Loop Id: 2451 | Module: exec | Source: par_csr_matop.c:218-231 [...] | Coverage: 0.01% |
---|
Loop Id: 2451 | Module: exec | Source: par_csr_matop.c:218-231 [...] | Coverage: 0.01% |
---|
0x559330 MOV (%R14,%RAX,8),%RDX [1] |
0x559334 MOV 0xf0(%RSP),%R11 [5] |
0x55933c MOV 0xf8(%RSP),%R15 [5] |
0x559344 ADD (%R11,%RDX,8),%R15 [4] |
0x559348 LEA (%RDI,%R15,8),%RDX |
0x55934c CMP (%RDX),%R10 [2] |
0x55934f JLE 559370 |
0x559351 MOV %R8,(%RDX) [2] |
0x559354 INC %RAX |
0x559357 INC %R8 |
0x55935a MOV (%R13),%RSI [3] |
0x55935e CMP %RAX,%RSI |
0x559361 JG 559330 |
0x559370 INC %RAX |
0x559373 CMP %RAX,%RSI |
0x559376 JG 559330 |
/home/eoseret/qaas_runs_CPU_9468/171-147-2675/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 218 - 231 |
-------------------------------------------------------------------------------- |
218: for (jj3 = B_offd_i[i2]; jj3 < B_offd_i[i2+1]; jj3++) |
219: { |
220: i3 = num_cols_diag_B+map_B_to_C[B_offd_j[jj3]]; |
[...] |
228: if (B_marker[i3] < jj_row_begin_offd) |
229: { |
230: B_marker[i3] = jj_count_offd; |
231: jj_count_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 | 1.28 |
Bottlenecks | |
Function | hypre_ParMatmul_RowSizes._omp_fn.0 |
Source | par_csr_matop.c:218-220,par_csr_matop.c:228-231 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 1.92 |
CQA cycles if no scalar integer | 1.92 |
CQA cycles if FP arith vectorized | 1.92 |
CQA cycles if fully vectorized | 0.24 |
Front-end cycles | 1.92 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 1.83 |
P2 cycles | 1.83 |
P3 cycles | 0.25 |
P4 cycles | 0.60 |
P5 cycles | 1.00 |
P6 cycles | 0.25 |
P7 cycles | 0.25 |
P8 cycles | 0.25 |
P9 cycles | 0.60 |
P10 cycles | 1.83 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.08 |
Stall cycles (UFS) | 0.02 |
Nb insns | 11.50 |
Nb uops | 10.50 |
Nb loads | 5.50 |
Nb stores | 0.50 |
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 | 24.92 |
Bytes prefetched | 0.00 |
Bytes loaded | 44.00 |
Bytes stored | 4.00 |
Stride 0 | 1.50 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 2.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
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 | 12.50 |
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 | 1.08 |
Bottlenecks | micro-operation queue, |
Function | hypre_ParMatmul_RowSizes._omp_fn.0 |
Source | par_csr_matop.c:218-220,par_csr_matop.c:228-231 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 2.17 |
CQA cycles if no scalar integer | 2.17 |
CQA cycles if FP arith vectorized | 2.17 |
CQA cycles if fully vectorized | 0.27 |
Front-end cycles | 2.17 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 0.50 |
P4 cycles | 0.60 |
P5 cycles | 1.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 0.60 |
P10 cycles | 2.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.31 |
Stall cycles (UFS) | 0.00 |
Nb insns | 13.00 |
Nb uops | 12.00 |
Nb loads | 6.00 |
Nb stores | 1.00 |
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 | 25.85 |
Bytes prefetched | 0.00 |
Bytes loaded | 48.00 |
Bytes stored | 8.00 |
Stride 0 | 2.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 2.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
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 | 12.50 |
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 | 1.67 |
Bottlenecks | micro-operation queue, |
Function | hypre_ParMatmul_RowSizes._omp_fn.0 |
Source | par_csr_matop.c:218-220,par_csr_matop.c:228-231 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 1.67 |
CQA cycles if no scalar integer | 1.67 |
CQA cycles if FP arith vectorized | 1.67 |
CQA cycles if fully vectorized | 0.21 |
Front-end cycles | 1.67 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
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 | 1.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 1.85 |
Stall cycles (UFS) | 0.03 |
Nb insns | 10.00 |
Nb uops | 9.00 |
Nb loads | 5.00 |
Nb stores | 0.00 |
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 | 24.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 40.00 |
Bytes stored | 0.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 0.00 |
Stride unknown | 2.00 |
Stride indirect | 0.00 |
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_ParMatmul_RowSizes._omp_fn.0 |
Source file and lines | par_csr_matop.c:218-231 |
Module | exec |
nb instructions | 11.50 |
nb uops | 10.50 |
loop length | 46 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 1.92 cycles |
front end | 1.92 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.80 | 1.83 | 1.83 | 0.25 | 0.60 | 1.00 | 0.25 | 0.25 | 0.25 | 0.60 | 1.83 |
cycles | 1.00 | 0.80 | 1.83 | 1.83 | 0.25 | 0.60 | 1.00 | 0.25 | 0.25 | 0.25 | 0.60 | 1.83 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.08 |
Stall cycles | 0.02 |
LM full (events) | 0.08 |
Front-end | 1.92 |
Dispatch | 1.83 |
Data deps. | 1.00 |
Overall L1 | 1.92 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
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 | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Function | hypre_ParMatmul_RowSizes._omp_fn.0 |
Source file and lines | par_csr_matop.c:218-231 |
Module | exec |
nb instructions | 13 |
nb uops | 12 |
loop length | 51 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 2.17 cycles |
front end | 2.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.80 | 2.00 | 2.00 | 0.50 | 0.60 | 1.00 | 0.50 | 0.50 | 0.50 | 0.60 | 2.00 |
cycles | 1.00 | 0.80 | 2.00 | 2.00 | 0.50 | 0.60 | 1.00 | 0.50 | 0.50 | 0.50 | 0.60 | 2.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.31 |
Stall cycles | 0.00 |
Front-end | 2.17 |
Dispatch | 2.00 |
Data deps. | 1.00 |
Overall L1 | 2.17 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
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 | 12% |
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 (%R14,%RAX,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0xf0(%RSP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0xf8(%RSP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD (%R11,%RDX,8),%R15 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
LEA (%RDI,%R15,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP (%RDX),%R10 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JLE 559370 <hypre_ParMatmul_RowSizes._omp_fn.0+0x4b0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R8,(%RDX) | 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 |
INC %R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV (%R13),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JG 559330 <hypre_ParMatmul_RowSizes._omp_fn.0+0x470> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | hypre_ParMatmul_RowSizes._omp_fn.0 |
Source file and lines | par_csr_matop.c:218-231 |
Module | exec |
nb instructions | 10 |
nb uops | 9 |
loop length | 41 |
used x86 registers | 9 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 1.67 cycles |
front end | 1.67 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.80 | 1.67 | 1.67 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 1.67 |
cycles | 1.00 | 0.80 | 1.67 | 1.67 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 1.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 1.85 |
Stall cycles | 0.03 |
LM full (events) | 0.16 |
Front-end | 1.67 |
Dispatch | 1.67 |
Data deps. | 1.00 |
Overall L1 | 1.67 |
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 (%R14,%RAX,8),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0xf0(%RSP),%R11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0xf8(%RSP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD (%R11,%RDX,8),%R15 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
LEA (%RDI,%R15,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CMP (%RDX),%R10 | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JLE 559370 <hypre_ParMatmul_RowSizes._omp_fn.0+0x4b0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
INC %RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RAX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JG 559330 <hypre_ParMatmul_RowSizes._omp_fn.0+0x470> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |