Loop Id: 3372 | Module: exec | Source: par_csr_matop.c:187-231 [...] | Coverage: 0.66% |
---|
Loop Id: 3372 | Module: exec | Source: par_csr_matop.c:187-231 [...] | Coverage: 0.66% |
---|
0x4af5c0 INC %R10 |
0x4af5c3 MOV -0x58(%RBP),%RSI |
0x4af5c7 CMP (%RSI,%RDX,8),%R10 |
0x4af5cb JGE 4af490 |
0x4af5d1 MOV -0x80(%RBP),%RSI |
0x4af5d5 MOV (%RSI,%R10,8),%R12 |
0x4af5d9 MOV 0x20(%RBP),%RDI |
0x4af5dd MOV (%RDI,%R12,8),%RSI |
0x4af5e1 MOV 0x8(%RDI,%R12,8),%RDI |
0x4af5e6 JMP 4af5f3 |
(3374) 0x4af5f0 INC %RSI |
(3374) 0x4af5f3 CMP %RDI,%RSI |
(3374) 0x4af5f6 JGE 4af620 |
(3374) 0x4af5f8 MOV (%RCX,%RSI,8),%R9 |
(3374) 0x4af5fc CMP %RBX,(%R14,%R9,8) |
(3374) 0x4af600 JGE 4af5f0 |
(3374) 0x4af602 MOV %RAX,(%R14,%R9,8) |
(3374) 0x4af606 INC %RAX |
(3374) 0x4af609 MOV 0x20(%RBP),%RDI |
(3374) 0x4af60d MOV 0x8(%RDI,%R12,8),%RDI |
(3374) 0x4af612 JMP 4af5f0 |
0x4af620 CMPQ $0,0x88(%RBP) |
0x4af628 JE 4af5c0 |
0x4af62a MOV 0x30(%RBP),%RDI |
0x4af62e MOV (%RDI,%R12,8),%RSI |
0x4af632 MOV 0x8(%RDI,%R12,8),%RDI |
0x4af637 JMP 4af643 |
(3373) 0x4af640 INC %RSI |
(3373) 0x4af643 CMP %RDI,%RSI |
(3373) 0x4af646 JGE 4af5c0 |
(3373) 0x4af64c MOV 0x38(%RBP),%R9 |
(3373) 0x4af650 MOV (%R9,%RSI,8),%R9 |
(3373) 0x4af654 MOV 0x60(%RBP),%R11 |
(3373) 0x4af658 MOV (%R11,%R9,8),%R9 |
(3373) 0x4af65c ADD %R15,%R9 |
(3373) 0x4af65f CMP %R8,(%R14,%R9,8) |
(3373) 0x4af663 JGE 4af640 |
(3373) 0x4af665 MOV %R13,(%R14,%R9,8) |
(3373) 0x4af669 INC %R13 |
(3373) 0x4af66c MOV 0x30(%RBP),%RDI |
(3373) 0x4af670 MOV 0x8(%RDI,%R12,8),%RDI |
(3373) 0x4af675 JMP 4af640 |
/scratch_na/users/xoserete/qaas_runs/171-172-8217/intel/AMG/build/AMG/AMG/parcsr_mv/par_csr_matop.c: 187 - 231 |
-------------------------------------------------------------------------------- |
187: for (jj2 = A_diag_i[i1]; jj2 < A_diag_i[i1+1]; jj2++) |
188: { |
189: i2 = A_diag_j[jj2]; |
[...] |
195: for (jj3 = B_diag_i[i2]; jj3 < B_diag_i[i2+1]; jj3++) |
196: { |
197: i3 = B_diag_j[jj3]; |
[...] |
205: if (B_marker[i3] < jj_row_begin_diag) |
206: { |
207: B_marker[i3] = jj_count_diag; |
208: jj_count_diag++; |
[...] |
216: if (num_cols_offd_B) |
217: { |
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 | 1.29 |
Bottlenecks | P2, P3, P11, |
Function | hypre_ParMatmul_RowSizes.extracted |
Source | par_csr_matop.c:187-189,par_csr_matop.c:195-195,par_csr_matop.c:216-218 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.67 |
CQA cycles if no scalar integer | 3.67 |
CQA cycles if FP arith vectorized | 3.67 |
CQA cycles if fully vectorized | 0.46 |
Front-end cycles | 2.83 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 3.67 |
P2 cycles | 3.67 |
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 | 3.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 4.81 |
Stall cycles (UFS) | 1.86 |
Nb insns | 16.00 |
Nb uops | 16.00 |
Nb loads | 11.00 |
Nb stores | 0.00 |
Nb stack references | 5.00 |
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 | 88.00 |
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 | 1.29 |
Bottlenecks | P2, P3, P11, |
Function | hypre_ParMatmul_RowSizes.extracted |
Source | par_csr_matop.c:187-189,par_csr_matop.c:195-195,par_csr_matop.c:216-218 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 3.67 |
CQA cycles if no scalar integer | 3.67 |
CQA cycles if FP arith vectorized | 3.67 |
CQA cycles if fully vectorized | 0.46 |
Front-end cycles | 2.83 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 0.80 |
P1 cycles | 3.67 |
P2 cycles | 3.67 |
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 | 3.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 4.81 |
Stall cycles (UFS) | 1.86 |
Nb insns | 16.00 |
Nb uops | 16.00 |
Nb loads | 11.00 |
Nb stores | 0.00 |
Nb stack references | 5.00 |
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 | 88.00 |
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_ParMatmul_RowSizes.extracted |
Source file and lines | par_csr_matop.c:187-231 |
Module | exec |
nb instructions | 16 |
nb uops | 16 |
loop length | 65 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 2.83 cycles |
front end | 2.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.80 | 3.67 | 3.67 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 3.67 |
cycles | 1.00 | 0.80 | 3.67 | 3.67 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 3.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 4.81 |
Stall cycles | 1.86 |
LM full (events) | 4.50 |
Front-end | 2.83 |
Dispatch | 3.67 |
Overall L1 | 3.67 |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x58(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP (%RSI,%RDX,8),%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 |
JGE 4af490 <hypre_ParMatmul_RowSizes.extracted+0xf0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x80(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%R10,8),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x20(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI,%R12,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RDI,%R12,8),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 4af5f3 <hypre_ParMatmul_RowSizes.extracted+0x253> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
CMPQ $0,0x88(%RBP) | 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 4af5c0 <hypre_ParMatmul_RowSizes.extracted+0x220> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x30(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI,%R12,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RDI,%R12,8),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 4af643 <hypre_ParMatmul_RowSizes.extracted+0x2a3> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
Function | hypre_ParMatmul_RowSizes.extracted |
Source file and lines | par_csr_matop.c:187-231 |
Module | exec |
nb instructions | 16 |
nb uops | 16 |
loop length | 65 |
used x86 registers | 6 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 2.83 cycles |
front end | 2.83 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.80 | 3.67 | 3.67 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 3.67 |
cycles | 1.00 | 0.80 | 3.67 | 3.67 | 0.00 | 0.60 | 1.00 | 0.00 | 0.00 | 0.00 | 0.60 | 3.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 4.81 |
Stall cycles | 1.86 |
LM full (events) | 4.50 |
Front-end | 2.83 |
Dispatch | 3.67 |
Overall L1 | 3.67 |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV -0x58(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP (%RSI,%RDX,8),%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 |
JGE 4af490 <hypre_ParMatmul_RowSizes.extracted+0xf0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV -0x80(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RSI,%R10,8),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x20(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI,%R12,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RDI,%R12,8),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 4af5f3 <hypre_ParMatmul_RowSizes.extracted+0x253> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |
CMPQ $0,0x88(%RBP) | 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 4af5c0 <hypre_ParMatmul_RowSizes.extracted+0x220> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x30(%RBP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RDI,%R12,8),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x8(%RDI,%R12,8),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
JMP 4af643 <hypre_ParMatmul_RowSizes.extracted+0x2a3> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 5.84 |