Loop Id: 1407 | Module: libparcsr_ls.so | Source: par_multi_interp.c:488-514 | Coverage: 0.01% |
---|
Loop Id: 1407 | Module: libparcsr_ls.so | Source: par_multi_interp.c:488-514 | Coverage: 0.01% |
---|
0x4dbf0 LEA -0x1(%RAX),%RCX |
0x4dbf4 CMP %RBX,%RAX |
0x4dbf7 MOV %RCX,%RAX |
0x4dbfa JLE 4dcf4 |
0x4dc00 MOV (%R8,%RAX,8),%RCX |
0x4dc04 MOV -0x1d0(%RBP),%RSI |
0x4dc0b MOV (%RSI,%RCX,8),%RDX |
0x4dc0f MOV 0x8(%RSI,%RCX,8),%RSI |
0x4dc14 JMP 4dc23 |
(1409) 0x4dc20 INC %RDX |
(1409) 0x4dc23 CMP %RSI,%RDX |
(1409) 0x4dc26 JGE 4dc60 |
(1409) 0x4dc28 MOV -0x228(%RBP),%RDI |
(1409) 0x4dc2f MOV (%RDI,%RDX,8),%RDI |
(1409) 0x4dc33 CMPQ $0x1,(%R14,%RDI,8) |
(1409) 0x4dc38 JNE 4dc20 |
(1409) 0x4dc3a INCQ 0x8(%R10,%RCX,8) |
(1409) 0x4dc3f INCQ -0x40(%RBP) |
(1409) 0x4dc43 MOVQ $0x1,(%R15,%RCX,8) |
(1409) 0x4dc4b MOV -0x1d0(%RBP),%RSI |
(1409) 0x4dc52 MOV 0x8(%RSI,%RCX,8),%RSI |
(1409) 0x4dc57 JMP 4dc20 |
0x4dc60 MOV -0x1c8(%RBP),%RSI |
0x4dc67 MOV (%RSI,%RCX,8),%RDX |
0x4dc6b MOV 0x8(%RSI,%RCX,8),%RSI |
0x4dc70 JMP 4dc83 |
(1408) 0x4dc80 INC %RDX |
(1408) 0x4dc83 CMP %RSI,%RDX |
(1408) 0x4dc86 JGE 4dcc0 |
(1408) 0x4dc88 MOV -0x1d8(%RBP),%RDI |
(1408) 0x4dc8f MOV (%RDI,%RDX,8),%RDI |
(1408) 0x4dc93 CMPQ $0x1,(%R9,%RDI,8) |
(1408) 0x4dc98 JNE 4dc80 |
(1408) 0x4dc9a MOV -0x60(%RBP),%RSI |
(1408) 0x4dc9e INCQ 0x8(%RSI,%RCX,8) |
(1408) 0x4dca3 INCQ -0x50(%RBP) |
(1408) 0x4dca7 MOVQ $0x1,(%R15,%RCX,8) |
(1408) 0x4dcaf MOV -0x1c8(%RBP),%RSI |
(1408) 0x4dcb6 MOV 0x8(%RSI,%RCX,8),%RSI |
(1408) 0x4dcbb JMP 4dc80 |
0x4dcc0 CMPQ $0x1,(%R15,%RCX,8) |
0x4dcc5 JNE 4dbf0 |
0x4dccb MOV (%R8,%RBX,8),%RDX |
0x4dccf MOV %RDX,(%R8,%RAX,8) |
0x4dcd3 INC %RAX |
0x4dcd6 MOV %RCX,(%R8,%RBX,8) |
0x4dcda INC %RBX |
0x4dcdd JMP 4dbf0 |
/scratch_na/users/xoserete/qaas_runs/171-587-0261/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.c:2965 | libparcsr_ls.so |
○ | hypre_PCGSetup | pcg.c:234 | libkrylov.so |
○ | main | amg.c:398 | exec |
○ | __libc_start_main | libc-2.28.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 | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.11 |
Bottlenecks | micro-operation queue, |
Function | hypre_BoomerAMGBuildMultipass |
Source | par_multi_interp.c:488-491,par_multi_interp.c:501-501,par_multi_interp.c:511-514 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.33 |
CQA cycles if no scalar integer | 3.33 |
CQA cycles if FP arith vectorized | 3.33 |
CQA cycles if fully vectorized | 0.42 |
Front-end cycles | 3.33 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 3.00 |
P2 cycles | 3.00 |
P3 cycles | 1.00 |
P4 cycles | 0.60 |
P5 cycles | 1.00 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 0.60 |
P10 cycles | 3.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.74 |
Stall cycles (UFS) | 3.26 |
Nb insns | 21.00 |
Nb uops | 20.00 |
Nb loads | 9.00 |
Nb stores | 2.00 |
Nb stack references | 2.00 |
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 | 26.40 |
Bytes prefetched | 0.00 |
Bytes loaded | 72.00 |
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 | 1.11 |
Bottlenecks | micro-operation queue, |
Function | hypre_BoomerAMGBuildMultipass |
Source | par_multi_interp.c:488-491,par_multi_interp.c:501-501,par_multi_interp.c:511-514 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.33 |
CQA cycles if no scalar integer | 3.33 |
CQA cycles if FP arith vectorized | 3.33 |
CQA cycles if fully vectorized | 0.42 |
Front-end cycles | 3.33 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 3.00 |
P2 cycles | 3.00 |
P3 cycles | 1.00 |
P4 cycles | 0.60 |
P5 cycles | 1.00 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 0.60 |
P10 cycles | 3.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 6.74 |
Stall cycles (UFS) | 3.26 |
Nb insns | 21.00 |
Nb uops | 20.00 |
Nb loads | 9.00 |
Nb stores | 2.00 |
Nb stack references | 2.00 |
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 | 26.40 |
Bytes prefetched | 0.00 |
Bytes loaded | 72.00 |
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 | libparcsr_ls.so |
nb instructions | 21 |
nb uops | 20 |
loop length | 90 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 3.33 cycles |
front end | 3.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.80 | 3.00 | 3.00 | 1.00 | 0.60 | 1.00 | 1.00 | 1.00 | 1.00 | 0.60 | 3.00 |
cycles | 1.00 | 0.80 | 3.00 | 3.00 | 1.00 | 0.60 | 1.00 | 1.00 | 1.00 | 1.00 | 0.60 | 3.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.74 |
Stall cycles | 3.26 |
LM full (events) | 4.61 |
Front-end | 3.33 |
Dispatch | 3.00 |
Overall L1 | 3.33 |
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 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LEA -0x1(%RAX),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP %RBX,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %RCX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JLE 4dcf4 <hypre_BoomerAMGBuildMultipass+0xe34> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV (%R8,%RAX,8),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x1d0(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%RCX,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RSI,%RCX,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 4dc23 <hypre_BoomerAMGBuildMultipass+0xd63> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
MOV -0x1c8(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%RCX,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RSI,%RCX,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 4dc83 <hypre_BoomerAMGBuildMultipass+0xdc3> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
CMPQ $0x1,(%R15,%RCX,8) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JNE 4dbf0 <hypre_BoomerAMGBuildMultipass+0xd30> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV (%R8,%RBX,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RDX,(%R8,%RAX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RCX,(%R8,%RBX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JMP 4dbf0 <hypre_BoomerAMGBuildMultipass+0xd30> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | hypre_BoomerAMGBuildMultipass |
Source file and lines | par_multi_interp.c:488-514 |
Module | libparcsr_ls.so |
nb instructions | 21 |
nb uops | 20 |
loop length | 90 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 3.33 cycles |
front end | 3.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.80 | 3.00 | 3.00 | 1.00 | 0.60 | 1.00 | 1.00 | 1.00 | 1.00 | 0.60 | 3.00 |
cycles | 1.00 | 0.80 | 3.00 | 3.00 | 1.00 | 0.60 | 1.00 | 1.00 | 1.00 | 1.00 | 0.60 | 3.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 6.74 |
Stall cycles | 3.26 |
LM full (events) | 4.61 |
Front-end | 3.33 |
Dispatch | 3.00 |
Overall L1 | 3.33 |
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 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LEA -0x1(%RAX),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP %RBX,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %RCX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JLE 4dcf4 <hypre_BoomerAMGBuildMultipass+0xe34> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV (%R8,%RAX,8),%RCX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV -0x1d0(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%RCX,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RSI,%RCX,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 4dc23 <hypre_BoomerAMGBuildMultipass+0xd63> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
MOV -0x1c8(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%RCX,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RSI,%RCX,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 4dc83 <hypre_BoomerAMGBuildMultipass+0xdc3> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
CMPQ $0x1,(%R15,%RCX,8) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JNE 4dbf0 <hypre_BoomerAMGBuildMultipass+0xd30> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV (%R8,%RBX,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RDX,(%R8,%RAX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RCX,(%R8,%RBX,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JMP 4dbf0 <hypre_BoomerAMGBuildMultipass+0xd30> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |