Loop Id: 7 | Module: exec | Source: stream.c:476-479 | Coverage: 0.25% |
---|
Loop Id: 7 | Module: exec | Source: stream.c:476-479 | Coverage: 0.25% |
---|
0x401820 VMOVUPD (%RBX,%RDI,8),%ZMM9 [1] |
0x401827 VSUBPD %ZMM1,%ZMM9,%ZMM9 |
0x40182d VANDPD %ZMM16,%ZMM9,%ZMM9 |
0x401833 VADDPD %ZMM7,%ZMM9,%ZMM7 |
0x401839 VMOVUPD (%R12,%RDI,8),%ZMM9 [1] |
0x401840 VSUBPD %ZMM8,%ZMM9,%ZMM9 |
0x401846 VANDPD %ZMM16,%ZMM9,%ZMM9 |
0x40184c VADDPD %ZMM3,%ZMM9,%ZMM3 |
0x401852 VMOVUPD (%R14,%RDI,8),%ZMM9 [1] |
0x401859 VSUBPD %ZMM2,%ZMM9,%ZMM9 |
0x40185f VANDPD %ZMM16,%ZMM9,%ZMM9 |
0x401865 VADDPD %ZMM6,%ZMM9,%ZMM6 |
0x40186b ADD $0x8,%RDI |
0x40186f CMP %RSI,%RDI |
0x401872 JBE 401820 |
/scratch_na/users/xoserete/qaas_runs/171-415-2041/intel/stream/build/stream/src/stream.c: 476 - 479 |
-------------------------------------------------------------------------------- |
476: for (j=0; j<STREAM_ARRAY_SIZE; j++) { |
477: aSumErr += abs(a[j] - aj); |
478: bSumErr += abs(b[j] - bj); |
479: cSumErr += abs(c[j] - cj); |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | main | stream.c:390 | 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 | 1.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.50 |
Bottlenecks | P0, P5, |
Function | checkSTREAMresults |
Source | stream.c:476-479 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 8 |
CQA cycles | 4.50 |
CQA cycles if no scalar integer | 4.50 |
CQA cycles if FP arith vectorized | 4.50 |
CQA cycles if fully vectorized | 4.50 |
Front-end cycles | 2.33 |
DIV/SQRT cycles | 4.50 |
P0 cycles | 3.00 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 0.00 |
P4 cycles | 4.50 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 1.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 3 |
FE+BE cycles (UFS) | 4.64 |
Stall cycles (UFS) | 1.76 |
Nb insns | 15.00 |
Nb uops | 14.00 |
Nb loads | 3.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 10.67 |
Nb FLOP add-sub | 48.00 |
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 | 42.67 |
Bytes prefetched | 0.00 |
Bytes loaded | 192.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 3.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 100.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 100.00 |
Vector-efficiency ratio load | 100.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 100.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 100.00 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.50 |
Bottlenecks | P0, P5, |
Function | checkSTREAMresults |
Source | stream.c:476-479 |
Source loop unroll info | unrolled by 8 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 8 |
CQA cycles | 4.50 |
CQA cycles if no scalar integer | 4.50 |
CQA cycles if FP arith vectorized | 4.50 |
CQA cycles if fully vectorized | 4.50 |
Front-end cycles | 2.33 |
DIV/SQRT cycles | 4.50 |
P0 cycles | 3.00 |
P1 cycles | 1.00 |
P2 cycles | 1.00 |
P3 cycles | 0.00 |
P4 cycles | 4.50 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 1.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 3 |
FE+BE cycles (UFS) | 4.64 |
Stall cycles (UFS) | 1.76 |
Nb insns | 15.00 |
Nb uops | 14.00 |
Nb loads | 3.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 10.67 |
Nb FLOP add-sub | 48.00 |
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 | 42.67 |
Bytes prefetched | 0.00 |
Bytes loaded | 192.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 3.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 100.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 100.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 100.00 |
Vector-efficiency ratio all | 100.00 |
Vector-efficiency ratio load | 100.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 100.00 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 100.00 |
Path / |
Function | checkSTREAMresults |
Source file and lines | stream.c:476-479 |
Module | exec |
nb instructions | 15 |
nb uops | 14 |
loop length | 84 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 8 |
nb stack references | 0 |
micro-operation queue | 2.33 cycles |
front end | 2.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.50 | 0.00 | 1.00 | 1.00 | 0.00 | 4.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.00 |
cycles | 4.50 | 3.00 | 1.00 | 1.00 | 0.00 | 4.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 3.00 |
FE+BE cycles | 4.64 |
Stall cycles | 1.76 |
RS full (events) | 3.68 |
Front-end | 2.33 |
Dispatch | 4.50 |
Data deps. | 3.00 |
Overall L1 | 4.50 |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVUPD (%RBX,%RDI,8),%ZMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VSUBPD %ZMM1,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VANDPD %ZMM16,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VADDPD %ZMM7,%ZMM9,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVUPD (%R12,%RDI,8),%ZMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VSUBPD %ZMM8,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VANDPD %ZMM16,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VADDPD %ZMM3,%ZMM9,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVUPD (%R14,%RDI,8),%ZMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VSUBPD %ZMM2,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VANDPD %ZMM16,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VADDPD %ZMM6,%ZMM9,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
ADD $0x8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RSI,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JBE 401820 <checkSTREAMresults+0x180> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | checkSTREAMresults |
Source file and lines | stream.c:476-479 |
Module | exec |
nb instructions | 15 |
nb uops | 14 |
loop length | 84 |
used x86 registers | 5 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 8 |
nb stack references | 0 |
micro-operation queue | 2.33 cycles |
front end | 2.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.50 | 0.00 | 1.00 | 1.00 | 0.00 | 4.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.00 |
cycles | 4.50 | 3.00 | 1.00 | 1.00 | 0.00 | 4.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 3.00 |
FE+BE cycles | 4.64 |
Stall cycles | 1.76 |
RS full (events) | 3.68 |
Front-end | 2.33 |
Dispatch | 4.50 |
Data deps. | 3.00 |
Overall L1 | 4.50 |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 100% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVUPD (%RBX,%RDI,8),%ZMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VSUBPD %ZMM1,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VANDPD %ZMM16,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VADDPD %ZMM7,%ZMM9,%ZMM7 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVUPD (%R12,%RDI,8),%ZMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VSUBPD %ZMM8,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VANDPD %ZMM16,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VADDPD %ZMM3,%ZMM9,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVUPD (%R14,%RDI,8),%ZMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.50 |
VSUBPD %ZMM2,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VANDPD %ZMM16,%ZMM9,%ZMM9 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VADDPD %ZMM6,%ZMM9,%ZMM6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
ADD $0x8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RSI,%RDI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JBE 401820 <checkSTREAMresults+0x180> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |