lz4_flex VS LZ4

I run a benchmark based on my LZ4 implementation (de/compressor) between cax11 and cx11 since the instances cost the same. The code doesn't use any SIMD.

By the way, the PR removing bounds checks from extend_from_within_overlapping is up: https://github.com/PSeitz/lz4_flex/pull/141

Zap uses LZ4 as it's primary compression algorithm, although I might add ZSTD as an option too. The LZ4 crate i'm using goes over the compression better than I can in the span of a comment. Check it out here.

I wrote something here how hc could work: https://github.com/PSeitz/lz4_flex/issues/21

Yes, the updated benchmarks are here: https://github.com/pseitz/lz4_flex#results-v080-17-05-2021-safe-decode-and-safe-encode-off

I ported the block format to Rust matching the C implementation in performance and ratio.

https://github.com/pseitz/lz4_flex

Following this change count_same_bytes is unsound - it offsets the pointer by the value of candidate without any bounds checks, which may result in out-of-bounds access.

LZ4 is a bit more complicated, but seems faster: https://github.com/lz4/lz4/blob/dev/doc/lz4_Block_format.md

According to these https://github.com/lz4/lz4 values you need around ten (10) quite modern cores in parallel to accomplish around 8GB/s.

The popular NoSQL database Cassandra utilizes a compression algorithm called LZ4 to reduce the footprint of data at rest. LZ4 is characterized by very fast compression speed at the cost of a higher compression ratio. This is a design choice that allows Cassandra to maintain high write throughput while also benefiting from compression in some capacity.

Yeah, sure, when you have monster core counts. on regular systems, not so much, here's from their own github page. it achieves, eh, 5GB/s on memory to memory transfers, i.e. best case scenario. so, uh, no? i'm not even sure it's any better than the CPU decompressor one Nvidia used.

> The downside of lz4 is that it can’t be configured to run at higher & slower compression ratios.

lz4 has some level of configurability? https://github.com/lz4/lz4/blob/v1.9.4/lib/lz4frame.h#L194

There's also LZ4_HC.

Since nobody mentioned it, I'll add lz4 (https://github.com/lz4/lz4).

Get your bootloader unlocked via Download mode and then obtain your stock firmware, preferably for your current region https://samfw.com (Download mode: CARRIER_CODE). Get the boot image from AP with 7zip, unpack from LZ4 with https://github.com/lz4/lz4/releases (drag and drop), patch with Magisk https://github.com/topjohnwu/magisk/releases/latest, grab the new image, name it "boot.img" and pack it into a .tar with 7zip and flash to AP with odin https://odindownload.com

After some investigations and experiments, I found out that it was the PNG compression (well, decompression I should say) that took a while. So I've made some experiments using the LZ4 compression library, which is focused on decompression speed, and it turned out to be an excellent solution!

Root with magisk: whether you use OneUI ≤3 or 4, patch the specific image needed for it (pre 4: boot, after 4: recovery) and flash it to the device. Boot it and enjoy root. https://github.com/lz4/lz4/releases can help extracting it from the AP tarball.