facebook
/
zstd
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #2253 from facebook/histvec 

optimized histogram
dev
Yann Collet 2020-08-02 14:08:42 -07:00 committed by GitHub
parent f85a0f8bcf 8b9cdd2597
commit 60b56e3b5f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 15 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
lib/compress/hist.c
View File

@ -60,9 +60,9 @@ typedef enum { trustInput, checkMaxSymbolValue } HIST_checkInput_e;
* this design makes better use of OoO cpus,
* and is noticeably faster when some values are heavily repeated.
* But it needs some additional workspace for intermediate tables.
* `workSpace` size must be a table of size >= HIST_WKSP_SIZE_U32.
* `workSpace` must be a U32 table of size >= HIST_WKSP_SIZE_U32.
* @return : largest histogram frequency,
* or an error code (notably when histogram would be larger than *maxSymbolValuePtr). */
* or an error code (notably when histogram's alphabet is larger than *maxSymbolValuePtr) */
static size_t HIST_count_parallel_wksp(
unsigned* count, unsigned* maxSymbolValuePtr,
const void* source, size_t sourceSize,
@ -71,22 +71,21 @@ static size_t HIST_count_parallel_wksp(
{
const BYTE* ip = (const BYTE*)source;
const BYTE* const iend = ip+sourceSize;
unsigned maxSymbolValue = *maxSymbolValuePtr;
size_t const countSize = (*maxSymbolValuePtr + 1) * sizeof(*count);
unsigned max=0;
U32* const Counting1 = workSpace;
U32* const Counting2 = Counting1 + 256;
U32* const Counting3 = Counting2 + 256;
U32* const Counting4 = Counting3 + 256;
memset(workSpace, 0, 4*256*sizeof(unsigned));
/* safety checks */
assert(*maxSymbolValuePtr <= 255);
if (!sourceSize) {
memset(count, 0, maxSymbolValue + 1);
memset(count, 0, countSize);
*maxSymbolValuePtr = 0;
return 0;
}
if (!maxSymbolValue) maxSymbolValue = 255; /* 0 == default */
memset(workSpace, 0, 4*256*sizeof(unsigned));
/* by stripes of 16 bytes */
{ U32 cached = MEM_read32(ip); ip += 4;
@ -118,21 +117,18 @@ static size_t HIST_count_parallel_wksp(
/* finish last symbols */
while (ip<iend) Counting1[*ip++]++;
if (check) { /* verify stats will fit into destination table */
U32 s; for (s=255; s>maxSymbolValue; s--) {
Counting1[s] += Counting2[s] + Counting3[s] + Counting4[s];
if (Counting1[s]) return ERROR(maxSymbolValue_tooSmall);
} }
{ U32 s;
if (maxSymbolValue > 255) maxSymbolValue = 255;
for (s=0; s<=maxSymbolValue; s++) {
count[s] = Counting1[s] + Counting2[s] + Counting3[s] + Counting4[s];
if (count[s] > max) max = count[s];
for (s=0; s<256; s++) {
Counting1[s] += Counting2[s] + Counting3[s] + Counting4[s];
if (Counting1[s] > max) max = Counting1[s];
} }
while (!count[maxSymbolValue]) maxSymbolValue--;
*maxSymbolValuePtr = maxSymbolValue;
{ unsigned maxSymbolValue = 255;
while (!Counting1[maxSymbolValue]) maxSymbolValue--;
if (check && maxSymbolValue > *maxSymbolValuePtr) return ERROR(maxSymbolValue_tooSmall);
*maxSymbolValuePtr = maxSymbolValue;
memmove(count, Counting1, countSize); /* in case count & Counting1 are overlapping */
}
return (size_t)max;
}