Loop Id: 2975 | Module: libparcsr_ls.so | Source: par_strength.c:1998-2083 [...] | Coverage: 0.01% |
---|
Loop Id: 2975 | Module: libparcsr_ls.so | Source: par_strength.c:1998-2083 [...] | Coverage: 0.01% |
---|
0x99b70 MOV %RAX,%RSI |
0x99b73 INC %RSI |
0x99b76 CMP -0x98(%RBP),%RSI |
0x99b7d JE 9a441 |
0x99b83 MOV 0xa0(%RBP),%RDX |
0x99b8a MOV %RSI,%RAX |
0x99b8d MOV (%RDX,%RSI,8),%RDX |
0x99b91 MOV -0x30(%RBP),%RSI |
0x99b95 MOV -0x38(%RBP),%RDI |
0x99b99 MOV -0x48(%RBP),%RCX |
0x99b9d MOV (%RCX,%RDX,8),%R8 |
0x99ba1 CMP 0x8(%RCX,%RDX,8),%R8 |
0x99ba6 MOV 0x40(%RBP),%RCX |
0x99baa JL 99bde |
0x99bac MOV -0x40(%RBP),%R9 |
0x99bb0 MOV (%R9,%RDX,8),%R8 |
0x99bb4 CMP 0x8(%R9,%RDX,8),%R8 |
0x99bb9 JGE 99b70 |
0x99bbb MOV 0x70(%RBP),%R9 |
0x99bbf MOV (%R9),%R9 |
0x99bc2 JMP 99d12 |
(2979) 0x99bd0 INC %R8 |
(2979) 0x99bd3 MOV -0x48(%RBP),%R9 |
(2979) 0x99bd7 CMP 0x8(%R9,%RDX,8),%R8 |
(2979) 0x99bdc JGE 99bac |
(2979) 0x99bde MOV -0xa0(%RBP),%R9 |
(2979) 0x99be5 MOV (%R9,%R8,8),%R9 |
(2979) 0x99be9 MOV -0x68(%RBP),%R10 |
(2979) 0x99bed CMPQ $0,(%R10,%R9,8) |
(2979) 0x99bf2 JLE 99c1c |
(2979) 0x99bf4 MOV 0x78(%RBP),%R10 |
(2979) 0x99bf8 MOV (%R10),%R10 |
(2979) 0x99bfb MOV (%R10,%R9,8),%R10 |
(2979) 0x99bff CMP %RSI,(%R15,%R10,8) |
(2979) 0x99c03 JGE 99c1c |
(2979) 0x99c05 MOV -0x30(%RBP),%R11 |
(2979) 0x99c09 MOV %R11,(%R15,%R10,8) |
(2979) 0x99c0d MOV 0x30(%RBP),%RBX |
(2979) 0x99c11 MOV (%RBX),%RBX |
(2979) 0x99c14 MOV %R10,(%RBX,%R11,8) |
(2979) 0x99c18 INCQ -0x30(%RBP) |
(2979) 0x99c1c MOV -0x48(%RBP),%R11 |
(2979) 0x99c20 MOV (%R11,%R9,8),%R10 |
(2979) 0x99c24 MOV 0x8(%R11,%R9,8),%R11 |
(2979) 0x99c29 JMP 99c33 |
(2981) 0x99c30 INC %R10 |
(2981) 0x99c33 CMP %R11,%R10 |
(2981) 0x99c36 JGE 99c90 |
(2981) 0x99c38 MOV -0xa0(%RBP),%RBX |
(2981) 0x99c3f MOV (%RBX,%R10,8),%RBX |
(2981) 0x99c43 MOV -0x68(%RBP),%R14 |
(2981) 0x99c47 CMPQ $0,(%R14,%RBX,8) |
(2981) 0x99c4c JLE 99c30 |
(2981) 0x99c4e MOV 0x78(%RBP),%R14 |
(2981) 0x99c52 MOV (%R14),%R14 |
(2981) 0x99c55 MOV (%R14,%RBX,8),%RBX |
(2981) 0x99c59 CMP %RAX,%RBX |
(2981) 0x99c5c JE 99c30 |
(2981) 0x99c5e CMP %RSI,(%R15,%RBX,8) |
(2981) 0x99c62 JGE 99c30 |
(2981) 0x99c64 MOV -0x30(%RBP),%R11 |
(2981) 0x99c68 MOV %R11,(%R15,%RBX,8) |
(2981) 0x99c6c MOV 0x30(%RBP),%R14 |
(2981) 0x99c70 MOV (%R14),%R14 |
(2981) 0x99c73 MOV %RBX,(%R14,%R11,8) |
(2981) 0x99c77 INCQ -0x30(%RBP) |
(2981) 0x99c7b MOV -0x48(%RBP),%R11 |
(2981) 0x99c7f MOV 0x8(%R11,%R9,8),%R11 |
(2981) 0x99c84 JMP 99c30 |
(2979) 0x99c90 MOV -0x40(%RBP),%R11 |
(2979) 0x99c94 MOV (%R11,%R9,8),%R10 |
(2979) 0x99c98 MOV 0x8(%R11,%R9,8),%RBX |
(2979) 0x99c9d CMP %RBX,%R10 |
(2979) 0x99ca0 JGE 99bd0 |
(2979) 0x99ca6 MOV 0x70(%RBP),%R11 |
(2979) 0x99caa MOV (%R11),%R11 |
(2979) 0x99cad JMP 99cbc |
(2980) 0x99cb0 INC %R10 |
(2980) 0x99cb3 CMP %RBX,%R10 |
(2980) 0x99cb6 JGE 99bd0 |
(2980) 0x99cbc MOV 0x18(%RBP),%R14 |
(2980) 0x99cc0 MOV (%R14,%R10,8),%R14 |
(2980) 0x99cc4 CMPQ $0,(%R11,%R14,8) |
(2980) 0x99cc9 JLE 99cb0 |
(2980) 0x99ccb MOV 0x80(%RBP),%R13 |
(2980) 0x99cd2 MOV (%R13,%R14,8),%R14 |
(2980) 0x99cd7 CMP %RDI,(%R12,%R14,8) |
(2980) 0x99cdb JGE 99cb0 |
(2980) 0x99cdd MOV -0x38(%RBP),%RBX |
(2980) 0x99ce1 MOV %RBX,(%R12,%R14,8) |
(2980) 0x99ce5 MOV (%RCX),%R13 |
(2980) 0x99ce8 MOV %R14,(%R13,%RBX,8) |
(2980) 0x99ced INCQ -0x38(%RBP) |
(2980) 0x99cf1 MOV -0x40(%RBP),%RBX |
(2980) 0x99cf5 MOV 0x8(%RBX,%R9,8),%RBX |
(2980) 0x99cfa JMP 99cb0 |
(2976) 0x99d00 INC %R8 |
(2976) 0x99d03 MOV -0x40(%RBP),%R10 |
(2976) 0x99d07 CMP 0x8(%R10,%RDX,8),%R8 |
(2976) 0x99d0c JGE 99b70 |
(2976) 0x99d12 MOV 0x18(%RBP),%R10 |
(2976) 0x99d16 MOV (%R10,%R8,8),%R10 |
(2976) 0x99d1a CMPQ $0,(%R9,%R10,8) |
(2976) 0x99d1f JLE 99d45 |
(2976) 0x99d21 MOV 0x80(%RBP),%R11 |
(2976) 0x99d28 MOV (%R11,%R10,8),%R11 |
(2976) 0x99d2c CMP %RDI,(%R12,%R11,8) |
(2976) 0x99d30 JGE 99d45 |
(2976) 0x99d32 MOV -0x38(%RBP),%RBX |
(2976) 0x99d36 MOV %RBX,(%R12,%R11,8) |
(2976) 0x99d3a MOV (%RCX),%R14 |
(2976) 0x99d3d MOV %R11,(%R14,%RBX,8) |
(2976) 0x99d41 INCQ -0x38(%RBP) |
(2976) 0x99d45 MOV 0x50(%RBP),%RBX |
(2976) 0x99d49 MOV (%RBX,%R10,8),%R11 |
(2976) 0x99d4d MOV 0x8(%RBX,%R10,8),%RBX |
(2976) 0x99d52 JMP 99d63 |
(2978) 0x99d60 INC %R11 |
(2978) 0x99d63 CMP %RBX,%R11 |
(2978) 0x99d66 JGE 99da0 |
(2978) 0x99d68 MOV 0x58(%RBP),%R14 |
(2978) 0x99d6c MOV (%R14,%R11,8),%R14 |
(2978) 0x99d70 CMP %RAX,%R14 |
(2978) 0x99d73 JE 99d60 |
(2978) 0x99d75 CMP %RSI,(%R15,%R14,8) |
(2978) 0x99d79 JGE 99d60 |
(2978) 0x99d7b MOV -0x30(%RBP),%RBX |
(2978) 0x99d7f MOV %RBX,(%R15,%R14,8) |
(2978) 0x99d83 MOV 0x30(%RBP),%R13 |
(2978) 0x99d87 MOV (%R13),%R13 |
(2978) 0x99d8b MOV %R14,(%R13,%RBX,8) |
(2978) 0x99d90 INCQ -0x30(%RBP) |
(2978) 0x99d94 MOV 0x50(%RBP),%RBX |
(2978) 0x99d98 MOV 0x8(%RBX,%R10,8),%RBX |
(2978) 0x99d9d JMP 99d60 |
(2976) 0x99da0 MOV 0x60(%RBP),%RBX |
(2976) 0x99da4 MOV (%RBX,%R10,8),%R11 |
(2976) 0x99da8 MOV 0x8(%RBX,%R10,8),%RBX |
(2976) 0x99dad JMP 99db3 |
(2977) 0x99db0 INC %R11 |
(2977) 0x99db3 CMP %RBX,%R11 |
(2977) 0x99db6 JGE 99d00 |
(2977) 0x99dbc MOV 0x68(%RBP),%R14 |
(2977) 0x99dc0 MOV (%R14,%R11,8),%R14 |
(2977) 0x99dc4 CMP %RDI,(%R12,%R14,8) |
(2977) 0x99dc8 JGE 99db0 |
(2977) 0x99dca MOV -0x38(%RBP),%RBX |
(2977) 0x99dce MOV %RBX,(%R12,%R14,8) |
(2977) 0x99dd2 MOV (%RCX),%R13 |
(2977) 0x99dd5 MOV %R14,(%R13,%RBX,8) |
(2977) 0x99dda INCQ -0x38(%RBP) |
(2977) 0x99dde MOV 0x60(%RBP),%RBX |
(2977) 0x99de2 MOV 0x8(%RBX,%R10,8),%RBX |
(2977) 0x99de7 JMP 99db0 |
/home/eoseret/qaas_runs_CPU_9468/171-147-2675/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c: 1998 - 2083 |
-------------------------------------------------------------------------------- |
1998: if (num_paths == 1) |
1999: { |
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 | 1.22 |
Bottlenecks | P2, P3, P11, |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source | par_strength.c:1998-2000,par_strength.c:2006-2011,par_strength.c:2053-2053,par_strength.c:2056-2056 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.67 |
CQA cycles if no scalar integer | 4.67 |
CQA cycles if FP arith vectorized | 4.67 |
CQA cycles if fully vectorized | 0.58 |
Front-end cycles | 3.83 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.00 |
P1 cycles | 4.67 |
P2 cycles | 4.67 |
P3 cycles | 0.00 |
P4 cycles | 1.00 |
P5 cycles | 1.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 1.00 |
P10 cycles | 4.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 5.63 |
Stall cycles (UFS) | 1.66 |
Nb insns | 21.00 |
Nb uops | 21.00 |
Nb loads | 14.00 |
Nb stores | 0.00 |
Nb stack references | 8.00 |
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 | 112.00 |
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 | 1.22 |
Bottlenecks | P2, P3, P11, |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source | par_strength.c:1998-2000,par_strength.c:2006-2011,par_strength.c:2053-2053,par_strength.c:2056-2056 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.67 |
CQA cycles if no scalar integer | 4.67 |
CQA cycles if FP arith vectorized | 4.67 |
CQA cycles if fully vectorized | 0.58 |
Front-end cycles | 3.83 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.00 |
P1 cycles | 4.67 |
P2 cycles | 4.67 |
P3 cycles | 0.00 |
P4 cycles | 1.00 |
P5 cycles | 1.50 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 1.00 |
P10 cycles | 4.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 5.63 |
Stall cycles (UFS) | 1.66 |
Nb insns | 21.00 |
Nb uops | 21.00 |
Nb loads | 14.00 |
Nb stores | 0.00 |
Nb stack references | 8.00 |
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 | 112.00 |
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:1998-2083 |
Module | libparcsr_ls.so |
nb instructions | 21 |
nb uops | 21 |
loop length | 87 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8 |
micro-operation queue | 3.83 cycles |
front end | 3.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.00 | 4.67 | 4.67 | 0.00 | 1.00 | 1.50 | 0.00 | 0.00 | 0.00 | 1.00 | 4.67 |
cycles | 1.50 | 1.00 | 4.67 | 4.67 | 0.00 | 1.00 | 1.50 | 0.00 | 0.00 | 0.00 | 1.00 | 4.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 5.63 |
Stall cycles | 1.66 |
LM full (events) | 4.33 |
Front-end | 3.83 |
Dispatch | 4.67 |
Overall L1 | 4.67 |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
INC %RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP -0x98(%RBP),%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 |
JE 9a441 <hypre_BoomerAMGCreate2ndS.extracted.17+0x16b1> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0xa0(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RSI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV (%RDX,%RSI,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x38(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x48(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RCX,%RDX,8),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%RCX,%RDX,8),%R8 | 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),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JL 99bde <hypre_BoomerAMGCreate2ndS.extracted.17+0xe4e> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x40(%RBP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R9,%RDX,8),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%R9,%RDX,8),%R8 | 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 99b70 <hypre_BoomerAMGCreate2ndS.extracted.17+0xde0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x70(%RBP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R9),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 99d12 <hypre_BoomerAMGCreate2ndS.extracted.17+0xf82> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source file and lines | par_strength.c:1998-2083 |
Module | libparcsr_ls.so |
nb instructions | 21 |
nb uops | 21 |
loop length | 87 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8 |
micro-operation queue | 3.83 cycles |
front end | 3.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.00 | 4.67 | 4.67 | 0.00 | 1.00 | 1.50 | 0.00 | 0.00 | 0.00 | 1.00 | 4.67 |
cycles | 1.50 | 1.00 | 4.67 | 4.67 | 0.00 | 1.00 | 1.50 | 0.00 | 0.00 | 0.00 | 1.00 | 4.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 5.63 |
Stall cycles | 1.66 |
LM full (events) | 4.33 |
Front-end | 3.83 |
Dispatch | 4.67 |
Overall L1 | 4.67 |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV %RAX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
INC %RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP -0x98(%RBP),%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 |
JE 9a441 <hypre_BoomerAMGCreate2ndS.extracted.17+0x16b1> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0xa0(%RBP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RSI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV (%RDX,%RSI,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x38(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x48(%RBP),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RCX,%RDX,8),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%RCX,%RDX,8),%R8 | 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),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JL 99bde <hypre_BoomerAMGCreate2ndS.extracted.17+0xe4e> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x40(%RBP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R9,%RDX,8),%R8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP 0x8(%R9,%RDX,8),%R8 | 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 99b70 <hypre_BoomerAMGCreate2ndS.extracted.17+0xde0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x70(%RBP),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%R9),%R9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 99d12 <hypre_BoomerAMGCreate2ndS.extracted.17+0xf82> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |