Loop Id: 796 | Module: exec | Source: par_multi_interp.c:488-514 | Coverage: 0.04% |
---|
Loop Id: 796 | Module: exec | Source: par_multi_interp.c:488-514 | Coverage: 0.04% |
---|
0x441c00 CMP %R12,%R9 |
0x441c03 LEA -0x1(%R9),%R9 |
0x441c07 JLE 441d49 |
0x441c0d MOV -0x130(%RBP),%RCX |
0x441c14 MOV (%RCX,%R9,8),%RCX |
0x441c18 MOV -0x1a0(%RBP),%RSI |
0x441c1f MOV (%RSI,%RCX,8),%RDX |
0x441c23 MOV 0x8(%RSI,%RCX,8),%RSI |
0x441c28 JMP 441c43 |
(798) 0x441c40 INC %RDX |
(798) 0x441c43 CMP %RSI,%RDX |
(798) 0x441c46 JGE 441ca0 |
(798) 0x441c48 MOV -0x1e0(%RBP),%RDI |
(798) 0x441c4f MOV (%RDI,%RDX,8),%RDI |
(798) 0x441c53 CMPQ $0x1,(%R10,%RDI,8) |
(798) 0x441c58 JNE 441c40 |
(798) 0x441c5a MOV -0xa8(%RBP),%RSI |
(798) 0x441c61 INCQ 0x8(%RSI,%RCX,8) |
(798) 0x441c66 INC %R14 |
(798) 0x441c69 MOV -0x30(%RBP),%RSI |
(798) 0x441c6d MOVQ $0x1,(%RSI,%RCX,8) |
(798) 0x441c75 MOV -0x1a0(%RBP),%RSI |
(798) 0x441c7c MOV 0x8(%RSI,%RCX,8),%RSI |
(798) 0x441c81 JMP 441c40 |
0x441ca0 MOV -0x198(%RBP),%RSI |
0x441ca7 MOV (%RSI,%RCX,8),%RDX |
0x441cab MOV 0x8(%RSI,%RCX,8),%RSI |
0x441cb0 JMP 441cc3 |
(797) 0x441cc0 INC %RDX |
(797) 0x441cc3 CMP %RSI,%RDX |
(797) 0x441cc6 JGE 441d00 |
(797) 0x441cc8 MOV (%RAX,%RDX,8),%RDI |
(797) 0x441ccc CMPQ $0x1,(%RBX,%RDI,8) |
(797) 0x441cd1 JNE 441cc0 |
(797) 0x441cd3 INCQ 0x8(%R8,%RCX,8) |
(797) 0x441cd8 INC %R15 |
(797) 0x441cdb MOV -0x30(%RBP),%RSI |
(797) 0x441cdf MOVQ $0x1,(%RSI,%RCX,8) |
(797) 0x441ce7 MOV -0x198(%RBP),%RSI |
(797) 0x441cee MOV 0x8(%RSI,%RCX,8),%RSI |
(797) 0x441cf3 JMP 441cc0 |
0x441d00 MOV -0x30(%RBP),%RDX |
0x441d04 CMPQ $0x1,(%RDX,%RCX,8) |
0x441d09 JNE 441c00 |
0x441d0f MOV -0x130(%RBP),%RSI |
0x441d16 MOV (%RSI,%R12,8),%RDX |
0x441d1a MOV %RDX,(%RSI,%R9,8) |
0x441d1e INC %R9 |
0x441d21 MOV %RCX,(%RSI,%R12,8) |
0x441d25 INC %R12 |
0x441d28 JMP 441c00 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_multi_interp.c: 488 - 514 |
-------------------------------------------------------------------------------- |
488: for (i = pass_array_size-1; i > cnt-1; i--) |
489: { |
490: i1 = pass_array[i]; |
491: for (j=S_diag_i[i1]; j < S_diag_i[i1+1]; j++) |
492: { |
493: j1 = S_diag_j[j]; |
494: if (CF_marker[j1] == 1) |
495: { |
496: P_diag_i[i1+1]++; |
497: cnt_nz++; |
498: assigned[i1] = 1; |
499: } |
500: } |
501: for (j=S_offd_i[i1]; j < S_offd_i[i1+1]; j++) |
502: { |
503: j1 = S_offd_j[j]; |
504: if (CF_marker_offd[j1] == 1) |
505: { |
506: P_offd_i[i1+1]++; |
507: cnt_nz_offd++; |
508: assigned[i1] = 1; |
509: } |
510: } |
511: if (assigned[i1] == 1) |
512: { |
513: pass_array[i++] = pass_array[cnt]; |
514: pass_array[cnt++] = i1; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | hypre_BoomerAMGSetup | par_amg_setup.c:737 | 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 | 1.09 |
Bottlenecks | P2, P3, |
Function | hypre_BoomerAMGBuildMultipass |
Source | par_multi_interp.c:488-514 |
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 | 5.50 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 2.00 |
P1 cycles | 6.00 |
P2 cycles | 6.00 |
P3 cycles | 2.00 |
P4 cycles | 2.00 |
P5 cycles | 3.00 |
P6 cycles | 2.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.69 |
Stall cycles (UFS) | 0.98 |
Nb insns | 23.00 |
Nb uops | 22.00 |
Nb loads | 12.00 |
Nb stores | 2.00 |
Nb stack references | 4.00 |
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 | 1.09 |
Bottlenecks | P2, P3, |
Function | hypre_BoomerAMGBuildMultipass |
Source | par_multi_interp.c:488-514 |
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 | 5.50 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 2.00 |
P1 cycles | 6.00 |
P2 cycles | 6.00 |
P3 cycles | 2.00 |
P4 cycles | 2.00 |
P5 cycles | 3.00 |
P6 cycles | 2.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.69 |
Stall cycles (UFS) | 0.98 |
Nb insns | 23.00 |
Nb uops | 22.00 |
Nb loads | 12.00 |
Nb stores | 2.00 |
Nb stack references | 4.00 |
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_BoomerAMGBuildMultipass |
Source file and lines | par_multi_interp.c:488-514 |
Module | exec |
nb instructions | 23 |
nb uops | 22 |
loop length | 105 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 4 |
micro-operation queue | 5.50 cycles |
front end | 5.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.00 | 6.00 | 6.00 | 2.00 | 2.00 | 3.00 | 2.00 |
cycles | 2.00 | 2.00 | 6.00 | 6.00 | 2.00 | 2.00 | 3.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.69 |
Stall cycles | 0.98 |
LM full (events) | 2.80 |
Front-end | 5.50 |
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 %R12,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0x1(%R9),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JLE 441d49 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x130(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%R9,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x1a0(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RSI,%RCX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 441c43 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x198(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RSI,%RCX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 441cc3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMPQ $0x1,(%RDX,%RCX,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 441c00 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x130(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI,%R12,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,(%RSI,%R9,8) | 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 %RCX,(%RSI,%R12,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 441c00 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
Function | hypre_BoomerAMGBuildMultipass |
Source file and lines | par_multi_interp.c:488-514 |
Module | exec |
nb instructions | 23 |
nb uops | 22 |
loop length | 105 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 4 |
micro-operation queue | 5.50 cycles |
front end | 5.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.00 | 6.00 | 6.00 | 2.00 | 2.00 | 3.00 | 2.00 |
cycles | 2.00 | 2.00 | 6.00 | 6.00 | 2.00 | 2.00 | 3.00 | 2.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.69 |
Stall cycles | 0.98 |
LM full (events) | 2.80 |
Front-end | 5.50 |
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 %R12,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0x1(%R9),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JLE 441d49 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x130(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX,%R9,8),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x1a0(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RSI,%RCX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 441c43 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x198(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI,%RCX,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RSI,%RCX,8),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 441cc3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMPQ $0x1,(%RDX,%RCX,8) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JNE 441c00 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x130(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI,%R12,8),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,(%RSI,%R9,8) | 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 %RCX,(%RSI,%R12,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
INC %R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 441c00 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |