Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update create results body #16

Open
wants to merge 1 commit into
base: testing-format-perf-table
Choose a base branch
from

Conversation

jlb6740
Copy link
Owner

@jlb6740 jlb6740 commented Oct 27, 2022

No description provided.

@jlb6740
Copy link
Owner Author

jlb6740 commented Oct 27, 2022

/bench_x64

@jlb6740
Copy link
Owner Author

jlb6740 commented Oct 27, 2022

Change factor shows patch effect on x64 if merged compared to current head for main.

Results are based on clocktick (CT) event cycles. Change Factor = (Patched_CT - Main_CT) / (Main_CT)
A negative change factor means clockticks are expected to be reduced by the patch.

wasm arch phase change_factor
benchmarks/blake3-scalar x86_64 Compilation -2.264%
benchmarks/blake3-simd x86_64 Compilation -0.952%
benchmarks/bz2 x86_64 Compilation -1.169%
benchmarks/intgemm-simd x86_64 Compilation -0.073%
benchmarks/meshoptimizer x86_64 Compilation -0.470%
benchmarks/noop x86_64 Compilation 1.484%
benchmarks/pulldown-cmark x86_64 Compilation 2.920%
benchmarks/shootout-ackermann x86_64 Compilation -1.525%
benchmarks/shootout-base64 x86_64 Compilation 3.301%
benchmarks/shootout-ctype x86_64 Compilation -2.706%
benchmarks/shootout-ed25519 x86_64 Compilation 1.641%
benchmarks/shootout-fib2 x86_64 Compilation -0.268%
benchmarks/shootout-gimli x86_64 Compilation 6.551%
benchmarks/shootout-heapsort x86_64 Compilation 1.015%
benchmarks/shootout-keccak x86_64 Compilation -1.059%
benchmarks/shootout-matrix x86_64 Compilation 1.295%
benchmarks/shootout-memmove x86_64 Compilation -5.877%
benchmarks/shootout-minicsv x86_64 Compilation 1.779%
benchmarks/shootout-nestedloop x86_64 Compilation 0.122%
benchmarks/shootout-random x86_64 Compilation -0.916%
benchmarks/shootout-ratelimit x86_64 Compilation 2.141%
benchmarks/shootout-seqhash x86_64 Compilation 1.004%
benchmarks/shootout-sieve x86_64 Compilation 0.260%
benchmarks/shootout-switch x86_64 Compilation 3.673%
benchmarks/shootout-xblabla20 x86_64 Compilation -2.125%
benchmarks/shootout-xchacha20 x86_64 Compilation 0.693%
benchmarks/spidermonkey x86_64 Compilation -0.094%
wasm arch phase change_factor
benchmarks/blake3-scalar x86_64 Instantiation -8.503%
benchmarks/blake3-simd x86_64 Instantiation 11.889%
benchmarks/bz2 x86_64 Instantiation 10.633%
benchmarks/intgemm-simd x86_64 Instantiation -20.765%
benchmarks/meshoptimizer x86_64 Instantiation 15.852%
benchmarks/noop x86_64 Instantiation 3.321%
benchmarks/pulldown-cmark x86_64 Instantiation -3.284%
benchmarks/shootout-ackermann x86_64 Instantiation -0.097%
benchmarks/shootout-base64 x86_64 Instantiation -1.808%
benchmarks/shootout-ctype x86_64 Instantiation -15.002%
benchmarks/shootout-ed25519 x86_64 Instantiation 0.630%
benchmarks/shootout-fib2 x86_64 Instantiation -0.610%
benchmarks/shootout-gimli x86_64 Instantiation 15.031%
benchmarks/shootout-heapsort x86_64 Instantiation 25.119%
benchmarks/shootout-keccak x86_64 Instantiation 5.948%
benchmarks/shootout-matrix x86_64 Instantiation 5.849%
benchmarks/shootout-memmove x86_64 Instantiation 2.700%
benchmarks/shootout-minicsv x86_64 Instantiation -25.233%
benchmarks/shootout-nestedloop x86_64 Instantiation 3.077%
benchmarks/shootout-random x86_64 Instantiation 1.315%
benchmarks/shootout-ratelimit x86_64 Instantiation 0.327%
benchmarks/shootout-seqhash x86_64 Instantiation -4.867%
benchmarks/shootout-sieve x86_64 Instantiation 3.642%
benchmarks/shootout-switch x86_64 Instantiation -0.317%
benchmarks/shootout-xblabla20 x86_64 Instantiation 3.272%
benchmarks/shootout-xchacha20 x86_64 Instantiation 11.555%
benchmarks/spidermonkey x86_64 Instantiation -2.845%
wasm arch phase change_factor
benchmarks/blake3-scalar x86_64 Execution -1.544%
benchmarks/blake3-simd x86_64 Execution -3.132%
benchmarks/bz2 x86_64 Execution 2.717%
benchmarks/intgemm-simd x86_64 Execution 0.179%
benchmarks/meshoptimizer x86_64 Execution 0.007%
benchmarks/noop x86_64 Execution -4.482%
benchmarks/pulldown-cmark x86_64 Execution -0.157%
benchmarks/shootout-ackermann x86_64 Execution -19.695%
benchmarks/shootout-base64 x86_64 Execution -0.069%
benchmarks/shootout-ctype x86_64 Execution 0.295%
benchmarks/shootout-ed25519 x86_64 Execution 0.082%
benchmarks/shootout-fib2 x86_64 Execution 0.060%
benchmarks/shootout-gimli x86_64 Execution -0.897%
benchmarks/shootout-heapsort x86_64 Execution 0.105%
benchmarks/shootout-keccak x86_64 Execution -0.574%
benchmarks/shootout-matrix x86_64 Execution -0.213%
benchmarks/shootout-memmove x86_64 Execution 0.211%
benchmarks/shootout-minicsv x86_64 Execution 0.063%
benchmarks/shootout-nestedloop x86_64 Execution -0.075%
benchmarks/shootout-random x86_64 Execution 0.101%
benchmarks/shootout-ratelimit x86_64 Execution 0.270%
benchmarks/shootout-seqhash x86_64 Execution 0.039%
benchmarks/shootout-sieve x86_64 Execution 0.001%
benchmarks/shootout-switch x86_64 Execution 0.447%
benchmarks/shootout-xblabla20 x86_64 Execution 1.642%
benchmarks/shootout-xchacha20 x86_64 Execution 1.066%
benchmarks/spidermonkey x86_64 Execution 0.598%

Averages (x64):

phase change_factor
Compilation 0.310%
Execution -0.850%
Instantiation 1.364%

@jlb6740 jlb6740 force-pushed the testing-format-perf-table3 branch from 376b4b5 to d94e33d Compare October 27, 2022 22:35
@jlb6740
Copy link
Owner Author

jlb6740 commented Oct 27, 2022

/bench_x64

@jlb6740
Copy link
Owner Author

jlb6740 commented Oct 27, 2022

compilation :: cycles :: benchmarks/spidermonkey/benchmark.wasm
Δ = 82527143.92 ± 63070105.09 (confidence = 99%)
commit.so is 1.00x to 1.02x faster than main.so!
[7094332044 7223827788.16 7369651872] commit.so
[7139730906 7306354932.08 7431698916] main.so

instantiation :: cycles :: benchmarks/pulldown-cmark/benchmark.wasm

No difference in performance.

[169480 194998.24 210320] commit.so
[167832 203042.88 301708] main.so

instantiation :: cycles :: benchmarks/spidermonkey/benchmark.wasm

No difference in performance.

[549258 583124.16 757248] commit.so
[542590 567999.68 608536] main.so

instantiation :: cycles :: benchmarks/bz2/benchmark.wasm

No difference in performance.

[103436 120873.76 135018] commit.so
[105472 123793.28 140580] main.so

compilation :: cycles :: benchmarks/bz2/benchmark.wasm

No difference in performance.

[211848442 231664096.96 272095476] commit.so
[214570300 230438081.68 271099534] main.so

execution :: cycles :: benchmarks/spidermonkey/benchmark.wasm

No difference in performance.

[1095587488 1106584867.76 1193067486] commit.so
[1089941538 1102936389.84 1114682980] main.so

execution :: cycles :: benchmarks/bz2/benchmark.wasm

No difference in performance.

[127597786 131041954.32 137982918] commit.so
[127647464 131380642.72 132328992] main.so

execution :: cycles :: benchmarks/pulldown-cmark/benchmark.wasm

No difference in performance.

[9331596 9484503.52 9749314] commit.so
[9349982 9492117.12 9707010] main.so

compilation :: cycles :: benchmarks/pulldown-cmark/benchmark.wasm

No difference in performance.

[318786584 344304061.12 378910388] commit.so
[316337080 344223652.96 365993334] main.so

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant