dany/libwebp
1
0
Fork 0
mirror of https://github.com/webmproject/libwebp.git synced 2024-12-27 14:18:21 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

dsp/mips: add whitespace around stringizing operator

Browse Source 
fixes compile with gcc 5.1
BUG=259

Change-Id: Ideb39c6290ab8569b1b6cc835bea11c822d0286c
This commit is contained in:
James Zern 2015-09-02 23:21:13 -07:00
parent d39dc8f3cc
commit eebaf97f5a
9 changed files with 485 additions and 485 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
src/dsp/dec_mips_dsp_r2.c
View File

@ -548,10 +548,10 @@ static void SimpleVFilter16(uint8_t* p, int stride, int thresh) {
// TEMP3 = SRC[D + D1 * BPS]
#define LOAD_4_BYTES(TEMP0, TEMP1, TEMP2, TEMP3, \
A, A1, B, B1, C, C1, D, D1, SRC) \
"lbu %["#TEMP0"], "#A"+"#A1"*"XSTR(BPS)"(%["#SRC"]) \n\t" \
"lbu %["#TEMP1"], "#B"+"#B1"*"XSTR(BPS)"(%["#SRC"]) \n\t" \
"lbu %["#TEMP2"], "#C"+"#C1"*"XSTR(BPS)"(%["#SRC"]) \n\t" \
"lbu %["#TEMP3"], "#D"+"#D1"*"XSTR(BPS)"(%["#SRC"]) \n\t" \
"lbu %[" #TEMP0 "], " #A "+" #A1 "*"XSTR(BPS)"(%[" #SRC "]) \n\t" \
"lbu %[" #TEMP1 "], " #B "+" #B1 "*"XSTR(BPS)"(%[" #SRC "]) \n\t" \
"lbu %[" #TEMP2 "], " #C "+" #C1 "*"XSTR(BPS)"(%[" #SRC "]) \n\t" \
"lbu %[" #TEMP3 "], " #D "+" #D1 "*"XSTR(BPS)"(%[" #SRC "]) \n\t" \
static void SimpleHFilter16(uint8_t* p, int stride, int thresh) {
int i;
@ -623,8 +623,8 @@ static void SimpleHFilter16i(uint8_t* p, int stride, int thresh) {
// DST[A * BPS] = TEMP0
// DST[B + C * BPS] = TEMP1
#define STORE_8_BYTES(TEMP0, TEMP1, A, B, C, DST) \
"usw %["#TEMP0"], "#A"*"XSTR(BPS)"(%["#DST"]) \n\t" \
"usw %["#TEMP1"], "#B"+"#C"*"XSTR(BPS)"(%["#DST"]) \n\t"
"usw %[" #TEMP0 "], " #A "*"XSTR(BPS)"(%[" #DST "]) \n\t" \
"usw %[" #TEMP1 "], " #B "+" #C "*"XSTR(BPS)"(%[" #DST "]) \n\t"
static void VE4(uint8_t* dst) { // vertical
const uint8_t* top = dst - BPS;
@ -725,8 +725,8 @@ static void RD4(uint8_t* dst) { // Down-right
// TEMP0 = SRC[A * BPS]
// TEMP1 = SRC[B + C * BPS]
#define LOAD_8_BYTES(TEMP0, TEMP1, A, B, C, SRC) \
"ulw %["#TEMP0"], "#A"*"XSTR(BPS)"(%["#SRC"]) \n\t" \
"ulw %["#TEMP1"], "#B"+"#C"*"XSTR(BPS)"(%["#SRC"]) \n\t"
"ulw %[" #TEMP0 "], " #A "*"XSTR(BPS)"(%[" #SRC "]) \n\t" \
"ulw %[" #TEMP1 "], " #B "+" #C "*"XSTR(BPS)"(%[" #SRC "]) \n\t"
static void LD4(uint8_t* dst) { // Down-Left
int temp0, temp1, temp2, temp3, temp4;
@ -873,24 +873,24 @@ static void DC8uvNoTop(uint8_t* dst) { // DC with no top samples
#define CLIPPING(SIZE) \
"preceu.ph.qbl %[temp2], %[temp0] \n\t" \
"preceu.ph.qbr %[temp0], %[temp0] \n\t" \
".if "#SIZE" == 8 \n\t" \
".if " #SIZE " == 8 \n\t" \
"preceu.ph.qbl %[temp3], %[temp1] \n\t" \
"preceu.ph.qbr %[temp1], %[temp1] \n\t" \
".endif \n\t" \
"addu.ph %[temp2], %[temp2], %[dst_1] \n\t" \
"addu.ph %[temp0], %[temp0], %[dst_1] \n\t" \
".if "#SIZE" == 8 \n\t" \
".if " #SIZE " == 8 \n\t" \
"addu.ph %[temp3], %[temp3], %[dst_1] \n\t" \
"addu.ph %[temp1], %[temp1], %[dst_1] \n\t" \
".endif \n\t" \
"shll_s.ph %[temp2], %[temp2], 7 \n\t" \
"shll_s.ph %[temp0], %[temp0], 7 \n\t" \
".if "#SIZE" == 8 \n\t" \
".if " #SIZE " == 8 \n\t" \
"shll_s.ph %[temp3], %[temp3], 7 \n\t" \
"shll_s.ph %[temp1], %[temp1], 7 \n\t" \
".endif \n\t" \
"precrqu_s.qb.ph %[temp0], %[temp2], %[temp0] \n\t" \
".if "#SIZE" == 8 \n\t" \
".if " #SIZE " == 8 \n\t" \
"precrqu_s.qb.ph %[temp1], %[temp3], %[temp1] \n\t" \
".endif \n\t"
@ -899,7 +899,7 @@ static void DC8uvNoTop(uint8_t* dst) { // DC with no top samples
int dst_1 = ((int)(DST)[-1] << 16) + (DST)[-1]; \
int temp0, temp1, temp2, temp3; \
__asm__ volatile ( \
".if "#SIZE" < 8 \n\t" \
".if " #SIZE " < 8 \n\t" \
"ulw %[temp0], 0(%[top]) \n\t" \
"subu.ph %[dst_1], %[dst_1], %[top_1] \n\t" \
CLIPPING(4) \
@ -911,7 +911,7 @@ static void DC8uvNoTop(uint8_t* dst) { // DC with no top samples
CLIPPING(8) \
"usw %[temp0], 0(%[dst]) \n\t" \
"usw %[temp1], 4(%[dst]) \n\t" \
".if "#SIZE" == 16 \n\t" \
".if " #SIZE " == 16 \n\t" \
"ulw %[temp0], 8(%[top]) \n\t" \
"ulw %[temp1], 12(%[top]) \n\t" \
CLIPPING(8) \

314
src/dsp/enc_mips32.c
View File

@ -31,26 +31,26 @@ static const int kC2 = 35468;
// TEMP0..TEMP3 - registers for corresponding tmp elements
// TEMP4..TEMP5 - temporary registers
#define VERTICAL_PASS(A, B, C, D, TEMP4, TEMP0, TEMP1, TEMP2, TEMP3) \
"lh %[temp16], "#A"(%[temp20]) \n\t" \
"lh %[temp18], "#B"(%[temp20]) \n\t" \
"lh %[temp17], "#C"(%[temp20]) \n\t" \
"lh %[temp19], "#D"(%[temp20]) \n\t" \
"addu %["#TEMP4"], %[temp16], %[temp18] \n\t" \
"lh %[temp16], " #A "(%[temp20]) \n\t" \
"lh %[temp18], " #B "(%[temp20]) \n\t" \
"lh %[temp17], " #C "(%[temp20]) \n\t" \
"lh %[temp19], " #D "(%[temp20]) \n\t" \
"addu %[" #TEMP4 "], %[temp16], %[temp18] \n\t" \
"subu %[temp16], %[temp16], %[temp18] \n\t" \
"mul %["#TEMP0"], %[temp17], %[kC2] \n\t" \
"mul %[" #TEMP0 "], %[temp17], %[kC2] \n\t" \
"mul %[temp18], %[temp19], %[kC1] \n\t" \
"mul %[temp17], %[temp17], %[kC1] \n\t" \
"mul %[temp19], %[temp19], %[kC2] \n\t" \
"sra %["#TEMP0"], %["#TEMP0"], 16 \n\n" \
"sra %[" #TEMP0 "], %[" #TEMP0 "], 16 \n\n" \
"sra %[temp18], %[temp18], 16 \n\n" \
"sra %[temp17], %[temp17], 16 \n\n" \
"sra %[temp19], %[temp19], 16 \n\n" \
"subu %["#TEMP2"], %["#TEMP0"], %[temp18] \n\t" \
"addu %["#TEMP3"], %[temp17], %[temp19] \n\t" \
"addu %["#TEMP0"], %["#TEMP4"], %["#TEMP3"] \n\t" \
"addu %["#TEMP1"], %[temp16], %["#TEMP2"] \n\t" \
"subu %["#TEMP2"], %[temp16], %["#TEMP2"] \n\t" \
"subu %["#TEMP3"], %["#TEMP4"], %["#TEMP3"] \n\t"
"subu %[" #TEMP2 "], %[" #TEMP0 "], %[temp18] \n\t" \
"addu %[" #TEMP3 "], %[temp17], %[temp19] \n\t" \
"addu %[" #TEMP0 "], %[" #TEMP4 "], %[" #TEMP3 "] \n\t" \
"addu %[" #TEMP1 "], %[temp16], %[" #TEMP2 "] \n\t" \
"subu %[" #TEMP2 "], %[temp16], %[" #TEMP2 "] \n\t" \
"subu %[" #TEMP3 "], %[" #TEMP4 "], %[" #TEMP3 "] \n\t"
// macro for one horizontal pass in ITransformOne
// MUL and STORE macros inlined
@ -59,58 +59,58 @@ static const int kC2 = 35468;
// A - offset in bytes to load from ref and store to dst buffer
// TEMP0, TEMP4, TEMP8 and TEMP12 - registers for corresponding tmp elements
#define HORIZONTAL_PASS(A, TEMP0, TEMP4, TEMP8, TEMP12) \
"addiu %["#TEMP0"], %["#TEMP0"], 4 \n\t" \
"addu %[temp16], %["#TEMP0"], %["#TEMP8"] \n\t" \
"subu %[temp17], %["#TEMP0"], %["#TEMP8"] \n\t" \
"mul %["#TEMP0"], %["#TEMP4"], %[kC2] \n\t" \
"mul %["#TEMP8"], %["#TEMP12"], %[kC1] \n\t" \
"mul %["#TEMP4"], %["#TEMP4"], %[kC1] \n\t" \
"mul %["#TEMP12"], %["#TEMP12"], %[kC2] \n\t" \
"sra %["#TEMP0"], %["#TEMP0"], 16 \n\t" \
"sra %["#TEMP8"], %["#TEMP8"], 16 \n\t" \
"sra %["#TEMP4"], %["#TEMP4"], 16 \n\t" \
"sra %["#TEMP12"], %["#TEMP12"], 16 \n\t" \
"subu %[temp18], %["#TEMP0"], %["#TEMP8"] \n\t" \
"addu %[temp19], %["#TEMP4"], %["#TEMP12"] \n\t" \
"addu %["#TEMP0"], %[temp16], %[temp19] \n\t" \
"addu %["#TEMP4"], %[temp17], %[temp18] \n\t" \
"subu %["#TEMP8"], %[temp17], %[temp18] \n\t" \
"subu %["#TEMP12"], %[temp16], %[temp19] \n\t" \
"addiu %[" #TEMP0 "], %[" #TEMP0 "], 4 \n\t" \
"addu %[temp16], %[" #TEMP0 "], %[" #TEMP8 "] \n\t" \
"subu %[temp17], %[" #TEMP0 "], %[" #TEMP8 "] \n\t" \
"mul %[" #TEMP0 "], %[" #TEMP4 "], %[kC2] \n\t" \
"mul %[" #TEMP8 "], %[" #TEMP12 "], %[kC1] \n\t" \
"mul %[" #TEMP4 "], %[" #TEMP4 "], %[kC1] \n\t" \
"mul %[" #TEMP12 "], %[" #TEMP12 "], %[kC2] \n\t" \
"sra %[" #TEMP0 "], %[" #TEMP0 "], 16 \n\t" \
"sra %[" #TEMP8 "], %[" #TEMP8 "], 16 \n\t" \
"sra %[" #TEMP4 "], %[" #TEMP4 "], 16 \n\t" \
"sra %[" #TEMP12 "], %[" #TEMP12 "], 16 \n\t" \
"subu %[temp18], %[" #TEMP0 "], %[" #TEMP8 "] \n\t" \
"addu %[temp19], %[" #TEMP4 "], %[" #TEMP12 "] \n\t" \
"addu %[" #TEMP0 "], %[temp16], %[temp19] \n\t" \
"addu %[" #TEMP4 "], %[temp17], %[temp18] \n\t" \
"subu %[" #TEMP8 "], %[temp17], %[temp18] \n\t" \
"subu %[" #TEMP12 "], %[temp16], %[temp19] \n\t" \
"lw %[temp20], 0(%[args]) \n\t" \
"sra %["#TEMP0"], %["#TEMP0"], 3 \n\t" \
"sra %["#TEMP4"], %["#TEMP4"], 3 \n\t" \
"sra %["#TEMP8"], %["#TEMP8"], 3 \n\t" \
"sra %["#TEMP12"], %["#TEMP12"], 3 \n\t" \
"lbu %[temp16], 0+"XSTR(BPS)"*"#A"(%[temp20]) \n\t" \
"lbu %[temp17], 1+"XSTR(BPS)"*"#A"(%[temp20]) \n\t" \
"lbu %[temp18], 2+"XSTR(BPS)"*"#A"(%[temp20]) \n\t" \
"lbu %[temp19], 3+"XSTR(BPS)"*"#A"(%[temp20]) \n\t" \
"addu %["#TEMP0"], %[temp16], %["#TEMP0"] \n\t" \
"addu %["#TEMP4"], %[temp17], %["#TEMP4"] \n\t" \
"addu %["#TEMP8"], %[temp18], %["#TEMP8"] \n\t" \
"addu %["#TEMP12"], %[temp19], %["#TEMP12"] \n\t" \
"slt %[temp16], %["#TEMP0"], $zero \n\t" \
"slt %[temp17], %["#TEMP4"], $zero \n\t" \
"slt %[temp18], %["#TEMP8"], $zero \n\t" \
"slt %[temp19], %["#TEMP12"], $zero \n\t" \
"movn %["#TEMP0"], $zero, %[temp16] \n\t" \
"movn %["#TEMP4"], $zero, %[temp17] \n\t" \
"movn %["#TEMP8"], $zero, %[temp18] \n\t" \
"movn %["#TEMP12"], $zero, %[temp19] \n\t" \
"sra %[" #TEMP0 "], %[" #TEMP0 "], 3 \n\t" \
"sra %[" #TEMP4 "], %[" #TEMP4 "], 3 \n\t" \
"sra %[" #TEMP8 "], %[" #TEMP8 "], 3 \n\t" \
"sra %[" #TEMP12 "], %[" #TEMP12 "], 3 \n\t" \
"lbu %[temp16], 0+"XSTR(BPS)"*" #A "(%[temp20]) \n\t" \
"lbu %[temp17], 1+"XSTR(BPS)"*" #A "(%[temp20]) \n\t" \
"lbu %[temp18], 2+"XSTR(BPS)"*" #A "(%[temp20]) \n\t" \
"lbu %[temp19], 3+"XSTR(BPS)"*" #A "(%[temp20]) \n\t" \
"addu %[" #TEMP0 "], %[temp16], %[" #TEMP0 "] \n\t" \
"addu %[" #TEMP4 "], %[temp17], %[" #TEMP4 "] \n\t" \
"addu %[" #TEMP8 "], %[temp18], %[" #TEMP8 "] \n\t" \
"addu %[" #TEMP12 "], %[temp19], %[" #TEMP12 "] \n\t" \
"slt %[temp16], %[" #TEMP0 "], $zero \n\t" \
"slt %[temp17], %[" #TEMP4 "], $zero \n\t" \
"slt %[temp18], %[" #TEMP8 "], $zero \n\t" \
"slt %[temp19], %[" #TEMP12 "], $zero \n\t" \
"movn %[" #TEMP0 "], $zero, %[temp16] \n\t" \
"movn %[" #TEMP4 "], $zero, %[temp17] \n\t" \
"movn %[" #TEMP8 "], $zero, %[temp18] \n\t" \
"movn %[" #TEMP12 "], $zero, %[temp19] \n\t" \
"addiu %[temp20], $zero, 255 \n\t" \
"slt %[temp16], %["#TEMP0"], %[temp20] \n\t" \
"slt %[temp17], %["#TEMP4"], %[temp20] \n\t" \
"slt %[temp18], %["#TEMP8"], %[temp20] \n\t" \
"slt %[temp19], %["#TEMP12"], %[temp20] \n\t" \
"movz %["#TEMP0"], %[temp20], %[temp16] \n\t" \
"movz %["#TEMP4"], %[temp20], %[temp17] \n\t" \
"slt %[temp16], %[" #TEMP0 "], %[temp20] \n\t" \
"slt %[temp17], %[" #TEMP4 "], %[temp20] \n\t" \
"slt %[temp18], %[" #TEMP8 "], %[temp20] \n\t" \
"slt %[temp19], %[" #TEMP12 "], %[temp20] \n\t" \
"movz %[" #TEMP0 "], %[temp20], %[temp16] \n\t" \
"movz %[" #TEMP4 "], %[temp20], %[temp17] \n\t" \
"lw %[temp16], 8(%[args]) \n\t" \
"movz %["#TEMP8"], %[temp20], %[temp18] \n\t" \
"movz %["#TEMP12"], %[temp20], %[temp19] \n\t" \
"sb %["#TEMP0"], 0+"XSTR(BPS)"*"#A"(%[temp16]) \n\t" \
"sb %["#TEMP4"], 1+"XSTR(BPS)"*"#A"(%[temp16]) \n\t" \
"sb %["#TEMP8"], 2+"XSTR(BPS)"*"#A"(%[temp16]) \n\t" \
"sb %["#TEMP12"], 3+"XSTR(BPS)"*"#A"(%[temp16]) \n\t"
"movz %[" #TEMP8 "], %[temp20], %[temp18] \n\t" \
"movz %[" #TEMP12 "], %[temp20], %[temp19] \n\t" \
"sb %[" #TEMP0 "], 0+"XSTR(BPS)"*" #A "(%[temp16]) \n\t" \
"sb %[" #TEMP4 "], 1+"XSTR(BPS)"*" #A "(%[temp16]) \n\t" \
"sb %[" #TEMP8 "], 2+"XSTR(BPS)"*" #A "(%[temp16]) \n\t" \
"sb %[" #TEMP12 "], 3+"XSTR(BPS)"*" #A "(%[temp16]) \n\t"
// Does one or two inverse transforms.
static WEBP_INLINE void ITransformOne(const uint8_t* ref, const int16_t* in,
@ -161,9 +161,9 @@ static void ITransform(const uint8_t* ref, const int16_t* in,
// K - offset in bytes (kZigzag[n] * 4)
// N - offset in bytes (n * 2)
#define QUANTIZE_ONE(J, K, N) \
"lh %[temp0], "#J"(%[ppin]) \n\t" \
"lhu %[temp1], "#J"(%[ppsharpen]) \n\t" \
"lw %[temp2], "#K"(%[ppzthresh]) \n\t" \
"lh %[temp0], " #J "(%[ppin]) \n\t" \
"lhu %[temp1], " #J "(%[ppsharpen]) \n\t" \
"lw %[temp2], " #K "(%[ppzthresh]) \n\t" \
"sra %[sign], %[temp0], 15 \n\t" \
"xor %[coeff], %[temp0], %[sign] \n\t" \
"subu %[coeff], %[coeff], %[sign] \n\t" \
@ -172,9 +172,9 @@ static void ITransform(const uint8_t* ref, const int16_t* in,
"addiu %[temp5], $zero, 0 \n\t" \
"addiu %[level], $zero, 0 \n\t" \
"beqz %[temp4], 2f \n\t" \
"lhu %[temp1], "#J"(%[ppiq]) \n\t" \
"lw %[temp2], "#K"(%[ppbias]) \n\t" \
"lhu %[temp3], "#J"(%[ppq]) \n\t" \
"lhu %[temp1], " #J "(%[ppiq]) \n\t" \
"lw %[temp2], " #K "(%[ppbias]) \n\t" \
"lhu %[temp3], " #J "(%[ppq]) \n\t" \
"mul %[level], %[coeff], %[temp1] \n\t" \
"addu %[level], %[level], %[temp2] \n\t" \
"sra %[level], %[level], 17 \n\t" \
@ -184,8 +184,8 @@ static void ITransform(const uint8_t* ref, const int16_t* in,
"subu %[level], %[level], %[sign] \n\t" \
"mul %[temp5], %[level], %[temp3] \n\t" \
"2: \n\t" \
"sh %[temp5], "#J"(%[ppin]) \n\t" \
"sh %[level], "#N"(%[pout]) \n\t"
"sh %[temp5], " #J "(%[ppin]) \n\t" \
"sh %[level], " #N "(%[pout]) \n\t"
static int QuantizeBlock(int16_t in[16], int16_t out[16],
const VP8Matrix* const mtx) {
@ -254,14 +254,14 @@ static int Quantize2Blocks(int16_t in[32], int16_t out[32],
// E..H - offsets in bytes to store first results to tmp buffer
// E1..H1 - offsets in bytes to store second results to tmp buffer
#define HORIZONTAL_PASS(A, E, F, G, H, E1, F1, G1, H1) \
"lbu %[temp0], 0+"XSTR(BPS)"*"#A"(%[a]) \n\t" \
"lbu %[temp1], 1+"XSTR(BPS)"*"#A"(%[a]) \n\t" \
"lbu %[temp2], 2+"XSTR(BPS)"*"#A"(%[a]) \n\t" \
"lbu %[temp3], 3+"XSTR(BPS)"*"#A"(%[a]) \n\t" \
"lbu %[temp4], 0+"XSTR(BPS)"*"#A"(%[b]) \n\t" \
"lbu %[temp5], 1+"XSTR(BPS)"*"#A"(%[b]) \n\t" \
"lbu %[temp6], 2+"XSTR(BPS)"*"#A"(%[b]) \n\t" \
"lbu %[temp7], 3+"XSTR(BPS)"*"#A"(%[b]) \n\t" \
"lbu %[temp0], 0+"XSTR(BPS)"*" #A "(%[a]) \n\t" \
"lbu %[temp1], 1+"XSTR(BPS)"*" #A "(%[a]) \n\t" \
"lbu %[temp2], 2+"XSTR(BPS)"*" #A "(%[a]) \n\t" \
"lbu %[temp3], 3+"XSTR(BPS)"*" #A "(%[a]) \n\t" \
"lbu %[temp4], 0+"XSTR(BPS)"*" #A "(%[b]) \n\t" \
"lbu %[temp5], 1+"XSTR(BPS)"*" #A "(%[b]) \n\t" \
"lbu %[temp6], 2+"XSTR(BPS)"*" #A "(%[b]) \n\t" \
"lbu %[temp7], 3+"XSTR(BPS)"*" #A "(%[b]) \n\t" \
"addu %[temp8], %[temp0], %[temp2] \n\t" \
"subu %[temp0], %[temp0], %[temp2] \n\t" \
"addu %[temp2], %[temp1], %[temp3] \n\t" \
@ -278,14 +278,14 @@ static int Quantize2Blocks(int16_t in[32], int16_t out[32],
"subu %[temp3], %[temp3], %[temp6] \n\t" \
"addu %[temp6], %[temp4], %[temp5] \n\t" \
"subu %[temp4], %[temp4], %[temp5] \n\t" \
"sw %[temp7], "#E"(%[tmp]) \n\t" \
"sw %[temp2], "#H"(%[tmp]) \n\t" \
"sw %[temp8], "#F"(%[tmp]) \n\t" \
"sw %[temp0], "#G"(%[tmp]) \n\t" \
"sw %[temp1], "#E1"(%[tmp]) \n\t" \
"sw %[temp3], "#H1"(%[tmp]) \n\t" \
"sw %[temp6], "#F1"(%[tmp]) \n\t" \
"sw %[temp4], "#G1"(%[tmp]) \n\t"
"sw %[temp7], " #E "(%[tmp]) \n\t" \
"sw %[temp2], " #H "(%[tmp]) \n\t" \
"sw %[temp8], " #F "(%[tmp]) \n\t" \
"sw %[temp0], " #G "(%[tmp]) \n\t" \
"sw %[temp1], " #E1 "(%[tmp]) \n\t" \
"sw %[temp3], " #H1 "(%[tmp]) \n\t" \
"sw %[temp6], " #F1 "(%[tmp]) \n\t" \
"sw %[temp4], " #G1 "(%[tmp]) \n\t"
// macro for one vertical pass in Disto4x4 (TTransform)
// two calls of function TTransform are merged into single one
@ -300,10 +300,10 @@ static int Quantize2Blocks(int16_t in[32], int16_t out[32],
// A1..D1 - offsets in bytes to load second results from tmp buffer
// E..H - offsets in bytes to load from w buffer
#define VERTICAL_PASS(A, B, C, D, A1, B1, C1, D1, E, F, G, H) \
"lw %[temp0], "#A1"(%[tmp]) \n\t" \
"lw %[temp1], "#C1"(%[tmp]) \n\t" \
"lw %[temp2], "#B1"(%[tmp]) \n\t" \
"lw %[temp3], "#D1"(%[tmp]) \n\t" \
"lw %[temp0], " #A1 "(%[tmp]) \n\t" \
"lw %[temp1], " #C1 "(%[tmp]) \n\t" \
"lw %[temp2], " #B1 "(%[tmp]) \n\t" \
"lw %[temp3], " #D1 "(%[tmp]) \n\t" \
"addu %[temp8], %[temp0], %[temp1] \n\t" \
"subu %[temp0], %[temp0], %[temp1] \n\t" \
"addu %[temp1], %[temp2], %[temp3] \n\t" \
@ -324,18 +324,18 @@ static int Quantize2Blocks(int16_t in[32], int16_t out[32],
"subu %[temp1], %[temp1], %[temp5] \n\t" \
"subu %[temp0], %[temp0], %[temp6] \n\t" \
"subu %[temp8], %[temp8], %[temp7] \n\t" \
"lhu %[temp4], "#E"(%[w]) \n\t" \
"lhu %[temp5], "#F"(%[w]) \n\t" \
"lhu %[temp6], "#G"(%[w]) \n\t" \
"lhu %[temp7], "#H"(%[w]) \n\t" \
"lhu %[temp4], " #E "(%[w]) \n\t" \
"lhu %[temp5], " #F "(%[w]) \n\t" \
"lhu %[temp6], " #G "(%[w]) \n\t" \
"lhu %[temp7], " #H "(%[w]) \n\t" \
"madd %[temp4], %[temp3] \n\t" \
"madd %[temp5], %[temp1] \n\t" \
"madd %[temp6], %[temp0] \n\t" \
"madd %[temp7], %[temp8] \n\t" \
"lw %[temp0], "#A"(%[tmp]) \n\t" \
"lw %[temp1], "#C"(%[tmp]) \n\t" \
"lw %[temp2], "#B"(%[tmp]) \n\t" \
"lw %[temp3], "#D"(%[tmp]) \n\t" \
"lw %[temp0], " #A "(%[tmp]) \n\t" \
"lw %[temp1], " #C "(%[tmp]) \n\t" \
"lw %[temp2], " #B "(%[tmp]) \n\t" \
"lw %[temp3], " #D "(%[tmp]) \n\t" \
"addu %[temp8], %[temp0], %[temp1] \n\t" \
"subu %[temp0], %[temp0], %[temp1] \n\t" \
"addu %[temp1], %[temp2], %[temp3] \n\t" \
@ -413,70 +413,70 @@ static int Disto16x16(const uint8_t* const a, const uint8_t* const b,
// A - offset in bytes to load from src and ref buffers
// TEMP0..TEMP3 - registers for corresponding tmp elements
#define HORIZONTAL_PASS(A, TEMP0, TEMP1, TEMP2, TEMP3) \
"lw %["#TEMP1"], 0(%[args]) \n\t" \
"lw %["#TEMP2"], 4(%[args]) \n\t" \
"lbu %[temp16], 0+"XSTR(BPS)"*"#A"(%["#TEMP1"]) \n\t" \
"lbu %[temp17], 0+"XSTR(BPS)"*"#A"(%["#TEMP2"]) \n\t" \
"lbu %[temp18], 1+"XSTR(BPS)"*"#A"(%["#TEMP1"]) \n\t" \
"lbu %[temp19], 1+"XSTR(BPS)"*"#A"(%["#TEMP2"]) \n\t" \
"lw %[" #TEMP1 "], 0(%[args]) \n\t" \
"lw %[" #TEMP2 "], 4(%[args]) \n\t" \
"lbu %[temp16], 0+"XSTR(BPS)"*" #A "(%[" #TEMP1 "]) \n\t" \
"lbu %[temp17], 0+"XSTR(BPS)"*" #A "(%[" #TEMP2 "]) \n\t" \
"lbu %[temp18], 1+"XSTR(BPS)"*" #A "(%[" #TEMP1 "]) \n\t" \
"lbu %[temp19], 1+"XSTR(BPS)"*" #A "(%[" #TEMP2 "]) \n\t" \
"subu %[temp20], %[temp16], %[temp17] \n\t" \
"lbu %[temp16], 2+"XSTR(BPS)"*"#A"(%["#TEMP1"]) \n\t" \
"lbu %[temp17], 2+"XSTR(BPS)"*"#A"(%["#TEMP2"]) \n\t" \
"subu %["#TEMP0"], %[temp18], %[temp19] \n\t" \
"lbu %[temp18], 3+"XSTR(BPS)"*"#A"(%["#TEMP1"]) \n\t" \
"lbu %[temp19], 3+"XSTR(BPS)"*"#A"(%["#TEMP2"]) \n\t" \
"subu %["#TEMP1"], %[temp16], %[temp17] \n\t" \
"subu %["#TEMP2"], %[temp18], %[temp19] \n\t" \
"addu %["#TEMP3"], %[temp20], %["#TEMP2"] \n\t" \
"subu %["#TEMP2"], %[temp20], %["#TEMP2"] \n\t" \
"addu %[temp20], %["#TEMP0"], %["#TEMP1"] \n\t" \
"subu %["#TEMP0"], %["#TEMP0"], %["#TEMP1"] \n\t" \
"mul %[temp16], %["#TEMP2"], %[c5352] \n\t" \
"mul %[temp17], %["#TEMP2"], %[c2217] \n\t" \
"mul %[temp18], %["#TEMP0"], %[c5352] \n\t" \
"mul %[temp19], %["#TEMP0"], %[c2217] \n\t" \
"addu %["#TEMP1"], %["#TEMP3"], %[temp20] \n\t" \
"subu %[temp20], %["#TEMP3"], %[temp20] \n\t" \
"sll %["#TEMP0"], %["#TEMP1"], 3 \n\t" \
"sll %["#TEMP2"], %[temp20], 3 \n\t" \
"lbu %[temp16], 2+"XSTR(BPS)"*" #A "(%[" #TEMP1 "]) \n\t" \
"lbu %[temp17], 2+"XSTR(BPS)"*" #A "(%[" #TEMP2 "]) \n\t" \
"subu %[" #TEMP0 "], %[temp18], %[temp19] \n\t" \
"lbu %[temp18], 3+"XSTR(BPS)"*" #A "(%[" #TEMP1 "]) \n\t" \
"lbu %[temp19], 3+"XSTR(BPS)"*" #A "(%[" #TEMP2 "]) \n\t" \
"subu %[" #TEMP1 "], %[temp16], %[temp17] \n\t" \
"subu %[" #TEMP2 "], %[temp18], %[temp19] \n\t" \
"addu %[" #TEMP3 "], %[temp20], %[" #TEMP2 "] \n\t" \
"subu %[" #TEMP2 "], %[temp20], %[" #TEMP2 "] \n\t" \
"addu %[temp20], %[" #TEMP0 "], %[" #TEMP1 "] \n\t" \
"subu %[" #TEMP0 "], %[" #TEMP0 "], %[" #TEMP1 "] \n\t" \
"mul %[temp16], %[" #TEMP2 "], %[c5352] \n\t" \
"mul %[temp17], %[" #TEMP2 "], %[c2217] \n\t" \
"mul %[temp18], %[" #TEMP0 "], %[c5352] \n\t" \
"mul %[temp19], %[" #TEMP0 "], %[c2217] \n\t" \
"addu %[" #TEMP1 "], %[" #TEMP3 "], %[temp20] \n\t" \
"subu %[temp20], %[" #TEMP3 "], %[temp20] \n\t" \
"sll %[" #TEMP0 "], %[" #TEMP1 "], 3 \n\t" \
"sll %[" #TEMP2 "], %[temp20], 3 \n\t" \
"addiu %[temp16], %[temp16], 1812 \n\t" \
"addiu %[temp17], %[temp17], 937 \n\t" \
"addu %[temp16], %[temp16], %[temp19] \n\t" \
"subu %[temp17], %[temp17], %[temp18] \n\t" \
"sra %["#TEMP1"], %[temp16], 9 \n\t" \
"sra %["#TEMP3"], %[temp17], 9 \n\t"
"sra %[" #TEMP1 "], %[temp16], 9 \n\t" \
"sra %[" #TEMP3 "], %[temp17], 9 \n\t"
// macro for one vertical pass in FTransform
// temp0..temp15 holds tmp[0]..tmp[15]
// A..D - offsets in bytes to store to out buffer
// TEMP0, TEMP4, TEMP8 and TEMP12 - registers for corresponding tmp elements
#define VERTICAL_PASS(A, B, C, D, TEMP0, TEMP4, TEMP8, TEMP12) \
"addu %[temp16], %["#TEMP0"], %["#TEMP12"] \n\t" \
"subu %[temp19], %["#TEMP0"], %["#TEMP12"] \n\t" \
"addu %[temp17], %["#TEMP4"], %["#TEMP8"] \n\t" \
"subu %[temp18], %["#TEMP4"], %["#TEMP8"] \n\t" \
"mul %["#TEMP8"], %[temp19], %[c2217] \n\t" \
"mul %["#TEMP12"], %[temp18], %[c2217] \n\t" \
"mul %["#TEMP4"], %[temp19], %[c5352] \n\t" \
"addu %[temp16], %[" #TEMP0 "], %[" #TEMP12 "] \n\t" \
"subu %[temp19], %[" #TEMP0 "], %[" #TEMP12 "] \n\t" \
"addu %[temp17], %[" #TEMP4 "], %[" #TEMP8 "] \n\t" \
"subu %[temp18], %[" #TEMP4 "], %[" #TEMP8 "] \n\t" \
"mul %[" #TEMP8 "], %[temp19], %[c2217] \n\t" \
"mul %[" #TEMP12 "], %[temp18], %[c2217] \n\t" \
"mul %[" #TEMP4 "], %[temp19], %[c5352] \n\t" \
"mul %[temp18], %[temp18], %[c5352] \n\t" \
"addiu %[temp16], %[temp16], 7 \n\t" \
"addu %["#TEMP0"], %[temp16], %[temp17] \n\t" \
"sra %["#TEMP0"], %["#TEMP0"], 4 \n\t" \
"addu %["#TEMP12"], %["#TEMP12"], %["#TEMP4"] \n\t" \
"subu %["#TEMP4"], %[temp16], %[temp17] \n\t" \
"sra %["#TEMP4"], %["#TEMP4"], 4 \n\t" \
"addiu %["#TEMP8"], %["#TEMP8"], 30000 \n\t" \
"addiu %["#TEMP12"], %["#TEMP12"], 12000 \n\t" \
"addiu %["#TEMP8"], %["#TEMP8"], 21000 \n\t" \
"subu %["#TEMP8"], %["#TEMP8"], %[temp18] \n\t" \
"sra %["#TEMP12"], %["#TEMP12"], 16 \n\t" \
"sra %["#TEMP8"], %["#TEMP8"], 16 \n\t" \
"addiu %[temp16], %["#TEMP12"], 1 \n\t" \
"movn %["#TEMP12"], %[temp16], %[temp19] \n\t" \
"sh %["#TEMP0"], "#A"(%[temp20]) \n\t" \
"sh %["#TEMP4"], "#C"(%[temp20]) \n\t" \
"sh %["#TEMP8"], "#D"(%[temp20]) \n\t" \
"sh %["#TEMP12"], "#B"(%[temp20]) \n\t"
"addu %[" #TEMP0 "], %[temp16], %[temp17] \n\t" \
"sra %[" #TEMP0 "], %[" #TEMP0 "], 4 \n\t" \
"addu %[" #TEMP12 "], %[" #TEMP12 "], %[" #TEMP4 "] \n\t" \
"subu %[" #TEMP4 "], %[temp16], %[temp17] \n\t" \
"sra %[" #TEMP4 "], %[" #TEMP4 "], 4 \n\t" \
"addiu %[" #TEMP8 "], %[" #TEMP8 "], 30000 \n\t" \
"addiu %[" #TEMP12 "], %[" #TEMP12 "], 12000 \n\t" \
"addiu %[" #TEMP8 "], %[" #TEMP8 "], 21000 \n\t" \
"subu %[" #TEMP8 "], %[" #TEMP8 "], %[temp18] \n\t" \
"sra %[" #TEMP12 "], %[" #TEMP12 "], 16 \n\t" \
"sra %[" #TEMP8 "], %[" #TEMP8 "], 16 \n\t" \
"addiu %[temp16], %[" #TEMP12 "], 1 \n\t" \
"movn %[" #TEMP12 "], %[temp16], %[temp19] \n\t" \
"sh %[" #TEMP0 "], " #A "(%[temp20]) \n\t" \
"sh %[" #TEMP4 "], " #C "(%[temp20]) \n\t" \
"sh %[" #TEMP8 "], " #D "(%[temp20]) \n\t" \
"sh %[" #TEMP12 "], " #B "(%[temp20]) \n\t"
static void FTransform(const uint8_t* src, const uint8_t* ref, int16_t* out) {
int temp0, temp1, temp2, temp3, temp4, temp5, temp6, temp7, temp8;
@ -516,14 +516,14 @@ static void FTransform(const uint8_t* src, const uint8_t* ref, int16_t* out) {
#if !defined(WORK_AROUND_GCC)
#define GET_SSE_INNER(A, B, C, D) \
"lbu %[temp0], "#A"(%[a]) \n\t" \
"lbu %[temp1], "#A"(%[b]) \n\t" \
"lbu %[temp2], "#B"(%[a]) \n\t" \
"lbu %[temp3], "#B"(%[b]) \n\t" \
"lbu %[temp4], "#C"(%[a]) \n\t" \
"lbu %[temp5], "#C"(%[b]) \n\t" \
"lbu %[temp6], "#D"(%[a]) \n\t" \
"lbu %[temp7], "#D"(%[b]) \n\t" \
"lbu %[temp0], " #A "(%[a]) \n\t" \
"lbu %[temp1], " #A "(%[b]) \n\t" \
"lbu %[temp2], " #B "(%[a]) \n\t" \
"lbu %[temp3], " #B "(%[b]) \n\t" \
"lbu %[temp4], " #C "(%[a]) \n\t" \
"lbu %[temp5], " #C "(%[b]) \n\t" \
"lbu %[temp6], " #D "(%[a]) \n\t" \
"lbu %[temp7], " #D "(%[b]) \n\t" \
"subu %[temp0], %[temp0], %[temp1] \n\t" \
"subu %[temp2], %[temp2], %[temp3] \n\t" \
"subu %[temp4], %[temp4], %[temp5] \n\t" \

288
src/dsp/enc_mips_dsp_r2.c
View File

@ -27,25 +27,25 @@ static const int kC2 = 35468;
// I - input (macro doesn't change it)
#define ADD_SUB_HALVES_X4(O0, O1, O2, O3, O4, O5, O6, O7, \
I0, I1, I2, I3, I4, I5, I6, I7) \
"addq.ph %["#O0"], %["#I0"], %["#I1"] \n\t" \
"subq.ph %["#O1"], %["#I0"], %["#I1"] \n\t" \
"addq.ph %["#O2"], %["#I2"], %["#I3"] \n\t" \
"subq.ph %["#O3"], %["#I2"], %["#I3"] \n\t" \
"addq.ph %["#O4"], %["#I4"], %["#I5"] \n\t" \
"subq.ph %["#O5"], %["#I4"], %["#I5"] \n\t" \
"addq.ph %["#O6"], %["#I6"], %["#I7"] \n\t" \
"subq.ph %["#O7"], %["#I6"], %["#I7"] \n\t"
"addq.ph %[" #O0 "], %[" #I0 "], %[" #I1 "] \n\t" \
"subq.ph %[" #O1 "], %[" #I0 "], %[" #I1 "] \n\t" \
"addq.ph %[" #O2 "], %[" #I2 "], %[" #I3 "] \n\t" \
"subq.ph %[" #O3 "], %[" #I2 "], %[" #I3 "] \n\t" \
"addq.ph %[" #O4 "], %[" #I4 "], %[" #I5 "] \n\t" \
"subq.ph %[" #O5 "], %[" #I4 "], %[" #I5 "] \n\t" \
"addq.ph %[" #O6 "], %[" #I6 "], %[" #I7 "] \n\t" \
"subq.ph %[" #O7 "], %[" #I6 "], %[" #I7 "] \n\t"
// IO - input/output
#define ABS_X8(IO0, IO1, IO2, IO3, IO4, IO5, IO6, IO7) \
"absq_s.ph %["#IO0"], %["#IO0"] \n\t" \
"absq_s.ph %["#IO1"], %["#IO1"] \n\t" \
"absq_s.ph %["#IO2"], %["#IO2"] \n\t" \
"absq_s.ph %["#IO3"], %["#IO3"] \n\t" \
"absq_s.ph %["#IO4"], %["#IO4"] \n\t" \
"absq_s.ph %["#IO5"], %["#IO5"] \n\t" \
"absq_s.ph %["#IO6"], %["#IO6"] \n\t" \
"absq_s.ph %["#IO7"], %["#IO7"] \n\t"
"absq_s.ph %[" #IO0 "], %[" #IO0 "] \n\t" \
"absq_s.ph %[" #IO1 "], %[" #IO1 "] \n\t" \
"absq_s.ph %[" #IO2 "], %[" #IO2 "] \n\t" \
"absq_s.ph %[" #IO3 "], %[" #IO3 "] \n\t" \
"absq_s.ph %[" #IO4 "], %[" #IO4 "] \n\t" \
"absq_s.ph %[" #IO5 "], %[" #IO5 "] \n\t" \
"absq_s.ph %[" #IO6 "], %[" #IO6 "] \n\t" \
"absq_s.ph %[" #IO7 "], %[" #IO7 "] \n\t"
// dpa.w.ph $ac0 temp0 ,temp1
// $ac += temp0[31..16] * temp1[31..16] + temp0[15..0] * temp1[15..0]
@ -56,15 +56,15 @@ static const int kC2 = 35468;
#define MUL_HALF(O0, I0, I1, I2, I3, I4, I5, I6, I7, \
I8, I9, I10, I11, I12, I13, I14, I15) \
"mult $ac0, $zero, $zero \n\t" \
"dpa.w.ph $ac0, %["#I2"], %["#I0"] \n\t" \
"dpax.w.ph $ac0, %["#I5"], %["#I6"] \n\t" \
"dpa.w.ph $ac0, %["#I8"], %["#I9"] \n\t" \
"dpax.w.ph $ac0, %["#I11"], %["#I4"] \n\t" \
"dpa.w.ph $ac0, %["#I12"], %["#I7"] \n\t" \
"dpax.w.ph $ac0, %["#I13"], %["#I1"] \n\t" \
"dpa.w.ph $ac0, %["#I14"], %["#I3"] \n\t" \
"dpax.w.ph $ac0, %["#I15"], %["#I10"] \n\t" \
"mflo %["#O0"], $ac0 \n\t"
"dpa.w.ph $ac0, %[" #I2 "], %[" #I0 "] \n\t" \
"dpax.w.ph $ac0, %[" #I5 "], %[" #I6 "] \n\t" \
"dpa.w.ph $ac0, %[" #I8 "], %[" #I9 "] \n\t" \
"dpax.w.ph $ac0, %[" #I11 "], %[" #I4 "] \n\t" \
"dpa.w.ph $ac0, %[" #I12 "], %[" #I7 "] \n\t" \
"dpax.w.ph $ac0, %[" #I13 "], %[" #I1 "] \n\t" \
"dpa.w.ph $ac0, %[" #I14 "], %[" #I3 "] \n\t" \
"dpax.w.ph $ac0, %[" #I15 "], %[" #I10 "] \n\t" \
"mflo %[" #O0 "], $ac0 \n\t"
#define OUTPUT_EARLY_CLOBBER_REGS_17() \
OUTPUT_EARLY_CLOBBER_REGS_10(), \
@ -77,69 +77,69 @@ static const int kC2 = 35468;
// A - offset in bytes to load from src and ref buffers
// TEMP0..TEMP3 - registers for corresponding tmp elements
#define HORIZONTAL_PASS(A, TEMP0, TEMP1, TEMP2, TEMP3) \
"lw %["#TEMP0"], 0(%[args]) \n\t" \
"lw %["#TEMP1"], 4(%[args]) \n\t" \
"lw %["#TEMP2"], "XSTR(BPS)"*"#A"(%["#TEMP0"]) \n\t" \
"lw %["#TEMP3"], "XSTR(BPS)"*"#A"(%["#TEMP1"]) \n\t" \
"preceu.ph.qbl %["#TEMP0"], %["#TEMP2"] \n\t" \
"preceu.ph.qbl %["#TEMP1"], %["#TEMP3"] \n\t" \
"preceu.ph.qbr %["#TEMP2"], %["#TEMP2"] \n\t" \
"preceu.ph.qbr %["#TEMP3"], %["#TEMP3"] \n\t" \
"subq.ph %["#TEMP0"], %["#TEMP0"], %["#TEMP1"] \n\t" \
"subq.ph %["#TEMP2"], %["#TEMP2"], %["#TEMP3"] \n\t" \
"rotr %["#TEMP0"], %["#TEMP0"], 16 \n\t" \
"addq.ph %["#TEMP1"], %["#TEMP2"], %["#TEMP0"] \n\t" \
"subq.ph %["#TEMP3"], %["#TEMP2"], %["#TEMP0"] \n\t" \
"seh %["#TEMP0"], %["#TEMP1"] \n\t" \
"sra %[temp16], %["#TEMP1"], 16 \n\t" \
"seh %[temp19], %["#TEMP3"] \n\t" \
"sra %["#TEMP3"], %["#TEMP3"], 16 \n\t" \
"subu %["#TEMP2"], %["#TEMP0"], %[temp16] \n\t" \
"addu %["#TEMP0"], %["#TEMP0"], %[temp16] \n\t" \
"lw %[" #TEMP0 "], 0(%[args]) \n\t" \
"lw %[" #TEMP1 "], 4(%[args]) \n\t" \
"lw %[" #TEMP2 "], "XSTR(BPS)"*" #A "(%[" #TEMP0 "]) \n\t" \
"lw %[" #TEMP3 "], "XSTR(BPS)"*" #A "(%[" #TEMP1 "]) \n\t" \
"preceu.ph.qbl %[" #TEMP0 "], %[" #TEMP2 "] \n\t" \
"preceu.ph.qbl %[" #TEMP1 "], %[" #TEMP3 "] \n\t" \
"preceu.ph.qbr %[" #TEMP2 "], %[" #TEMP2 "] \n\t" \
"preceu.ph.qbr %[" #TEMP3 "], %[" #TEMP3 "] \n\t" \
"subq.ph %[" #TEMP0 "], %[" #TEMP0 "], %[" #TEMP1 "] \n\t" \
"subq.ph %[" #TEMP2 "], %[" #TEMP2 "], %[" #TEMP3 "] \n\t" \
"rotr %[" #TEMP0 "], %[" #TEMP0 "], 16 \n\t" \
"addq.ph %[" #TEMP1 "], %[" #TEMP2 "], %[" #TEMP0 "] \n\t" \
"subq.ph %[" #TEMP3 "], %[" #TEMP2 "], %[" #TEMP0 "] \n\t" \
"seh %[" #TEMP0 "], %[" #TEMP1 "] \n\t" \
"sra %[temp16], %[" #TEMP1 "], 16 \n\t" \
"seh %[temp19], %[" #TEMP3 "] \n\t" \
"sra %[" #TEMP3 "], %[" #TEMP3 "], 16 \n\t" \
"subu %[" #TEMP2 "], %[" #TEMP0 "], %[temp16] \n\t" \
"addu %[" #TEMP0 "], %[" #TEMP0 "], %[temp16] \n\t" \
"mul %[temp17], %[temp19], %[c2217] \n\t" \
"mul %[temp18], %["#TEMP3"], %[c5352] \n\t" \
"mul %["#TEMP1"], %[temp19], %[c5352] \n\t" \
"mul %[temp16], %["#TEMP3"], %[c2217] \n\t" \
"sll %["#TEMP2"], %["#TEMP2"], 3 \n\t" \
"sll %["#TEMP0"], %["#TEMP0"], 3 \n\t" \
"subu %["#TEMP3"], %[temp17], %[temp18] \n\t" \
"addu %["#TEMP1"], %[temp16], %["#TEMP1"] \n\t" \
"addiu %["#TEMP3"], %["#TEMP3"], 937 \n\t" \
"addiu %["#TEMP1"], %["#TEMP1"], 1812 \n\t" \
"sra %["#TEMP3"], %["#TEMP3"], 9 \n\t" \
"sra %["#TEMP1"], %["#TEMP1"], 9 \n\t"
"mul %[temp18], %[" #TEMP3 "], %[c5352] \n\t" \
"mul %[" #TEMP1 "], %[temp19], %[c5352] \n\t" \
"mul %[temp16], %[" #TEMP3 "], %[c2217] \n\t" \
"sll %[" #TEMP2 "], %[" #TEMP2 "], 3 \n\t" \
"sll %[" #TEMP0 "], %[" #TEMP0 "], 3 \n\t" \
"subu %[" #TEMP3 "], %[temp17], %[temp18] \n\t" \
"addu %[" #TEMP1 "], %[temp16], %[" #TEMP1 "] \n\t" \
"addiu %[" #TEMP3 "], %[" #TEMP3 "], 937 \n\t" \
"addiu %[" #TEMP1 "], %[" #TEMP1 "], 1812 \n\t" \
"sra %[" #TEMP3 "], %[" #TEMP3 "], 9 \n\t" \
"sra %[" #TEMP1 "], %[" #TEMP1 "], 9 \n\t"
// macro for one vertical pass in FTransform
// temp0..temp15 holds tmp[0]..tmp[15]
// A..D - offsets in bytes to store to out buffer
// TEMP0, TEMP4, TEMP8 and TEMP12 - registers for corresponding tmp elements
#define VERTICAL_PASS(A, B, C, D, TEMP0, TEMP4, TEMP8, TEMP12) \
"addu %[temp16], %["#TEMP0"], %["#TEMP12"] \n\t" \
"subu %[temp19], %["#TEMP0"], %["#TEMP12"] \n\t" \
"addu %[temp17], %["#TEMP4"], %["#TEMP8"] \n\t" \
"subu %[temp18], %["#TEMP4"], %["#TEMP8"] \n\t" \
"mul %["#TEMP8"], %[temp19], %[c2217] \n\t" \
"mul %["#TEMP12"], %[temp18], %[c2217] \n\t" \
"mul %["#TEMP4"], %[temp19], %[c5352] \n\t" \
"addu %[temp16], %[" #TEMP0 "], %[" #TEMP12 "] \n\t" \
"subu %[temp19], %[" #TEMP0 "], %[" #TEMP12 "] \n\t" \
"addu %[temp17], %[" #TEMP4 "], %[" #TEMP8 "] \n\t" \
"subu %[temp18], %[" #TEMP4 "], %[" #TEMP8 "] \n\t" \
"mul %[" #TEMP8 "], %[temp19], %[c2217] \n\t" \
"mul %[" #TEMP12 "], %[temp18], %[c2217] \n\t" \
"mul %[" #TEMP4 "], %[temp19], %[c5352] \n\t" \
"mul %[temp18], %[temp18], %[c5352] \n\t" \
"addiu %[temp16], %[temp16], 7 \n\t" \
"addu %["#TEMP0"], %[temp16], %[temp17] \n\t" \
"sra %["#TEMP0"], %["#TEMP0"], 4 \n\t" \
"addu %["#TEMP12"], %["#TEMP12"], %["#TEMP4"] \n\t" \
"subu %["#TEMP4"], %[temp16], %[temp17] \n\t" \
"sra %["#TEMP4"], %["#TEMP4"], 4 \n\t" \
"addiu %["#TEMP8"], %["#TEMP8"], 30000 \n\t" \
"addiu %["#TEMP12"], %["#TEMP12"], 12000 \n\t" \
"addiu %["#TEMP8"], %["#TEMP8"], 21000 \n\t" \
"subu %["#TEMP8"], %["#TEMP8"], %[temp18] \n\t" \
"sra %["#TEMP12"], %["#TEMP12"], 16 \n\t" \
"sra %["#TEMP8"], %["#TEMP8"], 16 \n\t" \
"addiu %[temp16], %["#TEMP12"], 1 \n\t" \
"movn %["#TEMP12"], %[temp16], %[temp19] \n\t" \
"sh %["#TEMP0"], "#A"(%[temp20]) \n\t" \
"sh %["#TEMP4"], "#C"(%[temp20]) \n\t" \
"sh %["#TEMP8"], "#D"(%[temp20]) \n\t" \
"sh %["#TEMP12"], "#B"(%[temp20]) \n\t"
"addu %[" #TEMP0 "], %[temp16], %[temp17] \n\t" \
"sra %[" #TEMP0 "], %[" #TEMP0 "], 4 \n\t" \
"addu %[" #TEMP12 "], %[" #TEMP12 "], %[" #TEMP4 "] \n\t" \
"subu %[" #TEMP4 "], %[temp16], %[temp17] \n\t" \
"sra %[" #TEMP4 "], %[" #TEMP4 "], 4 \n\t" \
"addiu %[" #TEMP8 "], %[" #TEMP8 "], 30000 \n\t" \
"addiu %[" #TEMP12 "], %[" #TEMP12 "], 12000 \n\t" \
"addiu %[" #TEMP8 "], %[" #TEMP8 "], 21000 \n\t" \
"subu %[" #TEMP8 "], %[" #TEMP8 "], %[temp18] \n\t" \
"sra %[" #TEMP12 "], %[" #TEMP12 "], 16 \n\t" \
"sra %[" #TEMP8 "], %[" #TEMP8 "], 16 \n\t" \
"addiu %[temp16], %[" #TEMP12 "], 1 \n\t" \
"movn %[" #TEMP12 "], %[temp16], %[temp19] \n\t" \
"sh %[" #TEMP0 "], " #A "(%[temp20]) \n\t" \
"sh %[" #TEMP4 "], " #C "(%[temp20]) \n\t" \
"sh %[" #TEMP8 "], " #D "(%[temp20]) \n\t" \
"sh %[" #TEMP12 "], " #B "(%[temp20]) \n\t"
static void FTransform(const uint8_t* src, const uint8_t* ref, int16_t* out) {
const int c2217 = 2217;
@ -329,11 +329,11 @@ static int Disto16x16(const uint8_t* const a, const uint8_t* const b,
// Intra predictions
#define FILL_PART(J, SIZE) \
"usw %[value], 0+"#J"*"XSTR(BPS)"(%[dst]) \n\t" \
"usw %[value], 4+"#J"*"XSTR(BPS)"(%[dst]) \n\t" \
".if "#SIZE" == 16 \n\t" \
"usw %[value], 8+"#J"*"XSTR(BPS)"(%[dst]) \n\t" \
"usw %[value], 12+"#J"*"XSTR(BPS)"(%[dst]) \n\t" \
"usw %[value], 0+" #J "*"XSTR(BPS)"(%[dst]) \n\t" \
"usw %[value], 4+" #J "*"XSTR(BPS)"(%[dst]) \n\t" \
".if " #SIZE " == 16 \n\t" \
"usw %[value], 8+" #J "*"XSTR(BPS)"(%[dst]) \n\t" \
"usw %[value], 12+" #J "*"XSTR(BPS)"(%[dst]) \n\t" \
".endif \n\t"
#define FILL_8_OR_16(DST, VALUE, SIZE) do { \
@ -348,7 +348,7 @@ static int Disto16x16(const uint8_t* const a, const uint8_t* const b,
FILL_PART( 5, SIZE) \
FILL_PART( 6, SIZE) \
FILL_PART( 7, SIZE) \
".if "#SIZE" == 16 \n\t" \
".if " #SIZE " == 16 \n\t" \
FILL_PART( 8, 16) \
FILL_PART( 9, 16) \
FILL_PART(10, 16) \
@ -425,7 +425,7 @@ HORIZONTAL_PRED(dst, left, 16)
CLIPPING() \
"usw %[temp0], 0(%[dst]) \n\t" \
"usw %[temp1], 4(%[dst]) \n\t" \
".if "#SIZE" == 16 \n\t" \
".if " #SIZE " == 16 \n\t" \
"ulw %[temp0], 8(%[top]) \n\t" \
"ulw %[temp1], 12(%[top]) \n\t" \
CLIPPING() \
@ -1060,8 +1060,8 @@ static void Intra4Preds(uint8_t* dst, const uint8_t* top) {
#if !defined(WORK_AROUND_GCC)
#define GET_SSE_INNER(A) \
"lw %[temp0], "#A"(%[a]) \n\t" \
"lw %[temp1], "#A"(%[b]) \n\t" \
"lw %[temp0], " #A "(%[a]) \n\t" \
"lw %[temp1], " #A "(%[b]) \n\t" \
"preceu.ph.qbr %[temp2], %[temp0] \n\t" \
"preceu.ph.qbl %[temp0], %[temp0] \n\t" \
"preceu.ph.qbr %[temp3], %[temp1] \n\t" \
@ -1185,28 +1185,28 @@ static int SSE4x4(const uint8_t* a, const uint8_t* b) {
// N - offset in bytes (n * 2)
// N1 - offset in bytes ((n + 1) * 2)
#define QUANTIZE_ONE(J, K, N, N1) \
"ulw %[temp1], "#J"(%[ppin]) \n\t" \
"ulw %[temp2], "#J"(%[ppsharpen]) \n\t" \
"lhu %[temp3], "#K"(%[ppzthresh]) \n\t" \
"lhu %[temp6], "#K"+4(%[ppzthresh]) \n\t" \
"ulw %[temp1], " #J "(%[ppin]) \n\t" \
"ulw %[temp2], " #J "(%[ppsharpen]) \n\t" \
"lhu %[temp3], " #K "(%[ppzthresh]) \n\t" \
"lhu %[temp6], " #K "+4(%[ppzthresh]) \n\t" \
"absq_s.ph %[temp4], %[temp1] \n\t" \
"ins %[temp3], %[temp6], 16, 16 \n\t" \
"addu.ph %[coeff], %[temp4], %[temp2] \n\t" \
"shra.ph %[sign], %[temp1], 15 \n\t" \
"li %[level], 0x10001 \n\t" \
"cmp.lt.ph %[temp3], %[coeff] \n\t" \
"lhu %[temp1], "#J"(%[ppiq]) \n\t" \
"lhu %[temp1], " #J "(%[ppiq]) \n\t" \
"pick.ph %[temp5], %[level], $0 \n\t" \
"lw %[temp2], "#K"(%[ppbias]) \n\t" \
"lw %[temp2], " #K "(%[ppbias]) \n\t" \
"beqz %[temp5], 0f \n\t" \
"lhu %[temp3], "#J"(%[ppq]) \n\t" \
"lhu %[temp3], " #J "(%[ppq]) \n\t" \
"beq %[temp5], %[level], 1f \n\t" \
"andi %[temp5], %[temp5], 0x1 \n\t" \
"andi %[temp4], %[coeff], 0xffff \n\t" \
"beqz %[temp5], 2f \n\t" \
"mul %[level], %[temp4], %[temp1] \n\t" \
"sh $0, "#J"+2(%[ppin]) \n\t" \
"sh $0, "#N1"(%[pout]) \n\t" \
"sh $0, " #J "+2(%[ppin]) \n\t" \
"sh $0, " #N1 "(%[pout]) \n\t" \
"addu %[level], %[level], %[temp2] \n\t" \
"sra %[level], %[level], 17 \n\t" \
"slt %[temp4], %[max_level], %[level] \n\t" \
@ -1216,15 +1216,15 @@ static int SSE4x4(const uint8_t* a, const uint8_t* b) {
"subu %[level], %[level], %[temp6] \n\t" \
"mul %[temp5], %[level], %[temp3] \n\t" \
"or %[ret], %[ret], %[level] \n\t" \
"sh %[level], "#N"(%[pout]) \n\t" \
"sh %[temp5], "#J"(%[ppin]) \n\t" \
"sh %[level], " #N "(%[pout]) \n\t" \
"sh %[temp5], " #J "(%[ppin]) \n\t" \
"j 3f \n\t" \
"2: \n\t" \
"lhu %[temp1], "#J"+2(%[ppiq]) \n\t" \
"lhu %[temp1], " #J "+2(%[ppiq]) \n\t" \
"srl %[temp5], %[coeff], 16 \n\t" \
"mul %[level], %[temp5], %[temp1] \n\t" \
"lw %[temp2], "#K"+4(%[ppbias]) \n\t" \
"lhu %[temp3], "#J"+2(%[ppq]) \n\t" \
"lw %[temp2], " #K "+4(%[ppbias]) \n\t" \
"lhu %[temp3], " #J "+2(%[ppq]) \n\t" \
"addu %[level], %[level], %[temp2] \n\t" \
"sra %[level], %[level], 17 \n\t" \
"srl %[temp6], %[sign], 16 \n\t" \
@ -1233,20 +1233,20 @@ static int SSE4x4(const uint8_t* a, const uint8_t* b) {
"xor %[level], %[level], %[temp6] \n\t" \
"subu %[level], %[level], %[temp6] \n\t" \
"mul %[temp5], %[level], %[temp3] \n\t" \
"sh $0, "#J"(%[ppin]) \n\t" \
"sh $0, "#N"(%[pout]) \n\t" \
"sh $0, " #J "(%[ppin]) \n\t" \
"sh $0, " #N "(%[pout]) \n\t" \
"or %[ret], %[ret], %[level] \n\t" \
"sh %[temp5], "#J"+2(%[ppin]) \n\t" \
"sh %[level], "#N1"(%[pout]) \n\t" \
"sh %[temp5], " #J "+2(%[ppin]) \n\t" \
"sh %[level], " #N1 "(%[pout]) \n\t" \
"j 3f \n\t" \
"1: \n\t" \
"lhu %[temp1], "#J"(%[ppiq]) \n\t" \
"lw %[temp2], "#K"(%[ppbias]) \n\t" \
"ulw %[temp3], "#J"(%[ppq]) \n\t" \
"lhu %[temp1], " #J "(%[ppiq]) \n\t" \
"lw %[temp2], " #K "(%[ppbias]) \n\t" \
"ulw %[temp3], " #J "(%[ppq]) \n\t" \
"andi %[temp5], %[coeff], 0xffff \n\t" \
"srl %[temp0], %[coeff], 16 \n\t" \
"lhu %[temp6], "#J"+2(%[ppiq]) \n\t" \
"lw %[coeff], "#K"+4(%[ppbias]) \n\t" \
"lhu %[temp6], " #J "+2(%[ppiq]) \n\t" \
"lw %[coeff], " #K "+4(%[ppbias]) \n\t" \
"mul %[level], %[temp5], %[temp1] \n\t" \
"mul %[temp4], %[temp0], %[temp6] \n\t" \
"addu %[level], %[level], %[temp2] \n\t" \
@ -1259,15 +1259,15 @@ static int SSE4x4(const uint8_t* a, const uint8_t* b) {
"subu.ph %[level], %[level], %[sign] \n\t" \
"mul.ph %[temp3], %[level], %[temp3] \n\t" \
"or %[ret], %[ret], %[level] \n\t" \
"sh %[level], "#N"(%[pout]) \n\t" \
"sh %[level], " #N "(%[pout]) \n\t" \
"srl %[level], %[level], 16 \n\t" \
"sh %[level], "#N1"(%[pout]) \n\t" \
"usw %[temp3], "#J"(%[ppin]) \n\t" \
"sh %[level], " #N1 "(%[pout]) \n\t" \
"usw %[temp3], " #J "(%[ppin]) \n\t" \
"j 3f \n\t" \
"0: \n\t" \
"sh $0, "#N"(%[pout]) \n\t" \
"sh $0, "#N1"(%[pout]) \n\t" \
"usw $0, "#J"(%[ppin]) \n\t" \
"sh $0, " #N "(%[pout]) \n\t" \
"sh $0, " #N1 "(%[pout]) \n\t" \
"usw $0, " #J "(%[ppin]) \n\t" \
"3: \n\t"
static int QuantizeBlock(int16_t in[16], int16_t out[16],
@ -1326,37 +1326,37 @@ static int Quantize2Blocks(int16_t in[32], int16_t out[32],
// A, B, C, D - offset in bytes to load from in buffer
// TEMP0, TEMP1 - registers for corresponding tmp elements
#define HORIZONTAL_PASS_WHT(A, B, C, D, TEMP0, TEMP1) \
"lh %["#TEMP0"], "#A"(%[in]) \n\t" \
"lh %["#TEMP1"], "#B"(%[in]) \n\t" \
"lh %[temp8], "#C"(%[in]) \n\t" \
"lh %[temp9], "#D"(%[in]) \n\t" \
"ins %["#TEMP1"], %["#TEMP0"], 16, 16 \n\t" \
"lh %[" #TEMP0 "], " #A "(%[in]) \n\t" \
"lh %[" #TEMP1 "], " #B "(%[in]) \n\t" \
"lh %[temp8], " #C "(%[in]) \n\t" \
"lh %[temp9], " #D "(%[in]) \n\t" \
"ins %[" #TEMP1 "], %[" #TEMP0 "], 16, 16 \n\t" \
"ins %[temp9], %[temp8], 16, 16 \n\t" \
"subq.ph %[temp8], %["#TEMP1"], %[temp9] \n\t" \
"addq.ph %[temp9], %["#TEMP1"], %[temp9] \n\t" \
"precrq.ph.w %["#TEMP0"], %[temp8], %[temp9] \n\t" \
"subq.ph %[temp8], %[" #TEMP1 "], %[temp9] \n\t" \
"addq.ph %[temp9], %[" #TEMP1 "], %[temp9] \n\t" \
"precrq.ph.w %[" #TEMP0 "], %[temp8], %[temp9] \n\t" \
"append %[temp8], %[temp9], 16 \n\t" \
"subq.ph %["#TEMP1"], %["#TEMP0"], %[temp8] \n\t" \
"addq.ph %["#TEMP0"], %["#TEMP0"], %[temp8] \n\t" \
"rotr %["#TEMP1"], %["#TEMP1"], 16 \n\t"
"subq.ph %[" #TEMP1 "], %[" #TEMP0 "], %[temp8] \n\t" \
"addq.ph %[" #TEMP0 "], %[" #TEMP0 "], %[temp8] \n\t" \
"rotr %[" #TEMP1 "], %[" #TEMP1 "], 16 \n\t"
// macro for one vertical pass in FTransformWHT
// temp0..temp7 holds tmp[0]..tmp[15]
// A, B, C, D - offsets in bytes to store to out buffer
// TEMP0, TEMP2, TEMP4 and TEMP6 - registers for corresponding tmp elements
#define VERTICAL_PASS_WHT(A, B, C, D, TEMP0, TEMP2, TEMP4, TEMP6) \
"addq.ph %[temp8], %["#TEMP0"], %["#TEMP4"] \n\t" \
"addq.ph %[temp9], %["#TEMP2"], %["#TEMP6"] \n\t" \
"subq.ph %["#TEMP2"], %["#TEMP2"], %["#TEMP6"] \n\t" \
"subq.ph %["#TEMP6"], %["#TEMP0"], %["#TEMP4"] \n\t" \
"addqh.ph %["#TEMP0"], %[temp8], %[temp9] \n\t" \
"subqh.ph %["#TEMP4"], %["#TEMP6"], %["#TEMP2"] \n\t" \
"addqh.ph %["#TEMP2"], %["#TEMP2"], %["#TEMP6"] \n\t" \
"subqh.ph %["#TEMP6"], %[temp8], %[temp9] \n\t" \
"usw %["#TEMP0"], "#A"(%[out]) \n\t" \
"usw %["#TEMP2"], "#B"(%[out]) \n\t" \
"usw %["#TEMP4"], "#C"(%[out]) \n\t" \
"usw %["#TEMP6"], "#D"(%[out]) \n\t"
"addq.ph %[temp8], %[" #TEMP0 "], %[" #TEMP4 "] \n\t" \
"addq.ph %[temp9], %[" #TEMP2 "], %[" #TEMP6 "] \n\t" \
"subq.ph %[" #TEMP2 "], %[" #TEMP2 "], %[" #TEMP6 "] \n\t" \
"subq.ph %[" #TEMP6 "], %[" #TEMP0 "], %[" #TEMP4 "] \n\t" \
"addqh.ph %[" #TEMP0 "], %[temp8], %[temp9] \n\t" \
"subqh.ph %[" #TEMP4 "], %[" #TEMP6 "], %[" #TEMP2 "] \n\t" \
"addqh.ph %[" #TEMP2 "], %[" #TEMP2 "], %[" #TEMP6 "] \n\t" \
"subqh.ph %[" #TEMP6 "], %[temp8], %[temp9] \n\t" \
"usw %[" #TEMP0 "], " #A "(%[out]) \n\t" \
"usw %[" #TEMP2 "], " #B "(%[out]) \n\t" \
"usw %[" #TEMP4 "], " #C "(%[out]) \n\t" \
"usw %[" #TEMP6 "], " #D "(%[out]) \n\t"
static void FTransformWHT(const int16_t* in, int16_t* out) {
int temp0, temp1, temp2, temp3, temp4;
@ -1385,10 +1385,10 @@ static void FTransformWHT(const int16_t* in, int16_t* out) {
// convert 8 coeffs at time
// A, B, C, D - offsets in bytes to load from out buffer
#define CONVERT_COEFFS_TO_BIN(A, B, C, D) \
"ulw %[temp0], "#A"(%[out]) \n\t" \
"ulw %[temp1], "#B"(%[out]) \n\t" \
"ulw %[temp2], "#C"(%[out]) \n\t" \
"ulw %[temp3], "#D"(%[out]) \n\t" \
"ulw %[temp0], " #A "(%[out]) \n\t" \
"ulw %[temp1], " #B "(%[out]) \n\t" \
"ulw %[temp2], " #C "(%[out]) \n\t" \
"ulw %[temp3], " #D "(%[out]) \n\t" \
"absq_s.ph %[temp0], %[temp0] \n\t" \
"absq_s.ph %[temp1], %[temp1] \n\t" \
"absq_s.ph %[temp2], %[temp2] \n\t" \

10
src/dsp/filters_mips_dsp_r2.c
View File

@ -48,7 +48,7 @@
"srl %[temp0], %[length], 0x2 \n\t" \
"beqz %[temp0], 4f \n\t" \
" andi %[temp6], %[length], 0x3 \n\t" \
".if "#INVERSE" \n\t" \
".if " #INVERSE " \n\t" \
"lbu %[temp1], -1(%[src]) \n\t" \
"1: \n\t" \
"lbu %[temp2], 0(%[src]) \n\t" \
@ -84,7 +84,7 @@
"lbu %[temp1], -1(%[src]) \n\t" \
"lbu %[temp2], 0(%[src]) \n\t" \
"addiu %[src], %[src], 1 \n\t" \
".if "#INVERSE" \n\t" \
".if " #INVERSE " \n\t" \
"addu %[temp3], %[temp1], %[temp2] \n\t" \
"sb %[temp3], -1(%[src]) \n\t" \
".else \n\t" \
@ -131,7 +131,7 @@ static WEBP_INLINE void PredictLine(const uint8_t* src, uint8_t* dst,
"ulw %[temp3], 4(%[src]) \n\t" \
"ulw %[temp4], 4(%[pred]) \n\t" \
"addiu %[src], %[src], 8 \n\t" \
".if "#INVERSE" \n\t" \
".if " #INVERSE " \n\t" \
"addu.qb %[temp5], %[temp1], %[temp2] \n\t" \
"addu.qb %[temp6], %[temp3], %[temp4] \n\t" \
".else \n\t" \
@ -152,7 +152,7 @@ static WEBP_INLINE void PredictLine(const uint8_t* src, uint8_t* dst,
"lbu %[temp2], 0(%[pred]) \n\t" \
"addiu %[src], %[src], 1 \n\t" \
"addiu %[pred], %[pred], 1 \n\t" \
".if "#INVERSE" \n\t" \
".if " #INVERSE " \n\t" \
"addu %[temp3], %[temp1], %[temp2] \n\t" \
".else \n\t" \
"subu %[temp3], %[temp1], %[temp2] \n\t" \
@ -177,7 +177,7 @@ static WEBP_INLINE void PredictLine(const uint8_t* src, uint8_t* dst,
__asm__ volatile ( \
"lbu %[temp1], 0(%[src]) \n\t" \
"lbu %[temp2], 0(%[pred]) \n\t" \
".if "#INVERSE" \n\t" \
".if " #INVERSE " \n\t" \
"addu %[temp3], %[temp1], %[temp2] \n\t" \
".else \n\t" \
"subu %[temp3], %[temp1], %[temp2] \n\t" \

34
src/dsp/lossless_enc_mips32.c
View File

@ -278,28 +278,28 @@ static VP8LStreaks HuffmanCostCombinedCount(const uint32_t* X,
// literal_ and successive histograms could be unaligned
// so we must use ulw and usw
#define ADD_TO_OUT(A, B, C, D, E, P0, P1, P2) \
"ulw %[temp0], "#A"(%["#P0"]) \n\t" \
"ulw %[temp1], "#B"(%["#P0"]) \n\t" \
"ulw %[temp2], "#C"(%["#P0"]) \n\t" \
"ulw %[temp3], "#D"(%["#P0"]) \n\t" \
"ulw %[temp4], "#A"(%["#P1"]) \n\t" \
"ulw %[temp5], "#B"(%["#P1"]) \n\t" \
"ulw %[temp6], "#C"(%["#P1"]) \n\t" \
"ulw %[temp7], "#D"(%["#P1"]) \n\t" \
"ulw %[temp0], " #A "(%[" #P0 "]) \n\t" \
"ulw %[temp1], " #B "(%[" #P0 "]) \n\t" \
"ulw %[temp2], " #C "(%[" #P0 "]) \n\t" \
"ulw %[temp3], " #D "(%[" #P0 "]) \n\t" \
"ulw %[temp4], " #A "(%[" #P1 "]) \n\t" \
"ulw %[temp5], " #B "(%[" #P1 "]) \n\t" \
"ulw %[temp6], " #C "(%[" #P1 "]) \n\t" \
"ulw %[temp7], " #D "(%[" #P1 "]) \n\t" \
"addu %[temp4], %[temp4], %[temp0] \n\t" \
"addu %[temp5], %[temp5], %[temp1] \n\t" \
"addu %[temp6], %[temp6], %[temp2] \n\t" \
"addu %[temp7], %[temp7], %[temp3] \n\t" \
"addiu %["#P0"], %["#P0"], 16 \n\t" \
".if "#E" == 1 \n\t" \
"addiu %["#P1"], %["#P1"], 16 \n\t" \
"addiu %[" #P0 "], %[" #P0 "], 16 \n\t" \
".if " #E " == 1 \n\t" \
"addiu %[" #P1 "], %[" #P1 "], 16 \n\t" \
".endif \n\t" \
"usw %[temp4], "#A"(%["#P2"]) \n\t" \
"usw %[temp5], "#B"(%["#P2"]) \n\t" \
"usw %[temp6], "#C"(%["#P2"]) \n\t" \
"usw %[temp7], "#D"(%["#P2"]) \n\t" \
"addiu %["#P2"], %["#P2"], 16 \n\t" \
"bne %["#P0"], %[LoopEnd], 1b \n\t" \
"usw %[temp4], " #A "(%[" #P2 "]) \n\t" \
"usw %[temp5], " #B "(%[" #P2 "]) \n\t" \
"usw %[temp6], " #C "(%[" #P2 "]) \n\t" \
"usw %[temp7], " #D "(%[" #P2 "]) \n\t" \
"addiu %[" #P2 "], %[" #P2 "], 16 \n\t" \
"bne %[" #P0 "], %[LoopEnd], 1b \n\t" \
".set pop \n\t" \
#define ASM_END_COMMON_0 \

8
src/dsp/lossless_mips_dsp_r2.c
View File

@ -29,14 +29,14 @@ static void FUNC_NAME(const TYPE* src, \
for (x = 0; x < (width >> 2); ++x) { \
int tmp1, tmp2, tmp3, tmp4; \
__asm__ volatile ( \
".ifc "#TYPE", uint8_t \n\t" \
".ifc " #TYPE ", uint8_t \n\t" \
"lbu %[tmp1], 0(%[src]) \n\t" \
"lbu %[tmp2], 1(%[src]) \n\t" \
"lbu %[tmp3], 2(%[src]) \n\t" \
"lbu %[tmp4], 3(%[src]) \n\t" \
"addiu %[src], %[src], 4 \n\t" \
".endif \n\t" \
".ifc "#TYPE", uint32_t \n\t" \
".ifc " #TYPE ", uint32_t \n\t" \
"lw %[tmp1], 0(%[src]) \n\t" \
"lw %[tmp2], 4(%[src]) \n\t" \
"lw %[tmp3], 8(%[src]) \n\t" \
@ -55,7 +55,7 @@ static void FUNC_NAME(const TYPE* src, \
"lwx %[tmp2], %[tmp2](%[color_map]) \n\t" \
"lwx %[tmp3], %[tmp3](%[color_map]) \n\t" \
"lwx %[tmp4], %[tmp4](%[color_map]) \n\t" \
".ifc "#TYPE", uint8_t \n\t" \
".ifc " #TYPE ", uint8_t \n\t" \
"ext %[tmp1], %[tmp1], 8, 8 \n\t" \
"ext %[tmp2], %[tmp2], 8, 8 \n\t" \
"ext %[tmp3], %[tmp3], 8, 8 \n\t" \
@ -66,7 +66,7 @@ static void FUNC_NAME(const TYPE* src, \
"sb %[tmp4], 3(%[dst]) \n\t" \
"addiu %[dst], %[dst], 4 \n\t" \
".endif \n\t" \
".ifc "#TYPE", uint32_t \n\t" \
".ifc " #TYPE ", uint32_t \n\t" \
"sw %[tmp1], 0(%[dst]) \n\t" \
"sw %[tmp2], 4(%[dst]) \n\t" \
"sw %[tmp3], 8(%[dst]) \n\t" \

180
src/dsp/mips_macro.h
View File

@ -25,25 +25,25 @@
// I - input (macro doesn't change it)
#define ADD_SUB_HALVES(O0, O1, \
I0, I1) \
"addq.ph %["#O0"], %["#I0"], %["#I1"] \n\t" \
"subq.ph %["#O1"], %["#I0"], %["#I1"] \n\t"
"addq.ph %[" #O0 "], %[" #I0 "], %[" #I1 "] \n\t" \
"subq.ph %[" #O1 "], %[" #I0 "], %[" #I1 "] \n\t"
// O - output
// I - input (macro doesn't change it)
// I[0/1] - offset in bytes
#define LOAD_IN_X2(O0, O1, \
I0, I1) \
"lh %["#O0"], "#I0"(%[in]) \n\t" \
"lh %["#O1"], "#I1"(%[in]) \n\t"
"lh %[" #O0 "], " #I0 "(%[in]) \n\t" \
"lh %[" #O1 "], " #I1 "(%[in]) \n\t"
// I0 - location
// I1..I9 - offsets in bytes
#define LOAD_WITH_OFFSET_X4(O0, O1, O2, O3, \
I0, I1, I2, I3, I4, I5, I6, I7, I8, I9) \
"ulw %["#O0"], "#I1"+"XSTR(I9)"*"#I5"(%["#I0"]) \n\t" \
"ulw %["#O1"], "#I2"+"XSTR(I9)"*"#I6"(%["#I0"]) \n\t" \
"ulw %["#O2"], "#I3"+"XSTR(I9)"*"#I7"(%["#I0"]) \n\t" \
"ulw %["#O3"], "#I4"+"XSTR(I9)"*"#I8"(%["#I0"]) \n\t"
"ulw %[" #O0 "], " #I1 "+"XSTR(I9)"*" #I5 "(%[" #I0 "]) \n\t" \
"ulw %[" #O1 "], " #I2 "+"XSTR(I9)"*" #I6 "(%[" #I0 "]) \n\t" \
"ulw %[" #O2 "], " #I3 "+"XSTR(I9)"*" #I7 "(%[" #I0 "]) \n\t" \
"ulw %[" #O3 "], " #I4 "+"XSTR(I9)"*" #I8 "(%[" #I0 "]) \n\t"
// O - output
// IO - input/output
@ -51,42 +51,42 @@
#define MUL_SHIFT_SUM(O0, O1, O2, O3, O4, O5, O6, O7, \
IO0, IO1, IO2, IO3, \
I0, I1, I2, I3, I4, I5, I6, I7) \
"mul %["#O0"], %["#I0"], %[kC2] \n\t" \
"mul %["#O1"], %["#I0"], %[kC1] \n\t" \
"mul %["#O2"], %["#I1"], %[kC2] \n\t" \
"mul %["#O3"], %["#I1"], %[kC1] \n\t" \
"mul %["#O4"], %["#I2"], %[kC2] \n\t" \
"mul %["#O5"], %["#I2"], %[kC1] \n\t" \
"mul %["#O6"], %["#I3"], %[kC2] \n\t" \
"mul %["#O7"], %["#I3"], %[kC1] \n\t" \
"sra %["#O0"], %["#O0"], 16 \n\t" \
"sra %["#O1"], %["#O1"], 16 \n\t" \
"sra %["#O2"], %["#O2"], 16 \n\t" \
"sra %["#O3"], %["#O3"], 16 \n\t" \
"sra %["#O4"], %["#O4"], 16 \n\t" \
"sra %["#O5"], %["#O5"], 16 \n\t" \
"sra %["#O6"], %["#O6"], 16 \n\t" \
"sra %["#O7"], %["#O7"], 16 \n\t" \
"addu %["#IO0"], %["#IO0"], %["#I4"] \n\t" \
"addu %["#IO1"], %["#IO1"], %["#I5"] \n\t" \
"subu %["#IO2"], %["#IO2"], %["#I6"] \n\t" \
"subu %["#IO3"], %["#IO3"], %["#I7"] \n\t"
"mul %[" #O0 "], %[" #I0 "], %[kC2] \n\t" \
"mul %[" #O1 "], %[" #I0 "], %[kC1] \n\t" \
"mul %[" #O2 "], %[" #I1 "], %[kC2] \n\t" \
"mul %[" #O3 "], %[" #I1 "], %[kC1] \n\t" \
"mul %[" #O4 "], %[" #I2 "], %[kC2] \n\t" \
"mul %[" #O5 "], %[" #I2 "], %[kC1] \n\t" \
"mul %[" #O6 "], %[" #I3 "], %[kC2] \n\t" \
"mul %[" #O7 "], %[" #I3 "], %[kC1] \n\t" \
"sra %[" #O0 "], %[" #O0 "], 16 \n\t" \
"sra %[" #O1 "], %[" #O1 "], 16 \n\t" \
"sra %[" #O2 "], %[" #O2 "], 16 \n\t" \
"sra %[" #O3 "], %[" #O3 "], 16 \n\t" \
"sra %[" #O4 "], %[" #O4 "], 16 \n\t" \
"sra %[" #O5 "], %[" #O5 "], 16 \n\t" \
"sra %[" #O6 "], %[" #O6 "], 16 \n\t" \
"sra %[" #O7 "], %[" #O7 "], 16 \n\t" \
"addu %[" #IO0 "], %[" #IO0 "], %[" #I4 "] \n\t" \
"addu %[" #IO1 "], %[" #IO1 "], %[" #I5 "] \n\t" \
"subu %[" #IO2 "], %[" #IO2 "], %[" #I6 "] \n\t" \
"subu %[" #IO3 "], %[" #IO3 "], %[" #I7 "] \n\t"
// O - output
// I - input (macro doesn't change it)
#define INSERT_HALF_X2(O0, O1, \
I0, I1) \
"ins %["#O0"], %["#I0"], 16, 16 \n\t" \
"ins %["#O1"], %["#I1"], 16, 16 \n\t"
"ins %[" #O0 "], %[" #I0 "], 16, 16 \n\t" \
"ins %[" #O1 "], %[" #I1 "], 16, 16 \n\t"
// O - output
// I - input (macro doesn't change it)
#define SRA_16(O0, O1, O2, O3, \
I0, I1, I2, I3) \
"sra %["#O0"], %["#I0"], 16 \n\t" \
"sra %["#O1"], %["#I1"], 16 \n\t" \
"sra %["#O2"], %["#I2"], 16 \n\t" \
"sra %["#O3"], %["#I3"], 16 \n\t"
"sra %[" #O0 "], %[" #I0 "], 16 \n\t" \
"sra %[" #O1 "], %[" #I1 "], 16 \n\t" \
"sra %[" #O2 "], %[" #I2 "], 16 \n\t" \
"sra %[" #O3 "], %[" #I3 "], 16 \n\t"
// temp0[31..16 | 15..0] = temp8[31..16 | 15..0] + temp12[31..16 | 15..0]
// temp1[31..16 | 15..0] = temp8[31..16 | 15..0] - temp12[31..16 | 15..0]
@ -96,22 +96,22 @@
// I - input (macro doesn't change it)
#define SHIFT_R_SUM_X2(O0, O1, O2, O3, O4, O5, O6, O7, \
I0, I1, I2, I3, I4, I5, I6, I7) \
"addq.ph %["#O0"], %["#I0"], %["#I4"] \n\t" \
"subq.ph %["#O1"], %["#I0"], %["#I4"] \n\t" \
"addq.ph %["#O2"], %["#I1"], %["#I5"] \n\t" \
"subq.ph %["#O3"], %["#I1"], %["#I5"] \n\t" \
"addq.ph %["#O4"], %["#I2"], %["#I6"] \n\t" \
"subq.ph %["#O5"], %["#I2"], %["#I6"] \n\t" \
"addq.ph %["#O6"], %["#I3"], %["#I7"] \n\t" \
"subq.ph %["#O7"], %["#I3"], %["#I7"] \n\t" \
"shra.ph %["#O0"], %["#O0"], 3 \n\t" \
"shra.ph %["#O1"], %["#O1"], 3 \n\t" \
"shra.ph %["#O2"], %["#O2"], 3 \n\t" \
"shra.ph %["#O3"], %["#O3"], 3 \n\t" \
"shra.ph %["#O4"], %["#O4"], 3 \n\t" \
"shra.ph %["#O5"], %["#O5"], 3 \n\t" \
"shra.ph %["#O6"], %["#O6"], 3 \n\t" \
"shra.ph %["#O7"], %["#O7"], 3 \n\t"
"addq.ph %[" #O0 "], %[" #I0 "], %[" #I4 "] \n\t" \
"subq.ph %[" #O1 "], %[" #I0 "], %[" #I4 "] \n\t" \
"addq.ph %[" #O2 "], %[" #I1 "], %[" #I5 "] \n\t" \
"subq.ph %[" #O3 "], %[" #I1 "], %[" #I5 "] \n\t" \
"addq.ph %[" #O4 "], %[" #I2 "], %[" #I6 "] \n\t" \
"subq.ph %[" #O5 "], %[" #I2 "], %[" #I6 "] \n\t" \
"addq.ph %[" #O6 "], %[" #I3 "], %[" #I7 "] \n\t" \
"subq.ph %[" #O7 "], %[" #I3 "], %[" #I7 "] \n\t" \
"shra.ph %[" #O0 "], %[" #O0 "], 3 \n\t" \
"shra.ph %[" #O1 "], %[" #O1 "], 3 \n\t" \
"shra.ph %[" #O2 "], %[" #O2 "], 3 \n\t" \
"shra.ph %[" #O3 "], %[" #O3 "], 3 \n\t" \
"shra.ph %[" #O4 "], %[" #O4 "], 3 \n\t" \
"shra.ph %[" #O5 "], %[" #O5 "], 3 \n\t" \
"shra.ph %[" #O6 "], %[" #O6 "], 3 \n\t" \
"shra.ph %[" #O7 "], %[" #O7 "], 3 \n\t"
// precrq.ph.w temp0, temp8, temp2
// temp0 = temp8[31..16] | temp2[31..16]
@ -123,14 +123,14 @@
#define PACK_2_HALVES_TO_WORD(O0, O1, O2, O3, \
IO0, IO1, IO2, IO3, \
I0, I1, I2, I3) \
"precrq.ph.w %["#O0"], %["#I0"], %["#IO0"] \n\t" \
"precrq.ph.w %["#O1"], %["#I1"], %["#IO1"] \n\t" \
"ins %["#IO0"], %["#I0"], 16, 16 \n\t" \
"ins %["#IO1"], %["#I1"], 16, 16 \n\t" \
"precrq.ph.w %["#O2"], %["#I2"], %["#IO2"] \n\t" \
"precrq.ph.w %["#O3"], %["#I3"], %["#IO3"] \n\t" \
"ins %["#IO2"], %["#I2"], 16, 16 \n\t" \
"ins %["#IO3"], %["#I3"], 16, 16 \n\t"
"precrq.ph.w %[" #O0 "], %[" #I0 "], %[" #IO0 "] \n\t" \
"precrq.ph.w %[" #O1 "], %[" #I1 "], %[" #IO1 "] \n\t" \
"ins %[" #IO0 "], %[" #I0 "], 16, 16 \n\t" \
"ins %[" #IO1 "], %[" #I1 "], 16, 16 \n\t" \
"precrq.ph.w %[" #O2 "], %[" #I2 "], %[" #IO2 "] \n\t" \
"precrq.ph.w %[" #O3 "], %[" #I3 "], %[" #IO3 "] \n\t" \
"ins %[" #IO2 "], %[" #I2 "], 16, 16 \n\t" \
"ins %[" #IO3 "], %[" #I3 "], 16, 16 \n\t"
// preceu.ph.qbr temp0, temp8
// temp0 = 0 | 0 | temp8[23..16] | temp8[7..0]
@ -140,14 +140,14 @@
// I - input (macro doesn't change it)
#define CONVERT_2_BYTES_TO_HALF(O0, O1, O2, O3, O4, O5, O6, O7, \
I0, I1, I2, I3) \
"preceu.ph.qbr %["#O0"], %["#I0"] \n\t" \
"preceu.ph.qbl %["#O1"], %["#I0"] \n\t" \
"preceu.ph.qbr %["#O2"], %["#I1"] \n\t" \
"preceu.ph.qbl %["#O3"], %["#I1"] \n\t" \
"preceu.ph.qbr %["#O4"], %["#I2"] \n\t" \
"preceu.ph.qbl %["#O5"], %["#I2"] \n\t" \
"preceu.ph.qbr %["#O6"], %["#I3"] \n\t" \
"preceu.ph.qbl %["#O7"], %["#I3"] \n\t"
"preceu.ph.qbr %[" #O0 "], %[" #I0 "] \n\t" \
"preceu.ph.qbl %[" #O1 "], %[" #I0 "] \n\t" \
"preceu.ph.qbr %[" #O2 "], %[" #I1 "] \n\t" \
"preceu.ph.qbl %[" #O3 "], %[" #I1 "] \n\t" \
"preceu.ph.qbr %[" #O4 "], %[" #I2 "] \n\t" \
"preceu.ph.qbl %[" #O5 "], %[" #I2 "] \n\t" \
"preceu.ph.qbr %[" #O6 "], %[" #I3 "] \n\t" \
"preceu.ph.qbl %[" #O7 "], %[" #I3 "] \n\t"
// temp0[31..16 | 15..0] = temp0[31..16 | 15..0] + temp8[31..16 | 15..0]
// temp0[31..16 | 15..0] = temp0[31..16 <<(s) 7 | 15..0 <<(s) 7]
@ -160,30 +160,30 @@
#define STORE_SAT_SUM_X2(IO0, IO1, IO2, IO3, IO4, IO5, IO6, IO7, \
I0, I1, I2, I3, I4, I5, I6, I7, \
I8, I9, I10, I11, I12, I13) \
"addq.ph %["#IO0"], %["#IO0"], %["#I0"] \n\t" \
"addq.ph %["#IO1"], %["#IO1"], %["#I1"] \n\t" \
"addq.ph %["#IO2"], %["#IO2"], %["#I2"] \n\t" \
"addq.ph %["#IO3"], %["#IO3"], %["#I3"] \n\t" \
"addq.ph %["#IO4"], %["#IO4"], %["#I4"] \n\t" \
"addq.ph %["#IO5"], %["#IO5"], %["#I5"] \n\t" \
"addq.ph %["#IO6"], %["#IO6"], %["#I6"] \n\t" \
"addq.ph %["#IO7"], %["#IO7"], %["#I7"] \n\t" \
"shll_s.ph %["#IO0"], %["#IO0"], 7 \n\t" \
"shll_s.ph %["#IO1"], %["#IO1"], 7 \n\t" \
"shll_s.ph %["#IO2"], %["#IO2"], 7 \n\t" \
"shll_s.ph %["#IO3"], %["#IO3"], 7 \n\t" \
"shll_s.ph %["#IO4"], %["#IO4"], 7 \n\t" \
"shll_s.ph %["#IO5"], %["#IO5"], 7 \n\t" \
"shll_s.ph %["#IO6"], %["#IO6"], 7 \n\t" \
"shll_s.ph %["#IO7"], %["#IO7"], 7 \n\t" \
"precrqu_s.qb.ph %["#IO0"], %["#IO1"], %["#IO0"] \n\t" \
"precrqu_s.qb.ph %["#IO2"], %["#IO3"], %["#IO2"] \n\t" \
"precrqu_s.qb.ph %["#IO4"], %["#IO5"], %["#IO4"] \n\t" \
"precrqu_s.qb.ph %["#IO6"], %["#IO7"], %["#IO6"] \n\t" \
"usw %["#IO0"], "XSTR(I13)"*"#I9"(%["#I8"]) \n\t" \
"usw %["#IO2"], "XSTR(I13)"*"#I10"(%["#I8"]) \n\t" \
"usw %["#IO4"], "XSTR(I13)"*"#I11"(%["#I8"]) \n\t" \
"usw %["#IO6"], "XSTR(I13)"*"#I12"(%["#I8"]) \n\t"
"addq.ph %[" #IO0 "], %[" #IO0 "], %[" #I0 "] \n\t" \
"addq.ph %[" #IO1 "], %[" #IO1 "], %[" #I1 "] \n\t" \
"addq.ph %[" #IO2 "], %[" #IO2 "], %[" #I2 "] \n\t" \
"addq.ph %[" #IO3 "], %[" #IO3 "], %[" #I3 "] \n\t" \
"addq.ph %[" #IO4 "], %[" #IO4 "], %[" #I4 "] \n\t" \
"addq.ph %[" #IO5 "], %[" #IO5 "], %[" #I5 "] \n\t" \
"addq.ph %[" #IO6 "], %[" #IO6 "], %[" #I6 "] \n\t" \
"addq.ph %[" #IO7 "], %[" #IO7 "], %[" #I7 "] \n\t" \
"shll_s.ph %[" #IO0 "], %[" #IO0 "], 7 \n\t" \
"shll_s.ph %[" #IO1 "], %[" #IO1 "], 7 \n\t" \
"shll_s.ph %[" #IO2 "], %[" #IO2 "], 7 \n\t" \
"shll_s.ph %[" #IO3 "], %[" #IO3 "], 7 \n\t" \
"shll_s.ph %[" #IO4 "], %[" #IO4 "], 7 \n\t" \
"shll_s.ph %[" #IO5 "], %[" #IO5 "], 7 \n\t" \
"shll_s.ph %[" #IO6 "], %[" #IO6 "], 7 \n\t" \
"shll_s.ph %[" #IO7 "], %[" #IO7 "], 7 \n\t" \
"precrqu_s.qb.ph %[" #IO0 "], %[" #IO1 "], %[" #IO0 "] \n\t" \
"precrqu_s.qb.ph %[" #IO2 "], %[" #IO3 "], %[" #IO2 "] \n\t" \
"precrqu_s.qb.ph %[" #IO4 "], %[" #IO5 "], %[" #IO4 "] \n\t" \
"precrqu_s.qb.ph %[" #IO6 "], %[" #IO7 "], %[" #IO6 "] \n\t" \
"usw %[" #IO0 "], "XSTR(I13)"*" #I9 "(%[" #I8 "]) \n\t" \
"usw %[" #IO2 "], "XSTR(I13)"*" #I10 "(%[" #I8 "]) \n\t" \
"usw %[" #IO4 "], "XSTR(I13)"*" #I11 "(%[" #I8 "]) \n\t" \
"usw %[" #IO6 "], "XSTR(I13)"*" #I12 "(%[" #I8 "]) \n\t"
#define OUTPUT_EARLY_CLOBBER_REGS_10() \
: [temp1]"=&r"(temp1), [temp2]"=&r"(temp2), [temp3]"=&r"(temp3), \

18
src/dsp/upsampling_mips_dsp_r2.c
View File

@ -34,15 +34,15 @@
G = G - t2 + kGCst; \
B = B + kBCst; \
__asm__ volatile ( \
"shll_s.w %["#R"], %["#R"], 9 \n\t" \
"shll_s.w %["#G"], %["#G"], 9 \n\t" \
"shll_s.w %["#B"], %["#B"], 9 \n\t" \
"precrqu_s.qb.ph %["#R"], %["#R"], $zero \n\t" \
"precrqu_s.qb.ph %["#G"], %["#G"], $zero \n\t" \
"precrqu_s.qb.ph %["#B"], %["#B"], $zero \n\t" \
"srl %["#R"], %["#R"], 24 \n\t" \
"srl %["#G"], %["#G"], 24 \n\t" \
"srl %["#B"], %["#B"], 24 \n\t" \
"shll_s.w %[" #R "], %[" #R "], 9 \n\t" \
"shll_s.w %[" #G "], %[" #G "], 9 \n\t" \
"shll_s.w %[" #B "], %[" #B "], 9 \n\t" \
"precrqu_s.qb.ph %[" #R "], %[" #R "], $zero \n\t" \
"precrqu_s.qb.ph %[" #G "], %[" #G "], $zero \n\t" \
"precrqu_s.qb.ph %[" #B "], %[" #B "], $zero \n\t" \
"srl %[" #R "], %[" #R "], 24 \n\t" \
"srl %[" #G "], %[" #G "], 24 \n\t" \
"srl %[" #B "], %[" #B "], 24 \n\t" \
: [R]"+r"(R), [G]"+r"(G), [B]"+r"(B) \
: \
); \

10
src/dsp/yuv_mips_dsp_r2.c
View File

@ -39,12 +39,12 @@
"addu %[temp5], %[temp0], %[temp1] \n\t" \
"subu %[temp6], %[temp0], %[temp2] \n\t" \
"addu %[temp7], %[temp0], %[temp4] \n\t" \
".if "#K" \n\t" \
".if " #K " \n\t" \
"lbu %[temp0], 1(%[y]) \n\t" \
".endif \n\t" \
"shll_s.w %[temp5], %[temp5], 9 \n\t" \
"shll_s.w %[temp6], %[temp6], 9 \n\t" \
".if "#K" \n\t" \
".if " #K " \n\t" \
"mul %[temp0], %[t_con_5], %[temp0] \n\t" \
".endif \n\t" \
"shll_s.w %[temp7], %[temp7], 9 \n\t" \
@ -54,9 +54,9 @@
"srl %[temp5], %[temp5], 24 \n\t" \
"srl %[temp6], %[temp6], 24 \n\t" \
"srl %[temp7], %[temp7], 24 \n\t" \
"sb %[temp5], "#R"(%[dst]) \n\t" \
"sb %[temp6], "#G"(%[dst]) \n\t" \
"sb %[temp7], "#B"(%[dst]) \n\t" \
"sb %[temp5], " #R "(%[dst]) \n\t" \
"sb %[temp6], " #G "(%[dst]) \n\t" \
"sb %[temp7], " #B "(%[dst]) \n\t" \
#define ASM_CLOBBER_LIST() \
: [temp0]"=&r"(temp0), [temp1]"=&r"(temp1), [temp2]"=&r"(temp2), \