Decompression of level 12 frames
Decoder overview · Benchmark index
Recorded run: long-20261109 (2026-11-09). CSV · Environment · Methodology and limits.
Level belongs to the C encoder that prepared the frame; decoders have no level setting. Both decoders restore the same bytes.
Median speed across 8 datasets
Median of per-dataset C mean time / decoder mean time ratios, with equal weight. Higher is faster; 1× matches C. No confidence interval is inferred for this across-dataset median.
| Decoder | Median speed / C |
|---|---|
| zstd C | 1.000× |
| mzstd | 1.591× |
Datasets are ranked by mzstd speed relative to C, highest first. Throughput counts restored bytes; empty input has latency only. Whiskers and intervals describe sampling uncertainty, not all host variation. Cold APIs include allocation and disposal. C reads the frame’s content size and decodes into a buffer of exactly that size; mzstd returns its own vector.
empty
Empty input; measures API overhead.
9 compressed → 0 restored bytes; compressed / original: undefined.
| Decoder | Mean µs | 95% mean interval µs | Decoded MiB/s | Speed / C |
|---|---|---|---|---|
| zstd C | 2.225 | 2.168–2.285 | — | 1.000× |
| mzstd | 0.04463 | 0.04284–0.04646 | — | 49.850× |
tiny-text
44-byte quick-brown-fox sentence.
53 compressed → 44 restored bytes; compressed / original: 120.455%.
| Decoder | Mean µs | 95% mean interval µs | Decoded MiB/s | Speed / C |
|---|---|---|---|---|
| zstd C | 2.031 | 1.978–2.091 | 20.66 | 1.000× |
| mzstd | 0.05169 | 0.04981–0.05385 | 811.73 | 39.293× |
random-64k
64 KiB prefix of the deterministic pseudorandom corpus.
65,546 compressed → 65,536 restored bytes; compressed / original: 100.015%.
| Decoder | Mean µs | 95% mean interval µs | Decoded MiB/s | Speed / C |
|---|---|---|---|---|
| zstd C | 2.984 | 2.909–3.067 | 20,948.48 | 1.000× |
| mzstd | 0.9015 | 0.8957–0.9084 | 69,327.13 | 3.309× |
repeated-1m
1 MiB of repeated a bytes.
49 compressed → 1,048,576 restored bytes; compressed / original: 0.005%.
| Decoder | Mean µs | 95% mean interval µs | Decoded MiB/s | Speed / C |
|---|---|---|---|---|
| zstd C | 17.54 | 17.09–17.97 | 57,016.25 | 1.000× |
| mzstd | 10.56 | 10.33–10.81 | 94,653.90 | 1.660× |
binary-64k
64 KiB of structured binary bytes: ((i / 16) XOR i) modulo 256.
1,276 compressed → 65,536 restored bytes; compressed / original: 1.947%.
| Decoder | Mean µs | 95% mean interval µs | Decoded MiB/s | Speed / C |
|---|---|---|---|---|
| zstd C | 6.587 | 6.267–6.928 | 9,488.05 | 1.000× |
| mzstd | 4.33 | 4.168–4.508 | 14,435.58 | 1.521× |
random-1m
1 MiB of deterministic xorshift64 pseudorandom bytes.
1,048,609 compressed → 1,048,576 restored bytes; compressed / original: 100.003%.
| Decoder | Mean µs | 95% mean interval µs | Decoded MiB/s | Speed / C |
|---|---|---|---|---|
| zstd C | 19.92 | 19.66–20.2 | 50,200.53 | 1.000× |
| mzstd | 17.16 | 17.03–17.3 | 58,286.72 | 1.161× |
text-1m
Alice text repeated cyclically to 1 MiB.
52,034 compressed → 1,048,576 restored bytes; compressed / original: 4.962%.
| Decoder | Mean µs | 95% mean interval µs | Decoded MiB/s | Speed / C |
|---|---|---|---|---|
| zstd C | 100.6 | 99.23–102.4 | 9,937.21 | 1.000× |
| mzstd | 104.1 | 102.9–105.6 | 9,609.88 | 0.967× |
alice29
Alice in Wonderland text from the Canterbury corpus (testdata/alice29.txt).
51,492 compressed → 152,089 restored bytes; compressed / original: 33.856%.
| Decoder | Mean µs | 95% mean interval µs | Decoded MiB/s | Speed / C |
|---|---|---|---|---|
| zstd C | 95.56 | 91.75–99.98 | 1,517.85 | 1.000× |
| mzstd | 100.5 | 97.48–104 | 1,442.87 | 0.951× |