Loop Id: 1022 | Module: exec | Source: csr_matvec.c:312-312 | Coverage: 32.53% |
---|
Loop Id: 1022 | Module: exec | Source: csr_matvec.c:312-312 | Coverage: 32.53% |
---|
0x4aa7c0 LDP X7, X21, [X4, #1016] [3] |
0x4aa7c4 LDP D2, D3, [X5, #1016] [1] |
0x4aa7c8 SUBS X6, X6, #2 |
0x4aa7cc ADD X4, X4, #16 |
0x4aa7d0 ADD X5, X5, #16 |
0x4aa7d4 LDR D4, [X11, X7,LSL #3] [2] |
0x4aa7d8 LDR D5, [X11, X21,LSL #3] [2] |
0x4aa7dc FMSUB D0, D4, D2, D0 |
0x4aa7e0 FMSUB D1, D5, D3, D1 |
0x4aa7e4 B.NE 4aa7c0 |
/home/hbollore/qaas/qaas-runs/169-817-3176/intel/AMG/build/AMG/AMG/seq_mv/csr_matvec.c: 312 - 312 |
-------------------------------------------------------------------------------- |
312: tempx -= A_data[jj] * x_data[A_j[jj]]; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
○100.00 | __kmp_invoke_microtask | libomp.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 | 3.64 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.50 |
Bottlenecks | |
Function | .omp_outlined..18#0x4a9fb0 |
Source | csr_matvec.c:312-312 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | low |
Unroll/vectorization loop type | NA |
Unroll factor | 2 |
CQA cycles | 2.00 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 2.00 |
CQA cycles if fully vectorized | 0.55 |
Front-end cycles | 1.25 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 0.50 |
P1 cycles | 0.75 |
P2 cycles | 0.75 |
P3 cycles | 0.75 |
P4 cycles | 0.75 |
P5 cycles | 0.50 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 1.33 |
P10 cycles | 1.33 |
P11 cycles | 1.33 |
P12 cycles | 0.00 |
P13 cycles | 0.00 |
P14 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 10.00 |
Nb uops | 10.00 |
Nb loads | NA |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 2.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 2.00 |
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 | 48.00 |
Bytes stored | 0.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 25.00 |
Vectorization ratio load | 33.33 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 31.25 |
Vector-efficiency ratio load | 33.33 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 25.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 3.64 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.50 |
Bottlenecks | |
Function | .omp_outlined..18#0x4a9fb0 |
Source | csr_matvec.c:312-312 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | low |
Unroll/vectorization loop type | NA |
Unroll factor | 2 |
CQA cycles | 2.00 |
CQA cycles if no scalar integer | 2.00 |
CQA cycles if FP arith vectorized | 2.00 |
CQA cycles if fully vectorized | 0.55 |
Front-end cycles | 1.25 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 0.50 |
P1 cycles | 0.75 |
P2 cycles | 0.75 |
P3 cycles | 0.75 |
P4 cycles | 0.75 |
P5 cycles | 0.50 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 1.33 |
P10 cycles | 1.33 |
P11 cycles | 1.33 |
P12 cycles | 0.00 |
P13 cycles | 0.00 |
P14 cycles | 0.00 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 10.00 |
Nb uops | 10.00 |
Nb loads | NA |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 2.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 2.00 |
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 | 48.00 |
Bytes stored | 0.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 25.00 |
Vectorization ratio load | 33.33 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 31.25 |
Vector-efficiency ratio load | 33.33 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 25.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Path / |
Function | .omp_outlined..18#0x4a9fb0 |
Source file and lines | csr_matvec.c:312-312 |
Module | exec |
nb instructions | 10 |
loop length | 40 |
nb stack references | 0 |
front end | 1.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.50 | 0.50 | 0.75 | 0.75 | 0.75 | 0.75 | 0.50 | 0.50 | 0.50 | 0.50 | 1.33 | 1.33 | 1.33 | 0.00 | 0.00 |
cycles | 0.50 | 0.50 | 0.75 | 0.75 | 0.75 | 0.75 | 0.50 | 0.50 | 0.50 | 0.50 | 1.33 | 1.33 | 1.33 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
Front-end | 1.25 |
Data deps. | 2.00 |
Overall L1 | 2.00 |
all | 25% |
load | 33% |
store | NA (no store vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LDP X7, X21, [X4, #1016] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
LDP D2, D3, [X5, #1016] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 |
SUBS X6, X6, #2 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
ADD X4, X4, #16 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD X5, X5, #16 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
LDR D4, [X11, X7,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 |
LDR D5, [X11, X21,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 |
FMSUB D0, D4, D2, D0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 |
FMSUB D1, D5, D3, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 |
B.NE 4aa7c0 <.omp_outlined..18+0x810> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
Function | .omp_outlined..18#0x4a9fb0 |
Source file and lines | csr_matvec.c:312-312 |
Module | exec |
nb instructions | 10 |
loop length | 40 |
nb stack references | 0 |
front end | 1.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.50 | 0.50 | 0.75 | 0.75 | 0.75 | 0.75 | 0.50 | 0.50 | 0.50 | 0.50 | 1.33 | 1.33 | 1.33 | 0.00 | 0.00 |
cycles | 0.50 | 0.50 | 0.75 | 0.75 | 0.75 | 0.75 | 0.50 | 0.50 | 0.50 | 0.50 | 1.33 | 1.33 | 1.33 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 2.00 |
Front-end | 1.25 |
Data deps. | 2.00 |
Overall L1 | 2.00 |
all | 25% |
load | 33% |
store | NA (no store vectorizable/vectorized instructions) |
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 | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LDP X7, X21, [X4, #1016] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 4 | 1 |
LDP D2, D3, [X5, #1016] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 |
SUBS X6, X6, #2 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
ADD X4, X4, #16 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
ADD X5, X5, #16 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 |
LDR D4, [X11, X7,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 |
LDR D5, [X11, X21,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 |
FMSUB D0, D4, D2, D0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 |
FMSUB D1, D5, D3, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 |
B.NE 4aa7c0 <.omp_outlined..18+0x810> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |