Loop Id: 10 | Module: exec | Source: Step10_orig.c:29-29 | Coverage: 6.24% |
---|
Loop Id: 10 | Module: exec | Source: Step10_orig.c:29-29 | Coverage: 6.24% |
---|
0x40160c LASTB D3, P2, Z4.D |
0x401610 FMUL D3, D3, D3 |
0x401614 FDIV D3, D24, D3 |
0x401618 CPY Z15.D, P2/M, D3 |
0x40161c PNEXT P2.D, P0, P2.D |
0x401620 B.NE 40160c |
/home/hbollore/qaas-runs/170-256-3563/intel/HACCmk/build/HACCmk/src/Step10_orig.c: 29 - 29 |
-------------------------------------------------------------------------------- |
29: f = pow( r2 + mp_rsm2, -1.5 ) - ( ma0 + r2*(ma1 + r2*(ma2 + r2*(ma3 + r2*(ma4 + r2*ma5))))); |
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 | 4.00 - 6.86 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.33 |
Bottlenecks | |
Function | Step10_orig |
Source | Step10_orig.c:29-29 |
Source loop unroll info | multi-versionned |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
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 | 0.50 - 0.29 |
Front-end cycles | 0.75 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 0.50 |
P1 cycles | 0.00 |
P2 cycles | 0.00 |
P3 cycles | 1.00 |
P4 cycles | 0.00 |
P5 cycles | 1.50 |
P6 cycles | 1.00 |
P7 cycles | 0.75 |
P8 cycles | 0.75 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
P12 cycles | 0.00 |
P13 cycles | 0.00 |
P14 cycles | 1.00 - 0.50 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 6.00 |
Nb uops | 6.00 |
Nb loads | NA |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 1.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 1.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 0.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 0.00 |
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 | NA |
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 | 18.75 |
Vector-efficiency ratio load | NA |
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 | 18.75 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 4.00 - 6.86 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.33 |
Bottlenecks | |
Function | Step10_orig |
Source | Step10_orig.c:29-29 |
Source loop unroll info | multi-versionned |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
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 | 0.50 - 0.29 |
Front-end cycles | 0.75 |
DIV/SQRT cycles | 0.50 |
P0 cycles | 0.50 |
P1 cycles | 0.00 |
P2 cycles | 0.00 |
P3 cycles | 1.00 |
P4 cycles | 0.00 |
P5 cycles | 1.50 |
P6 cycles | 1.00 |
P7 cycles | 0.75 |
P8 cycles | 0.75 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
P12 cycles | 0.00 |
P13 cycles | 0.00 |
P14 cycles | 1.00 - 0.50 |
Inter-iter dependencies cycles | 2 |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 6.00 |
Nb uops | 6.00 |
Nb loads | NA |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 1.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 1.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 0.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 0.00 |
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 | NA |
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 | 18.75 |
Vector-efficiency ratio load | NA |
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 | 18.75 |
Path / |
Function | Step10_orig |
Source file and lines | Step10_orig.c:29-29 |
Module | exec |
nb instructions | 6 |
loop length | 24 |
nb stack references | 0 |
front end | 0.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.50 | 0.50 | 0.00 | 0.00 | 1.00 | 0.00 | 1.50 | 1.00 | 0.75 | 0.75 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 0.50 | 0.50 | 0.00 | 0.00 | 1.00 | 0.00 | 1.50 | 1.00 | 0.75 | 0.75 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | 1.00-0.50 |
Longest recurrence chain latency (RecMII) | 2.00 |
Front-end | 0.75 |
Data deps. | 2.00 |
Overall L1 | 2.00 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
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% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LASTB D3, P2, Z4.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
FMUL D3, D3, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 |
FDIV D3, D24, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 7-15 | 1-0.50 |
CPY Z15.D, P2/M, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 |
PNEXT P2.D, P0, P2.D | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
B.NE 40160c <Step10_orig+0x1ac> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
Function | Step10_orig |
Source file and lines | Step10_orig.c:29-29 |
Module | exec |
nb instructions | 6 |
loop length | 24 |
nb stack references | 0 |
front end | 0.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 0.50 | 0.50 | 0.00 | 0.00 | 1.00 | 0.00 | 1.50 | 1.00 | 0.75 | 0.75 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 0.50 | 0.50 | 0.00 | 0.00 | 1.00 | 0.00 | 1.50 | 1.00 | 0.75 | 0.75 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | 1.00-0.50 |
Longest recurrence chain latency (RecMII) | 2.00 |
Front-end | 0.75 |
Data deps. | 2.00 |
Overall L1 | 2.00 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
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% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LASTB D3, P2, Z4.D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
FMUL D3, D3, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 |
FDIV D3, D24, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 7-15 | 1-0.50 |
CPY Z15.D, P2/M, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 |
PNEXT P2.D, P0, P2.D | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
B.NE 40160c <Step10_orig+0x1ac> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |