ddidderr/zstd-rs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[huf] Add generic C versions of the fast decoding loops

Browse Source 
Add generic C versions of the fast decoding loops to serve architectures
that don't have an assembly implementation. Also allow selecting the C
decoding loop over the assembly decoding loop through a zstd
decompression parameter `ZSTD_d_disableHuffmanAssembly`.

I benchmarked on my Intel i9-9900K and my Macbook Air with an M1 processor.
The benchmark command forces zstd to compress without any matches, using
only literals compression, and measures only Huffman decompression speed:

```
zstd -b1e1 --compress-literals --zstd=tlen=131072 silesia.tar
```

The new fast decoding loops outperform the previous implementation uniformly,
but don't beat the x86-64 assembly. Additionally, the fast C decoding loops suffer
from the same stability problems that we've seen in the past, where the assembly
version doesn't. So even though clang gets close to assembly on x86-64, it still
has stability issues.

| Arch    | Function       | Compiler     | Default (MB/s) | Assembly (MB/s) | Fast (MB/s) |
|---------|----------------|--------------|----------------|-----------------|-------------|
| x86-64  | decompress 4X1 | gcc-12.2.0   |         1029.6 |          1308.1 |      1208.1 |
| x86-64  | decompress 4X1 | clang-14.0.6 |         1019.3 |          1305.6 |      1276.3 |
| x86-64  | decompress 4X2 | gcc-12.2.0   |         1348.5 |          1657.0 |      1374.1 |
| x86-64  | decompress 4X2 | clang-14.0.6 |         1027.6 |          1659.9 |      1468.1 |
| aarch64 | decompress 4X1 | clang-12.0.5 |         1081.0 |             N/A |      1234.9 |
| aarch64 | decompress 4X2 | clang-12.0.5 |         1270.0 |             N/A |      1516.6 |
This commit is contained in:
Nick Terrell
2023-01-25 13:47:51 -08:00
committed by Nick Terrell
parent f3255bfeff
commit 8957fef554
13 changed files with 448 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/zstd.h
+14 -1
View File
@@ -614,13 +614,15 @@ typedef enum {
* ZSTD_d_stableOutBuffer
* ZSTD_d_forceIgnoreChecksum
* ZSTD_d_refMultipleDDicts
* ZSTD_d_disableHuffmanAssembly
* Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them.
* note : never ever use experimentalParam? names directly
*/
ZSTD_d_experimentalParam1=1000,
ZSTD_d_experimentalParam2=1001,
ZSTD_d_experimentalParam3=1002,
ZSTD_d_experimentalParam4=1003
ZSTD_d_experimentalParam4=1003,
ZSTD_d_experimentalParam5=1004
} ZSTD_dParameter;
@@ -2345,6 +2347,17 @@ ZSTDLIB_STATIC_API size_t ZSTD_DCtx_getParameter(ZSTD_DCtx* dctx, ZSTD_dParamete
*/
#define ZSTD_d_refMultipleDDicts ZSTD_d_experimentalParam4
/* ZSTD_d_disableHuffmanAssembly
* Set to 1 to disable the Huffman assembly implementation.
* The default value is 0, which allows zstd to use the Huffman assembly
* implementation if available.
*
* This parameter can be used to disable Huffman assembly at runtime.
* If you want to disable it at compile time you can define the macro
* ZSTD_DISABLE_ASM.
*/
#define ZSTD_d_disableHuffmanAssembly ZSTD_d_experimentalParam5
/*! ZSTD_DCtx_setFormat() :
* This function is REDUNDANT. Prefer ZSTD_DCtx_setParameter().