[llvm-exegesis] Split Epsilon param into two (PR40787)
Summary:
This eps param is used for two distinct things:
* initial point clusterization
* checking clusters against the llvm values
What if one wants to only look at highly different clusters, without changing
the clustering itself? In particular, this helps to weed out noisy measurements
(since the clusterization epsilon is still small, so there is a better chance
that noisy measurements from the same opcode will go into different clusters)
By splitting it into two params it is now possible.
This is nearly-free performance-wise:
Old:
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency-1.yaml -analysis-inconsistencies-output-file=/tmp/clusters-old.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 10099 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-old.html'
...
Performance counter stats for './bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency-1.yaml -analysis-inconsistencies-output-file=/tmp/clusters-old.html' (25 runs):
390.01 msec task-clock # 0.998 CPUs utilized ( +- 0.25% )
12 context-switches # 31.735 M/sec ( +- 27.38% )
0 cpu-migrations # 0.000 K/sec
4745 page-faults # 12183.732 M/sec ( +- 0.54% )
1562711900 cycles # 4012303.327 GHz ( +- 0.24% ) (82.90%)
185567822 stalled-cycles-frontend # 11.87% frontend cycles idle ( +- 0.52% ) (83.30%)
392106234 stalled-cycles-backend # 25.09% backend cycles idle ( +- 1.31% ) (33.79%)
1839236666 instructions # 1.18 insn per cycle
# 0.21 stalled cycles per insn ( +- 0.15% ) (50.37%)
407035764 branches # 1045074878.710 M/sec ( +- 0.12% ) (66.80%)
10896459 branch-misses # 2.68% of all branches ( +- 0.17% ) (83.20%)
0.390629 +- 0.000972 seconds time elapsed ( +- 0.25% )
```
```
$ perf stat -r 9 ./bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency.yml -analysis-inconsistencies-output-file=/tmp/clusters-old.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 50572 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-old.html'
...
Performance counter stats for './bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency.yml -analysis-inconsistencies-output-file=/tmp/clusters-old.html' (9 runs):
6803.36 msec task-clock # 0.999 CPUs utilized ( +- 0.96% )
262 context-switches # 38.546 M/sec ( +- 23.06% )
0 cpu-migrations # 0.065 M/sec ( +- 76.03% )
13287 page-faults # 1953.206 M/sec ( +- 0.32% )
27252537904 cycles # 4006024.257 GHz ( +- 0.95% ) (83.31%)
1496314935 stalled-cycles-frontend # 5.49% frontend cycles idle ( +- 0.97% ) (83.32%)
16128404524 stalled-cycles-backend # 59.18% backend cycles idle ( +- 0.30% ) (33.37%)
17611143370 instructions # 0.65 insn per cycle
# 0.92 stalled cycles per insn ( +- 0.05% ) (50.04%)
3894906599 branches # 572537147.437 M/sec ( +- 0.03% ) (66.69%)
116314514 branch-misses # 2.99% of all branches ( +- 0.20% ) (83.35%)
6.8118 +- 0.0689 seconds time elapsed ( +- 1.01%)
```
New:
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency-1.yaml -analysis-inconsistencies-output-file=/tmp/clusters-new.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 10099 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new.html'
...
Performance counter stats for './bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency-1.yaml -analysis-inconsistencies-output-file=/tmp/clusters-new.html' (25 runs):
400.14 msec task-clock # 0.998 CPUs utilized ( +- 0.66% )
12 context-switches # 29.429 M/sec ( +- 25.95% )
0 cpu-migrations # 0.100 M/sec ( +-100.00% )
4714 page-faults # 11796.496 M/sec ( +- 0.55% )
1603131306 cycles # 4011840.105 GHz ( +- 0.66% ) (82.85%)
199538509 stalled-cycles-frontend # 12.45% frontend cycles idle ( +- 2.40% ) (83.10%)
402249109 stalled-cycles-backend # 25.09% backend cycles idle ( +- 1.19% ) (34.05%)
1847783963 instructions # 1.15 insn per cycle
# 0.22 stalled cycles per insn ( +- 0.18% ) (50.64%)
407162722 branches # 1018925730.631 M/sec ( +- 0.12% ) (67.02%)
10932779 branch-misses # 2.69% of all branches ( +- 0.51% ) (83.28%)
0.40077 +- 0.00267 seconds time elapsed ( +- 0.67% )
lebedevri@pini-pini:/build/llvm-build-Clang-release$ perf stat -r 9 ./bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency.yml -analysis-inconsistencies-output-file=/tmp/clusters-new.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 50572 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new.html'
...
Performance counter stats for './bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency.yml -analysis-inconsistencies-output-file=/tmp/clusters-new.html' (9 runs):
6947.79 msec task-clock # 1.000 CPUs utilized ( +- 0.90% )
217 context-switches # 31.236 M/sec ( +- 36.16% )
1 cpu-migrations # 0.096 M/sec ( +- 50.00% )
13258 page-faults # 1908.389 M/sec ( +- 0.34% )
27830796523 cycles # 4006032.286 GHz ( +- 0.89% ) (83.30%)
1504554006 stalled-cycles-frontend # 5.41% frontend cycles idle ( +- 2.10% ) (83.32%)
16716574843 stalled-cycles-backend # 60.07% backend cycles idle ( +- 0.65% ) (33.38%)
17755545931 instructions # 0.64 insn per cycle
# 0.94 stalled cycles per insn ( +- 0.09% ) (50.04%)
3897255686 branches # 560980426.597 M/sec ( +- 0.06% ) (66.70%)
117045395 branch-misses # 3.00% of all branches ( +- 0.47% ) (83.34%)
6.9507 +- 0.0627 seconds time elapsed ( +- 0.90% )
```
I.e. it's +2.6% slowdown for one whole sweep, or +2% for 5 whole sweeps.
Within noise i'd say.
Should help with [[ https://bugs.llvm.org/show_bug.cgi?id=40787 | PR40787 ]].
Reviewers: courbet, gchatelet
Reviewed By: courbet
Subscribers: tschuett, RKSimon, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D58476
llvm-svn: 354767
2019-02-25 17:36:12 +08:00
|
|
|
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-clusters-output-file=- -analysis-clustering-epsilon=0.1 -analysis-inconsistency-epsilon=0.1 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-CLUSTERS %s
|
|
|
|
|
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-inconsistencies-output-file=- -analysis-clustering-epsilon=0.5 -analysis-inconsistency-epsilon=0.5 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-INCONSISTENCIES-ALL,CHECK-INCONSISTENCIES-STABLE %s
|
|
|
|
|
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-inconsistencies-output-file=- -analysis-clustering-epsilon=0.5 -analysis-inconsistency-epsilon=0.5 -analysis-display-unstable-clusters -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-INCONSISTENCIES-ALL,CHECK-INCONSISTENCIES-UNSTABLE %s
|
[llvm-exegesis] Opcode stabilization / reclusterization (PR40715)
Summary:
Given an instruction `Opcode`, we can make benchmarks (measurements) of the
instruction characteristics/performance. Then, to facilitate further analysis
we group the benchmarks with *similar* characteristics into clusters.
Now, this is all not entirely deterministic. Some instructions have variable
characteristics, depending on their arguments. And thus, if we do several
benchmarks of the same instruction `Opcode`, we may end up with *different*
performance characteristics measurements. And when we then do clustering,
these several benchmarks of the same instruction `Opcode` may end up being
clustered into *different* clusters. This is not great for further analysis.
We shall find every `Opcode` with benchmarks not in just one cluster, and move
*all* the benchmarks of said `Opcode` into one new unstable cluster per `Opcode`.
I have solved this by making `ClusterId` a bit field, adding a `IsUnstable` bit,
and introducing `-analysis-display-unstable-clusters` switch to toggle between
displaying stable-only clusters and unstable-only clusters.
The reclusterization is deterministically stable, produces identical reports
between runs. (Or at least that is what i'm seeing, maybe it isn't)
Timings/comparisons:
old (current trunk/head) {F8303582}
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=0.5 -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-inverse_throughput.yaml -analysis-inconsistencies-output-file=/tmp/clusters-old.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 43970 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-old.html'
...
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 43970 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-old.html'
Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=0.5 -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-inverse_throughput.yaml -analysis-inconsistencies-output-file=/tmp/clusters-old.html' (25 runs):
6624.73 msec task-clock # 0.999 CPUs utilized ( +- 0.53% )
172 context-switches # 25.965 M/sec ( +- 29.89% )
0 cpu-migrations # 0.042 M/sec ( +- 56.54% )
31073 page-faults # 4690.754 M/sec ( +- 0.08% )
26538711696 cycles # 4006230.292 GHz ( +- 0.53% ) (83.31%)
2017496807 stalled-cycles-frontend # 7.60% frontend cycles idle ( +- 0.93% ) (83.32%)
13403650062 stalled-cycles-backend # 50.51% backend cycles idle ( +- 0.33% ) (33.37%)
19770706799 instructions # 0.74 insn per cycle
# 0.68 stalled cycles per insn ( +- 0.04% ) (50.04%)
4419821812 branches # 667207369.714 M/sec ( +- 0.03% ) (66.69%)
121741669 branch-misses # 2.75% of all branches ( +- 0.28% ) (83.34%)
6.6283 +- 0.0358 seconds time elapsed ( +- 0.54% )
```
patch, with reclustering but without filtering (i.e. outputting all the stable *and* unstable clusters) {F8303586}
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=0.5 -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-inverse_throughput.yaml -analysis-inconsistencies-output-file=/tmp/clusters-new-all.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 43970 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new-all.html'
...
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 43970 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new-all.html'
Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=0.5 -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-inverse_throughput.yaml -analysis-inconsistencies-output-file=/tmp/clusters-new-all.html' (25 runs):
6475.29 msec task-clock # 0.999 CPUs utilized ( +- 0.31% )
213 context-switches # 32.952 M/sec ( +- 23.81% )
1 cpu-migrations # 0.130 M/sec ( +- 43.84% )
31287 page-faults # 4832.057 M/sec ( +- 0.08% )
25939086577 cycles # 4006160.279 GHz ( +- 0.31% ) (83.31%)
1958812858 stalled-cycles-frontend # 7.55% frontend cycles idle ( +- 0.68% ) (83.32%)
13218961512 stalled-cycles-backend # 50.96% backend cycles idle ( +- 0.29% ) (33.37%)
19752995402 instructions # 0.76 insn per cycle
# 0.67 stalled cycles per insn ( +- 0.04% ) (50.04%)
4417079244 branches # 682195472.305 M/sec ( +- 0.03% ) (66.70%)
121510065 branch-misses # 2.75% of all branches ( +- 0.19% ) (83.34%)
6.4832 +- 0.0229 seconds time elapsed ( +- 0.35% )
```
Funnily, *this* measurement shows that said reclustering actually improved performance.
patch, with reclustering, only the stable clusters {F8303594}
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=0.5 -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-inverse_throughput.yaml -analysis-inconsistencies-output-file=/tmp/clusters-new-stable.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 43970 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new-stable.html'
...
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 43970 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new-stable.html'
Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=0.5 -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-inverse_throughput.yaml -analysis-inconsistencies-output-file=/tmp/clusters-new-stable.html' (25 runs):
6387.71 msec task-clock # 0.999 CPUs utilized ( +- 0.13% )
133 context-switches # 20.792 M/sec ( +- 23.39% )
0 cpu-migrations # 0.063 M/sec ( +- 61.24% )
31318 page-faults # 4903.256 M/sec ( +- 0.08% )
25591984967 cycles # 4006786.266 GHz ( +- 0.13% ) (83.31%)
1881234904 stalled-cycles-frontend # 7.35% frontend cycles idle ( +- 0.25% ) (83.33%)
13209749965 stalled-cycles-backend # 51.62% backend cycles idle ( +- 0.16% ) (33.36%)
19767554347 instructions # 0.77 insn per cycle
# 0.67 stalled cycles per insn ( +- 0.04% ) (50.03%)
4417480305 branches # 691618858.046 M/sec ( +- 0.03% ) (66.68%)
118676358 branch-misses # 2.69% of all branches ( +- 0.07% ) (83.33%)
6.3954 +- 0.0118 seconds time elapsed ( +- 0.18% )
```
Performance improved even further?! Makes sense i guess, less clusters to print.
patch, with reclustering, only the unstable clusters {F8303601}
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=0.5 -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-inverse_throughput.yaml -analysis-inconsistencies-output-file=/tmp/clusters-new-unstable.html -analysis-display-unstable-clusters
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 43970 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new-unstable.html'
...
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 43970 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new-unstable.html'
Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=0.5 -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-inverse_throughput.yaml -analysis-inconsistencies-output-file=/tmp/clusters-new-unstable.html -analysis-display-unstable-clusters' (25 runs):
6124.96 msec task-clock # 1.000 CPUs utilized ( +- 0.20% )
194 context-switches # 31.709 M/sec ( +- 20.46% )
0 cpu-migrations # 0.039 M/sec ( +- 49.77% )
31413 page-faults # 5129.261 M/sec ( +- 0.06% )
24536794267 cycles # 4006425.858 GHz ( +- 0.19% ) (83.31%)
1676085087 stalled-cycles-frontend # 6.83% frontend cycles idle ( +- 0.46% ) (83.32%)
13035595603 stalled-cycles-backend # 53.13% backend cycles idle ( +- 0.16% ) (33.36%)
18260877653 instructions # 0.74 insn per cycle
# 0.71 stalled cycles per insn ( +- 0.05% ) (50.03%)
4112411983 branches # 671484364.603 M/sec ( +- 0.03% ) (66.68%)
114066929 branch-misses # 2.77% of all branches ( +- 0.11% ) (83.32%)
6.1278 +- 0.0121 seconds time elapsed ( +- 0.20% )
```
This tells us that the actual `-analysis-inconsistencies-output-file=` outputting only takes ~0.4 sec for 43970 benchmark points (3 whole sweeps)
(Also, wow this is fast, it used to take several minutes originally)
Fixes [[ https://bugs.llvm.org/show_bug.cgi?id=40715 | PR40715 ]].
Reviewers: courbet, gchatelet
Reviewed By: courbet
Subscribers: tschuett, jdoerfert, llvm-commits, RKSimon
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D58355
llvm-svn: 354441
2019-02-20 17:14:04 +08:00
|
|
|
|
|
|
|
|
# We have one ADD32rr measurement, and two measurements for SQRTSSr.
|
|
|
|
|
# The ADD32rr measurement and one of the SQRTSSr measurements are identical,
|
|
|
|
|
# and thus will be be in the same cluster. But the second SQRTSSr measurement
|
|
|
|
|
# is different from the first SQRTSSr measurement, and thus it will be in it's
|
|
|
|
|
# own cluster. We do reclusterization, and thus since there is more than one
|
|
|
|
|
# measurement from SQRTSSr, and they are not in the same cluster, we move
|
|
|
|
|
# all two SQRTSSr measurements into their own cluster, and mark it as unstable.
|
|
|
|
|
# By default, we do not show such unstable clusters.
|
|
|
|
|
# If told to show, we *only* show such unstable clusters.
|
|
|
|
|
|
|
|
|
|
# CHECK-CLUSTERS: {{^}}cluster_id,opcode_name,config,sched_class,latency{{$}}
|
|
|
|
|
# CHECK-CLUSTERS-NEXT: {{^}}0,
|
|
|
|
|
# CHECK-CLUSTERS-SAME: ,90.00{{$}}
|
|
|
|
|
# CHECK-CLUSTERS: {{^}}3,
|
|
|
|
|
# CHECK-CLUSTERS-SAME: ,90.11{{$}}
|
|
|
|
|
# CHECK-CLUSTERS-NEXT: {{^}}3,
|
|
|
|
|
# CHECK-CLUSTERS-SAME: ,100.00{{$}}
|
|
|
|
|
|
|
|
|
|
# CHECK-INCONSISTENCIES-STABLE: ADD32rr
|
|
|
|
|
# CHECK-INCONSISTENCIES-STABLE-NOT: ADD32rr
|
|
|
|
|
# CHECK-INCONSISTENCIES-STABLE-NOT: SQRTSSr
|
|
|
|
|
|
|
|
|
|
# CHECK-INCONSISTENCIES-UNSTABLE: SQRTSSr
|
|
|
|
|
# CHECK-INCONSISTENCIES-UNSTABLE: SQRTSSr
|
|
|
|
|
# CHECK-INCONSISTENCIES-UNSTABLE-NOT: SQRTSSr
|
|
|
|
|
# CHECK-INCONSISTENCIES-UNSTABLE-NOT: ADD32rr
|
|
|
|
|
|
|
|
|
|
---
|
|
|
|
|
mode: latency
|
|
|
|
|
key:
|
|
|
|
|
instructions:
|
|
|
|
|
- 'ADD32rr EDX EDX EAX'
|
|
|
|
|
config: ''
|
|
|
|
|
register_initial_values:
|
|
|
|
|
- 'EDX=0x0'
|
|
|
|
|
- 'EAX=0x0'
|
|
|
|
|
cpu_name: bdver2
|
|
|
|
|
llvm_triple: x86_64-unknown-linux-gnu
|
|
|
|
|
num_repetitions: 10000
|
|
|
|
|
measurements:
|
|
|
|
|
- { key: latency, value: 90.0000, per_snippet_value: 90.0000 }
|
|
|
|
|
error: ''
|
|
|
|
|
info: Repeating a single implicitly serial instruction
|
|
|
|
|
assembled_snippet: BA00000000B80000000001C201C201C201C201C201C201C201C201C201C201C201C201C201C201C201C2C3
|
|
|
|
|
---
|
|
|
|
|
mode: latency
|
|
|
|
|
key:
|
|
|
|
|
instructions:
|
|
|
|
|
- 'SQRTSSr XMM11 XMM11'
|
|
|
|
|
config: ''
|
|
|
|
|
register_initial_values:
|
|
|
|
|
- 'XMM11=0x0'
|
|
|
|
|
cpu_name: bdver2
|
|
|
|
|
llvm_triple: x86_64-unknown-linux-gnu
|
|
|
|
|
num_repetitions: 10000
|
|
|
|
|
measurements:
|
|
|
|
|
- { key: latency, value: 90.1111, per_snippet_value: 90.1111 }
|
|
|
|
|
error: ''
|
|
|
|
|
info: Repeating a single explicitly serial instruction
|
|
|
|
|
assembled_snippet: 4883EC10C7042400000000C744240400000000C744240800000000C744240C00000000C57A6F1C244883C410F3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBC3
|
|
|
|
|
...
|
|
|
|
|
---
|
|
|
|
|
mode: latency
|
|
|
|
|
key:
|
|
|
|
|
instructions:
|
|
|
|
|
- 'SQRTSSr XMM11 XMM11'
|
|
|
|
|
config: ''
|
|
|
|
|
register_initial_values:
|
|
|
|
|
- 'XMM11=0x0'
|
|
|
|
|
cpu_name: bdver2
|
|
|
|
|
llvm_triple: x86_64-unknown-linux-gnu
|
|
|
|
|
num_repetitions: 10000
|
|
|
|
|
measurements:
|
|
|
|
|
- { key: latency, value: 100, per_snippet_value: 100 }
|
|
|
|
|
error: ''
|
|
|
|
|
info: Repeating a single explicitly serial instruction
|
|
|
|
|
assembled_snippet: 4883EC10C7042400000000C744240400000000C744240800000000C744240C00000000C57A6F1C244883C410F3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBC3
|
|
|
|
|
...
|