Loop Id: 2384 | Module: exec | Source: par_strength.c:1731-1765 | Coverage: 0.28% |
---|
Loop Id: 2384 | Module: exec | Source: par_strength.c:1731-1765 | Coverage: 0.28% |
---|
0x498000 INC %R10 |
0x498003 MOV -0x58(%RBP),%RAX |
0x498007 MOV -0x40(%RBP),%RCX |
0x49800b CMP 0x8(%RAX,%RCX,8),%R10 |
0x498010 JGE 498140 |
0x498016 MOV -0x88(%RBP),%RAX |
0x49801d MOV (%RAX,%R10,8),%RSI |
0x498021 MOV -0x68(%RBP),%RAX |
0x498025 CMPQ $0,(%RAX,%RSI,8) |
0x49802a JLE 498045 |
0x49802c MOV 0x78(%RBP),%RAX |
0x498030 MOV (%RAX,%RSI,8),%RAX |
0x498034 CMP %R13,(%R14,%RAX,8) |
0x498038 JGE 498045 |
0x49803a MOV %R9,(%R14,%RAX,8) |
0x49803e INC %R9 |
0x498041 MOV %R9,-0x30(%RBP) |
0x498045 MOV -0x58(%RBP),%RAX |
0x498049 MOV (%RAX,%RSI,8),%RBX |
0x49804d MOV 0x8(%RAX,%RSI,8),%RAX |
0x498052 JMP 498063 |
(2386) 0x498060 INC %RBX |
(2386) 0x498063 CMP %RAX,%RBX |
(2386) 0x498066 JGE 4980c0 |
(2386) 0x498068 MOV -0x88(%RBP),%RCX |
(2386) 0x49806f MOV (%RCX,%RBX,8),%RCX |
(2386) 0x498073 MOV -0x68(%RBP),%RDX |
(2386) 0x498077 CMPQ $0,(%RDX,%RCX,8) |
(2386) 0x49807c JLE 498060 |
(2386) 0x49807e MOV 0x78(%RBP),%RDX |
(2386) 0x498082 MOV (%RDX,%RCX,8),%R8 |
(2386) 0x498086 CMP %R11,%R8 |
(2386) 0x498089 JE 498060 |
(2386) 0x49808b CMP %R13,(%R14,%R8,8) |
(2386) 0x49808f JGE 498060 |
(2386) 0x498091 MOV %R9,(%R14,%R8,8) |
(2386) 0x498095 INC %R9 |
(2386) 0x498098 MOV %R9,-0x30(%RBP) |
(2386) 0x49809c MOV -0x58(%RBP),%RAX |
(2386) 0x4980a0 MOV 0x8(%RAX,%RSI,8),%RAX |
(2386) 0x4980a5 JMP 498060 |
0x4980c0 MOV 0x10(%RBP),%RCX |
0x4980c4 MOV (%RCX,%RSI,8),%RAX |
0x4980c8 MOV 0x8(%RCX,%RSI,8),%RBX |
0x4980cd JMP 4980e3 |
(2385) 0x4980e0 INC %RAX |
(2385) 0x4980e3 CMP %RBX,%RAX |
(2385) 0x4980e6 JGE 498000 |
(2385) 0x4980ec MOV 0x18(%RBP),%RCX |
(2385) 0x4980f0 MOV (%RCX,%RAX,8),%RCX |
(2385) 0x4980f4 MOV 0x70(%RBP),%RDX |
(2385) 0x4980f8 CMPQ $0,(%RDX,%RCX,8) |
(2385) 0x4980fd JLE 4980e0 |
(2385) 0x4980ff MOV 0x80(%RBP),%RDX |
(2385) 0x498106 MOV (%RDX,%RCX,8),%RCX |
(2385) 0x49810a CMP %R15,(%R12,%RCX,8) |
(2385) 0x49810e JGE 4980e0 |
(2385) 0x498110 MOV %RDI,(%R12,%RCX,8) |
(2385) 0x498114 INC %RDI |
(2385) 0x498117 MOV %RDI,-0x38(%RBP) |
(2385) 0x49811b MOV 0x10(%RBP),%RCX |
(2385) 0x49811f MOV 0x8(%RCX,%RSI,8),%RBX |
(2385) 0x498124 JMP 4980e0 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c: 1731 - 1765 |
-------------------------------------------------------------------------------- |
1731: for (jj1 = S_diag_i[i1]; jj1 < S_diag_i[i1+1]; jj1++) |
1732: { |
1733: i2 = S_diag_j[jj1]; |
1734: if (CF_marker[i2] > 0) |
1735: { |
1736: index = fine_to_coarse[i2]; |
1737: if (S_marker[index] < jj_row_begin_diag) |
1738: { |
1739: S_marker[index] = num_nonzeros_diag; |
1740: num_nonzeros_diag++; |
1741: } |
1742: } |
1743: for (jj2 = S_diag_i[i2]; jj2 < S_diag_i[i2+1]; jj2++) |
1744: { |
1745: i3 = S_diag_j[jj2]; |
1746: if (CF_marker[i3] > 0) |
1747: { |
1748: index = fine_to_coarse[i3]; |
1749: if (index != ic && S_marker[index] < jj_row_begin_diag) |
1750: { |
1751: S_marker[index] = num_nonzeros_diag; |
1752: num_nonzeros_diag++; |
1753: } |
1754: } |
1755: } |
1756: for (jj2 = S_offd_i[i2]; jj2 < S_offd_i[i2+1]; jj2++) |
1757: { |
1758: i3 = S_offd_j[jj2]; |
1759: if (CF_marker_offd[i3] > 0) |
1760: { |
1761: index = map_S_to_C[i3]; |
1762: if (S_marker_offd[index] < jj_row_begin_offd) |
1763: { |
1764: S_marker_offd[index] = num_nonzeros_offd; |
1765: 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 | par_strength.c:1668 | exec |
○ | hypre_BoomerAMGSetup | par_amg_setup.c:617 | 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 | 1.19 |
Bottlenecks | P2, P3, |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source | par_strength.c:1731-1765 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 8.00 |
CQA cycles if no scalar integer | 8.00 |
CQA cycles if FP arith vectorized | 8.00 |
CQA cycles if fully vectorized | 1.00 |
Front-end cycles | 6.75 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 2.50 |
P1 cycles | 8.00 |
P2 cycles | 8.00 |
P3 cycles | 2.00 |
P4 cycles | 2.50 |
P5 cycles | 2.50 |
P6 cycles | 2.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 8.44 |
Stall cycles (UFS) | 1.48 |
Nb insns | 25.00 |
Nb uops | 25.00 |
Nb loads | 16.00 |
Nb stores | 2.00 |
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 | 18.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
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 | 1.19 |
Bottlenecks | P2, P3, |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source | par_strength.c:1731-1765 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 8.00 |
CQA cycles if no scalar integer | 8.00 |
CQA cycles if FP arith vectorized | 8.00 |
CQA cycles if fully vectorized | 1.00 |
Front-end cycles | 6.75 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 2.50 |
P1 cycles | 8.00 |
P2 cycles | 8.00 |
P3 cycles | 2.00 |
P4 cycles | 2.50 |
P5 cycles | 2.50 |
P6 cycles | 2.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 8.44 |
Stall cycles (UFS) | 1.48 |
Nb insns | 25.00 |
Nb uops | 25.00 |
Nb loads | 16.00 |
Nb stores | 2.00 |
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 | 18.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
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_BoomerAMGCreate2ndS.extracted.17 |
Source file and lines | par_strength.c:1731-1765 |
Module | exec |
nb instructions | 25 |
nb uops | 25 |
loop length | 99 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 6.75 cycles |
front end | 6.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.50 | 2.50 | 8.00 | 8.00 | 2.00 | 2.50 | 2.50 | 2.00 |
cycles | 2.50 | 2.50 | 8.00 | 8.00 | 2.00 | 2.50 | 2.50 | 2.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 8.44 |
Stall cycles | 1.48 |
LM full (events) | 3.58 |
Front-end | 6.75 |
Dispatch | 8.00 |
Overall L1 | 8.00 |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP 0x8(%RAX,%RCX,8),%R10 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 498140 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x88(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R10,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMPQ $0,(%RAX,%RSI,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 498045 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x78(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RSI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R13,(%R14,%RAX,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 498045 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R9,(%R14,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R9,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RSI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RSI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 498063 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV 0x10(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RSI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RSI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4980e3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source file and lines | par_strength.c:1731-1765 |
Module | exec |
nb instructions | 25 |
nb uops | 25 |
loop length | 99 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 7 |
micro-operation queue | 6.75 cycles |
front end | 6.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.50 | 2.50 | 8.00 | 8.00 | 2.00 | 2.50 | 2.50 | 2.00 |
cycles | 2.50 | 2.50 | 8.00 | 8.00 | 2.00 | 2.50 | 2.50 | 2.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 8.44 |
Stall cycles | 1.48 |
LM full (events) | 3.58 |
Front-end | 6.75 |
Dispatch | 8.00 |
Overall L1 | 8.00 |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|
INC %R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP 0x8(%RAX,%RCX,8),%R10 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 498140 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x88(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R10,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x68(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMPQ $0,(%RAX,%RSI,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 498045 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x78(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RSI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %R13,(%R14,%RAX,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JGE 498045 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R9,(%R14,%RAX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R9,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%RSI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX,%RSI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 498063 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV 0x10(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%RSI,8),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RCX,%RSI,8),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 4980e3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |