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/decompress/huf_decompress_amd64.S
+14 -12
View File
@@ -30,14 +30,14 @@
* TODO: Support Windows calling convention.
*/
ZSTD_HIDE_ASM_FUNCTION(HUF_decompress4X1_usingDTable_internal_bmi2_asm_loop)
ZSTD_HIDE_ASM_FUNCTION(HUF_decompress4X2_usingDTable_internal_bmi2_asm_loop)
ZSTD_HIDE_ASM_FUNCTION(_HUF_decompress4X2_usingDTable_internal_bmi2_asm_loop)
ZSTD_HIDE_ASM_FUNCTION(_HUF_decompress4X1_usingDTable_internal_bmi2_asm_loop)
.global HUF_decompress4X1_usingDTable_internal_bmi2_asm_loop
.global HUF_decompress4X2_usingDTable_internal_bmi2_asm_loop
.global _HUF_decompress4X1_usingDTable_internal_bmi2_asm_loop
.global _HUF_decompress4X2_usingDTable_internal_bmi2_asm_loop
ZSTD_HIDE_ASM_FUNCTION(HUF_decompress4X1_usingDTable_internal_fast_asm_loop)
ZSTD_HIDE_ASM_FUNCTION(HUF_decompress4X2_usingDTable_internal_fast_asm_loop)
ZSTD_HIDE_ASM_FUNCTION(_HUF_decompress4X2_usingDTable_internal_fast_asm_loop)
ZSTD_HIDE_ASM_FUNCTION(_HUF_decompress4X1_usingDTable_internal_fast_asm_loop)
.global HUF_decompress4X1_usingDTable_internal_fast_asm_loop
.global HUF_decompress4X2_usingDTable_internal_fast_asm_loop
.global _HUF_decompress4X1_usingDTable_internal_fast_asm_loop
.global _HUF_decompress4X2_usingDTable_internal_fast_asm_loop
.text
/* Sets up register mappings for clarity.
@@ -95,8 +95,9 @@ ZSTD_HIDE_ASM_FUNCTION(_HUF_decompress4X1_usingDTable_internal_bmi2_asm_loop)
/* Define both _HUF_* & HUF_* symbols because MacOS
* C symbols are prefixed with '_' & Linux symbols aren't.
*/
_HUF_decompress4X1_usingDTable_internal_bmi2_asm_loop:
HUF_decompress4X1_usingDTable_internal_bmi2_asm_loop:
_HUF_decompress4X1_usingDTable_internal_fast_asm_loop:
HUF_decompress4X1_usingDTable_internal_fast_asm_loop:
ZSTD_CET_ENDBRANCH
/* Save all registers - even if they are callee saved for simplicity. */
push %rax
push %rbx
@@ -350,8 +351,9 @@ HUF_decompress4X1_usingDTable_internal_bmi2_asm_loop:
pop %rax
ret
_HUF_decompress4X2_usingDTable_internal_bmi2_asm_loop:
HUF_decompress4X2_usingDTable_internal_bmi2_asm_loop:
_HUF_decompress4X2_usingDTable_internal_fast_asm_loop:
HUF_decompress4X2_usingDTable_internal_fast_asm_loop:
ZSTD_CET_ENDBRANCH
/* Save all registers - even if they are callee saved for simplicity. */
push %rax
push %rbx