vectorcall - Branch - ifduyue/python-xxhash

perf: METH_FASTCALL, tp_vectorcall, and related optimizations

#147Merged

Comparing

vectorcall

(

a974b6b

) with

master

(

1585d2b

)

Untouched: 10

New: 24

Skipped: 86

Benchmarks

86 total

The benchmarks below were skipped, so their baseline results are used instead. If they were deleted in your codebase, archive them to remove them from the performance reports.
Learn more about archiving benchmarks

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh32_digest_512kb

tests/test_benchmark.py

Skipped

523.8 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_hexdigest_512kb

tests/test_benchmark.py

Skipped

445 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh32_digest_10kb

tests/test_benchmark.py

Skipped

94.5 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh32_hexdigest_1kb

tests/test_benchmark.py

Skipped

87.7 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_hexdigest_2mb

tests/test_benchmark.py

Skipped

1.6 ms*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_hexdigest_10kb

tests/test_benchmark.py

Skipped

94.6 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_streaming_digest_10kb

tests/test_benchmark.py

Skipped

129.9 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_hexdigest_1kb

tests/test_benchmark.py

Skipped

88.4 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_intdigest_10kb

tests/test_benchmark.py

Skipped

95.7 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_digest_2mb

tests/test_benchmark.py

Skipped

1.6 ms*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_digest_512kb

tests/test_benchmark.py

Skipped

444.2 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh32_hexdigest_512kb

tests/test_benchmark.py

Skipped

524.2 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh32_intdigest_10kb

tests/test_benchmark.py

Skipped

96.1 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh32_hexdigest_10kb

tests/test_benchmark.py

Skipped

96.8 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh32_streaming_digest_1kb

tests/test_benchmark.py

Skipped

103.2 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh32_intdigest_512kb

tests/test_benchmark.py

Skipped

523.8 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_streaming_digest_512kb

tests/test_benchmark.py

Skipped

1.7 ms*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh32_digest_1kb

tests/test_benchmark.py

Skipped

86.9 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_streaming_hexdigest_512kb

tests/test_benchmark.py

Skipped

1.7 ms*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_intdigest_512kb

tests/test_benchmark.py

Skipped

446.3 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_streaming_digest_1kb

tests/test_benchmark.py

Skipped

103.1 µs*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_streaming_intdigest_2mb

tests/test_benchmark.py

Skipped

6.6 ms*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_streaming_digest_2mb

tests/test_benchmark.py

Skipped

6.6 ms*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh32_digest_2mb

tests/test_benchmark.py

Skipped

1.9 ms*

Uses the CPU Simulation instrument
to collect CPU performance metrics.

test_xxh3_128_streaming_hexdigest_1kb

tests/test_benchmark.py

Skipped

103.4 µs*

Commits

Click on a commit to change the comparison range

Base

master

1585d2b

+0.75%

perf: add tp_vectorcall to all four hash types

1585d2b

3 days ago

by ifduyue

-1.26%

fix: remove unsupported min_rounds from codspeed benchmark markers

f49eaa4

3 days ago

by ifduyue

+0.05%

fix: don't overwrite tp_alloc error with PyErr_NoMemory in vectorcall

da76b27

3 days ago

by ifduyue

-0.02%

fix: release buffer on tp_alloc failure in vectorcall functions

9647f32

3 days ago

by ifduyue

+0.02%

refactor: reuse PYXXH*_do_update helpers in vectorcall functions

cba0f28

3 days ago

by ifduyue

+0.06%

fix: use buf.obj instead of buf.buf for buffer-acquired check

14675ad

3 days ago

by ifduyue

+0.28%

bench: add 2MB throughput benchmarks

a974b6b

3 days ago

by ifduyue

Home Terms Privacy Docs