dany/libwebp
1
0
Fork 0
mirror of https://github.com/webmproject/libwebp.git synced 2024-12-28 14:38:21 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

mips32/mipsDSPr2: function ImportRow rebased

Browse Source 
Change-Id: Id58d266040fdb5fe1e507cd0f6370ea625156e4d
This commit is contained in:
Djordje Pesut 2015-08-06 15:52:27 +02:00
parent 7df93893dc
commit 717e4d5a7c
2 changed files with 211 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

108
src/dsp/rescaler_mips32.c
View File

@ -17,6 +17,113 @@
#include "../utils/rescaler.h" #include "../utils/rescaler.h"
static void ImportRow(WebPRescaler* const wrk,
const uint8_t* const src, int channel) {
const int x_stride = wrk->num_channels;
const int x_out_max = wrk->dst_width * wrk->num_channels;
const int fx_scale = wrk->fx_scale;
const int x_add = wrk->x_add;
const int x_sub = wrk->x_sub;
const int src_width = wrk->src_width;
int* frow = wrk->frow + channel;
int* irow = wrk->irow + channel;
const uint8_t* src1 = src + channel;
int temp1, temp2, temp3, temp4;
int base, frac, sum;
int accum, accum1;
const int x_stride1 = x_stride << 2;
int loop_c = x_out_max - channel;
int x_out = channel;
if (!wrk->x_expand) {
__asm__ volatile (
"li %[temp1], 0x8000 \n\t"
"li %[temp2], 0x10000 \n\t"
"li %[sum], 0 \n\t"
"li %[accum], 0 \n\t"
"1: \n\t"
"addu %[accum], %[accum], %[x_add] \n\t"
"li %[base], 0 \n\t"
"blez %[accum], 3f \n\t"
"2: \n\t"
"lbu %[base], 0(%[src1]) \n\t"
"subu %[accum], %[accum], %[x_sub] \n\t"
"addu %[src1], %[src1], %[x_stride] \n\t"
"addu %[sum], %[sum], %[base] \n\t"
"bgtz %[accum], 2b \n\t"
"3: \n\t"
"negu %[accum1], %[accum] \n\t"
"mul %[frac], %[base], %[accum1] \n\t"
"mul %[temp3], %[sum], %[x_sub] \n\t"
"lw %[base], 0(%[irow]) \n\t"
"subu %[loop_c], %[loop_c], %[x_stride] \n\t"
"sll %[accum1], %[frac], 2 \n\t"
"mult %[temp1], %[temp2] \n\t"
"madd %[accum1], %[fx_scale] \n\t"
"mfhi %[sum] \n\t"
"subu %[temp3], %[temp3], %[frac] \n\t"
"sw %[temp3], 0(%[frow]) \n\t"
"addu %[base], %[base], %[temp3] \n\t"
"sw %[base], 0(%[irow]) \n\t"
"addu %[irow], %[irow], %[x_stride1] \n\t"
"addu %[frow], %[frow], %[x_stride1] \n\t"
"bgtz %[loop_c], 1b \n\t"
: [accum] "=&r" (accum), [src1] "+r" (src1), [temp3] "=&r" (temp3),
[sum] "=&r" (sum), [base] "=&r" (base), [frac] "=&r" (frac),
[frow] "+r" (frow), [irow] "+r" (irow), [accum1] "=&r" (accum1),
[temp2] "=&r" (temp2), [temp1] "=&r" (temp1)
: [x_stride] "r" (x_stride), [fx_scale] "r" (fx_scale),
[x_sub] "r" (x_sub), [x_add] "r" (x_add),
[loop_c] "r" (loop_c), [x_stride1] "r" (x_stride1)
: "memory", "hi", "lo"
);
} else {
__asm__ volatile (
"addiu %[temp3], %[src_width], -1 \n\t"
"lbu %[temp2], 0(%[src1]) \n\t"
"addu %[src1], %[src1], %[x_stride] \n\t"
"bgtz %[temp3], 0f \n\t"
"addiu %[temp1], %[temp2], 0 \n\t"
"b 3f \n\t"
"0: \n\t"
"lbu %[temp1], 0(%[src1]) \n\t"
"3: \n\t"
"addiu %[accum], %[x_add], 0 \n\t"
"1: \n\t"
"subu %[temp3], %[temp2], %[temp1] \n\t"
"mul %[temp3], %[temp3], %[accum] \n\t"
"mul %[temp4], %[temp1], %[x_add] \n\t"
"lw %[frac], 0(%[irow]) \n\t"
"addu %[temp3], %[temp4], %[temp3] \n\t"
"sw %[temp3], 0(%[frow]) \n\t"
"addu %[frow], %[frow], %[x_stride1] \n\t"
"addu %[frac], %[frac], %[temp3] \n\t"
"addu %[x_out], %[x_out], %[x_stride] \n\t"
"sw %[frac], 0(%[irow]) \n\t"
"subu %[temp3], %[x_out], %[x_out_max] \n\t"
"addu %[irow], %[irow], %[x_stride1] \n\t"
"bgez %[temp3], 2f \n\t"
"subu %[accum], %[accum], %[x_sub] \n\t"
"bgez %[accum], 4f \n\t"
"addiu %[temp2], %[temp1], 0 \n\t"
"addu %[src1], %[src1], %[x_stride] \n\t"
"lbu %[temp1], 0(%[src1]) \n\t"
"addu %[accum], %[accum], %[x_add] \n\t"
"4: \n\t"
"b 1b \n\t"
"2: \n\t"
: [src1] "+r" (src1), [accum] "=&r" (accum), [temp1] "=&r" (temp1),
[temp2] "=&r" (temp2), [temp3] "=&r" (temp3), [temp4] "=&r" (temp4),
[x_out] "+r" (x_out), [frac] "=&r" (frac), [frow] "+r" (frow),
[irow] "+r" (irow)
: [x_stride] "r" (x_stride), [x_add] "r" (x_add), [x_sub] "r" (x_sub),
[x_stride1] "r" (x_stride1), [src_width] "r" (src_width),
[x_out_max] "r" (x_out_max)
: "memory", "hi", "lo"
);
}
}
static void ExportRow(WebPRescaler* const wrk, int x_out) { static void ExportRow(WebPRescaler* const wrk, int x_out) {
if (wrk->y_accum <= 0) { if (wrk->y_accum <= 0) {
uint8_t* const dst = wrk->dst; uint8_t* const dst = wrk->dst;
@ -86,6 +193,7 @@ static void ExportRow(WebPRescaler* const wrk, int x_out) {
extern void WebPRescalerDspInitMIPS32(void); extern void WebPRescalerDspInitMIPS32(void);
WEBP_TSAN_IGNORE_FUNCTION void WebPRescalerDspInitMIPS32(void) { WEBP_TSAN_IGNORE_FUNCTION void WebPRescalerDspInitMIPS32(void) {
WebPRescalerImportRow = ImportRow;
WebPRescalerExportRow = ExportRow; WebPRescalerExportRow = ExportRow;
} }

103
src/dsp/rescaler_mips_dsp_r2.c
View File

@ -17,6 +17,108 @@
#include "../utils/rescaler.h" #include "../utils/rescaler.h"
static void ImportRow(WebPRescaler* const wrk,
const uint8_t* const src, int channel) {
const int x_stride = wrk->num_channels;
const int x_out_max = wrk->dst_width * wrk->num_channels;
const int fx_scale = wrk->fx_scale;
const int x_add = wrk->x_add;
const int x_sub = wrk->x_sub;
const int src_width = wrk->src_width;
int* frow = wrk->frow + channel;
int* irow = wrk->irow + channel;
const uint8_t* src1 = src + channel;
int temp1, temp2, temp3, temp4;
int base, frac, sum;
int accum, accum1;
const int x_stride1 = x_stride << 2;
int loop_c = x_out_max - channel;
int x_out = channel;
if (!wrk->x_expand) {
__asm__ volatile (
"li %[sum], 0 \n\t"
"li %[accum], 0 \n\t"
"1: \n\t"
"addu %[accum], %[accum], %[x_add] \n\t"
"li %[base], 0 \n\t"
"blez %[accum], 3f \n\t"
"2: \n\t"
"lbu %[base], 0(%[src1]) \n\t"
"subu %[accum], %[accum], %[x_sub] \n\t"
"addu %[src1], %[src1], %[x_stride] \n\t"
"addu %[sum], %[sum], %[base] \n\t"
"bgtz %[accum], 2b \n\t"
"3: \n\t"
"negu %[accum1], %[accum] \n\t"
"mul %[frac], %[base], %[accum1] \n\t"
"mul %[temp3], %[sum], %[x_sub] \n\t"
"lw %[base], 0(%[irow]) \n\t"
"sll %[accum1], %[frac], 1 \n\t"
"subu %[loop_c], %[loop_c], %[x_stride] \n\t"
"mulq_rs.w %[sum], %[accum1], %[fx_scale] \n\t"
"subu %[temp3], %[temp3], %[frac] \n\t"
"sw %[temp3], 0(%[frow]) \n\t"
"addu %[base], %[base], %[temp3] \n\t"
"sw %[base], 0(%[irow]) \n\t"
"addu %[irow], %[irow], %[x_stride1] \n\t"
"addu %[frow], %[frow], %[x_stride1] \n\t"
"bgtz %[loop_c], 1b \n\t"
: [accum]"=&r"(accum), [src1]"+&r"(src1), [temp3]"=&r"(temp3),
[sum]"=&r"(sum), [base]"=&r"(base), [frac]"=&r"(frac),
[frow]"+&r"(frow), [irow]"+&r"(irow), [accum1]"=&r"(accum1),
[loop_c]"+&r"(loop_c)
: [x_stride]"r"(x_stride), [fx_scale]"r"(fx_scale), [x_sub]"r"(x_sub),
[x_add] "r" (x_add), [x_stride1] "r" (x_stride1)
: "memory", "hi", "lo"
);
} else {
__asm__ volatile (
"addiu %[temp3], %[src_width], -1 \n\t"
"lbu %[temp2], 0(%[src1]) \n\t"
"addu %[src1], %[src1], %[x_stride] \n\t"
"bgtz %[temp3], 0f \n\t"
"addiu %[temp1], %[temp2], 0 \n\t"
"b 3f \n\t"
"0: \n\t"
"lbu %[temp1], 0(%[src1]) \n\t"
"3: \n\t"
"addiu %[accum], %[x_add], 0 \n\t"
"1: \n\t"
"subu %[temp3], %[temp2], %[temp1] \n\t"
"mul %[temp3], %[temp3], %[accum] \n\t"
"mul %[temp4], %[temp1], %[x_add] \n\t"
"lw %[frac], 0(%[irow]) \n\t"
"addu %[temp3], %[temp4], %[temp3] \n\t"
"sw %[temp3], 0(%[frow]) \n\t"
"addu %[frow], %[frow], %[x_stride1] \n\t"
"addu %[frac], %[frac], %[temp3] \n\t"
"addu %[x_out], %[x_out], %[x_stride] \n\t"
"sw %[frac], 0(%[irow]) \n\t"
"subu %[temp3], %[x_out], %[x_out_max] \n\t"
"addu %[irow], %[irow], %[x_stride1] \n\t"
"bgez %[temp3], 2f \n\t"
"subu %[accum], %[accum], %[x_sub] \n\t"
"bgez %[accum], 4f \n\t"
"addiu %[temp2], %[temp1], 0 \n\t"
"addu %[src1], %[src1], %[x_stride] \n\t"
"lbu %[temp1], 0(%[src1]) \n\t"
"addu %[accum], %[accum], %[x_add] \n\t"
"4: \n\t"
"b 1b \n\t"
"2: \n\t"
: [src1] "+r" (src1), [accum] "=&r" (accum), [temp1] "=&r" (temp1),
[temp2] "=&r" (temp2), [temp3] "=&r" (temp3), [temp4] "=&r" (temp4),
[x_out] "+r" (x_out), [frac] "=&r" (frac), [frow] "+r" (frow),
[irow] "+r" (irow)
: [x_stride] "r" (x_stride), [x_add] "r" (x_add), [x_sub] "r" (x_sub),
[x_stride1] "r" (x_stride1), [src_width] "r" (src_width),
[x_out_max] "r" (x_out_max)
: "memory", "hi", "lo"
);
}
}
static void ExportRow(WebPRescaler* const wrk, int x_out) { static void ExportRow(WebPRescaler* const wrk, int x_out) {
if (wrk->y_accum <= 0) { if (wrk->y_accum <= 0) {
// if wrk->fxy_scale can fit into 32 bits use optimized code, // if wrk->fxy_scale can fit into 32 bits use optimized code,
@ -108,6 +210,7 @@ static void ExportRow(WebPRescaler* const wrk, int x_out) {
extern void WebPRescalerDspInitMIPSdspR2(void); extern void WebPRescalerDspInitMIPSdspR2(void);
WEBP_TSAN_IGNORE_FUNCTION void WebPRescalerDspInitMIPSdspR2(void) { WEBP_TSAN_IGNORE_FUNCTION void WebPRescalerDspInitMIPSdspR2(void) {
WebPRescalerImportRow = ImportRow;
WebPRescalerExportRow = ExportRow; WebPRescalerExportRow = ExportRow;
} }