycles (UFS) | 1.46 |
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 | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.37 |
Bottlenecks | P2, P3, P11, |
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 | 0.46 |
Front-end cycles | 2.67 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 3.67 |
P2 cycles | 3.67 |
P3 cycles | 0.00 |
P4 cycles | 0.60 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.60 |
P10 cycles | 3.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 4.24 |
Stall cycles (UFS) | 1.46 |
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 | exec |
nb instructions | 15 |
nb uops | 15 |
loop length | 65 |
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 | 2.67 cycles |
front end | 2.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.80 | 3.67 | 3.67 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 3.67 |
cycles | 1.00 | 0.80 | 3.67 | 3.67 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 3.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 4.24 |
Stall cycles | 1.46 |
LM full (events) | 3.36 |
Front-end | 2.67 |
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 | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP -0x80(%RBP),%RBX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JE 4909ab <hypre_BoomerAMGCreate2ndS.extracted.17+0x195b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0xa0(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX,%RBX,8),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x38(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x58(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI,%RAX,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%RDI,%RAX,8),%RSI | 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 0x40(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JL 4901f2 <hypre_BoomerAMGCreate2ndS.extracted.17+0x11a2> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
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,%RAX,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 4900e7 <hypre_BoomerAMGCreate2ndS.extracted.17+0x1097> | 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:2000-2083 |
Module | exec |
nb instructions | 15 |
nb uops | 15 |
loop length | 65 |
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 | 2.67 cycles |
front end | 2.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.80 | 3.67 | 3.67 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 3.67 |
cycles | 1.00 | 0.80 | 3.67 | 3.67 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 3.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 4.24 |
Stall cycles | 1.46 |
LM full (events) | 3.36 |
Front-end | 2.67 |
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 | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP -0x80(%RBP),%RBX | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JE 4909ab <hypre_BoomerAMGCreate2ndS.extracted.17+0x195b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0xa0(%RBP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RAX,%RBX,8),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x30(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x38(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x58(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI,%RAX,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%RDI,%RAX,8),%RSI | 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 0x40(%RBP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JL 4901f2 <hypre_BoomerAMGCreate2ndS.extracted.17+0x11a2> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
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,%RAX,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 4900e7 <hypre_BoomerAMGCreate2ndS.extracted.17+0x1097> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |