summaryrefslogtreecommitdiffstats
path: root/src/3rdparty/libwebp/src/dsp/enc_mips32.c
diff options
context:
space:
mode:
authorLiang Qi <liang.qi@theqtcompany.com>2015-12-08 09:06:25 +0100
committerLiang Qi <liang.qi@theqtcompany.com>2015-12-08 20:43:30 +0000
commitfa4ed3621c9e50441b98e6c52c9bbe3ad9438248 (patch)
tree33a5739b577def87b5ec563f3dd7a9f0132431ad /src/3rdparty/libwebp/src/dsp/enc_mips32.c
parent531c30ea66d2b8fe517c89bed149a938e16332ec (diff)
libwebp: update to 0.4.4
This commit imports libwebp 0.4.4, including AUTHORS, COPYING, ChangeLog, NEWS, PATENTS, README and src directories. In src, only includes header and source files. The patches required to build it in Qt will follow in separate commit(s). Change-Id: Ib12593f56553e5358548c224d1855273f3fd2318 Reviewed-by: Lars Knoll <lars.knoll@theqtcompany.com> Reviewed-by: aavit <eirik.aavitsland@theqtcompany.com>
Diffstat (limited to 'src/3rdparty/libwebp/src/dsp/enc_mips32.c')
-rw-r--r--src/3rdparty/libwebp/src/dsp/enc_mips32.c354
1 files changed, 177 insertions, 177 deletions
diff --git a/src/3rdparty/libwebp/src/dsp/enc_mips32.c b/src/3rdparty/libwebp/src/dsp/enc_mips32.c
index def9a16..6cede18 100644
--- a/src/3rdparty/libwebp/src/dsp/enc_mips32.c
+++ b/src/3rdparty/libwebp/src/dsp/enc_mips32.c
@@ -34,26 +34,26 @@ 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" \
- "subu %[temp16], %[temp16], %[temp18] \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 %[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"
+ "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 %[temp18], %[temp19], %[kC1] \n\t" \
+ "mul %[temp17], %[temp17], %[kC1] \n\t" \
+ "mul %[temp19], %[temp19], %[kC2] \n\t" \
+ "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"
// macro for one horizontal pass in ITransformOne
// MUL and STORE macros inlined
@@ -61,59 +61,59 @@ static const int kC2 = 35468;
// temp0..temp15 holds tmp[0]..tmp[15]
// A..D - offsets 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, B, C, D, 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" \
- "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], "#A"(%[temp20]) \n\t" \
- "lbu %[temp17], "#B"(%[temp20]) \n\t" \
- "lbu %[temp18], "#C"(%[temp20]) \n\t" \
- "lbu %[temp19], "#D"(%[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" \
- "lw %[temp16], 8(%[args]) \n\t" \
- "movz %["#TEMP8"], %[temp20], %[temp18] \n\t" \
- "movz %["#TEMP12"], %[temp20], %[temp19] \n\t" \
- "sb %["#TEMP0"], "#A"(%[temp16]) \n\t" \
- "sb %["#TEMP4"], "#B"(%[temp16]) \n\t" \
- "sb %["#TEMP8"], "#C"(%[temp16]) \n\t" \
- "sb %["#TEMP12"], "#D"(%[temp16]) \n\t"
+#define HORIZONTAL_PASS(A, B, C, D, 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" \
+ "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], " #A "(%[temp20]) \n\t" \
+ "lbu %[temp17], " #B "(%[temp20]) \n\t" \
+ "lbu %[temp18], " #C "(%[temp20]) \n\t" \
+ "lbu %[temp19], " #D "(%[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" \
+ "lw %[temp16], 8(%[args]) \n\t" \
+ "movz %[" #TEMP8 "], %[temp20], %[temp18] \n\t" \
+ "movz %[" #TEMP12 "], %[temp20], %[temp19] \n\t" \
+ "sb %[" #TEMP0 "], " #A "(%[temp16]) \n\t" \
+ "sb %[" #TEMP4 "], " #B "(%[temp16]) \n\t" \
+ "sb %[" #TEMP8 "], " #C "(%[temp16]) \n\t" \
+ "sb %[" #TEMP12 "], " #D "(%[temp16]) \n\t"
// Does one or two inverse transforms.
static WEBP_INLINE void ITransformOne(const uint8_t* ref, const int16_t* in,
@@ -164,9 +164,9 @@ 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" \
@@ -175,9 +175,9 @@ 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" \
@@ -187,8 +187,8 @@ 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) {
@@ -249,14 +249,14 @@ static int QuantizeBlock(int16_t in[16], int16_t out[16],
// 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, B, C, D, E, F, G, H, E1, F1, G1, H1) \
- "lbu %[temp0], "#A"(%[a]) \n\t" \
- "lbu %[temp1], "#B"(%[a]) \n\t" \
- "lbu %[temp2], "#C"(%[a]) \n\t" \
- "lbu %[temp3], "#D"(%[a]) \n\t" \
- "lbu %[temp4], "#A"(%[b]) \n\t" \
- "lbu %[temp5], "#B"(%[b]) \n\t" \
- "lbu %[temp6], "#C"(%[b]) \n\t" \
- "lbu %[temp7], "#D"(%[b]) \n\t" \
+ "lbu %[temp0], " #A "(%[a]) \n\t" \
+ "lbu %[temp1], " #B "(%[a]) \n\t" \
+ "lbu %[temp2], " #C "(%[a]) \n\t" \
+ "lbu %[temp3], " #D "(%[a]) \n\t" \
+ "lbu %[temp4], " #A "(%[b]) \n\t" \
+ "lbu %[temp5], " #B "(%[b]) \n\t" \
+ "lbu %[temp6], " #C "(%[b]) \n\t" \
+ "lbu %[temp7], " #D "(%[b]) \n\t" \
"addu %[temp8], %[temp0], %[temp2] \n\t" \
"subu %[temp0], %[temp0], %[temp2] \n\t" \
"addu %[temp2], %[temp1], %[temp3] \n\t" \
@@ -273,14 +273,14 @@ static int QuantizeBlock(int16_t in[16], int16_t out[16],
"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
@@ -295,10 +295,10 @@ static int QuantizeBlock(int16_t in[16], int16_t out[16],
// 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" \
@@ -319,18 +319,18 @@ static int QuantizeBlock(int16_t in[16], int16_t out[16],
"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" \
@@ -407,71 +407,71 @@ static int Disto16x16(const uint8_t* const a, const uint8_t* const b,
// temp0..temp15 holds tmp[0]..tmp[15]
// A..D - offsets in bytes to load from src and ref buffers
// TEMP0..TEMP3 - registers for corresponding tmp elements
-#define HORIZONTAL_PASS(A, B, C, D, TEMP0, TEMP1, TEMP2, TEMP3) \
- "lw %["#TEMP1"], 0(%[args]) \n\t" \
- "lw %["#TEMP2"], 4(%[args]) \n\t" \
- "lbu %[temp16], "#A"(%["#TEMP1"]) \n\t" \
- "lbu %[temp17], "#A"(%["#TEMP2"]) \n\t" \
- "lbu %[temp18], "#B"(%["#TEMP1"]) \n\t" \
- "lbu %[temp19], "#B"(%["#TEMP2"]) \n\t" \
- "subu %[temp20], %[temp16], %[temp17] \n\t" \
- "lbu %[temp16], "#C"(%["#TEMP1"]) \n\t" \
- "lbu %[temp17], "#C"(%["#TEMP2"]) \n\t" \
- "subu %["#TEMP0"], %[temp18], %[temp19] \n\t" \
- "lbu %[temp18], "#D"(%["#TEMP1"]) \n\t" \
- "lbu %[temp19], "#D"(%["#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"
+#define HORIZONTAL_PASS(A, B, C, D, TEMP0, TEMP1, TEMP2, TEMP3) \
+ "lw %[" #TEMP1 "], 0(%[args]) \n\t" \
+ "lw %[" #TEMP2 "], 4(%[args]) \n\t" \
+ "lbu %[temp16], " #A "(%[" #TEMP1 "]) \n\t" \
+ "lbu %[temp17], " #A "(%[" #TEMP2 "]) \n\t" \
+ "lbu %[temp18], " #B "(%[" #TEMP1 "]) \n\t" \
+ "lbu %[temp19], " #B "(%[" #TEMP2 "]) \n\t" \
+ "subu %[temp20], %[temp16], %[temp17] \n\t" \
+ "lbu %[temp16], " #C "(%[" #TEMP1 "]) \n\t" \
+ "lbu %[temp17], " #C "(%[" #TEMP2 "]) \n\t" \
+ "subu %[" #TEMP0 "], %[temp18], %[temp19] \n\t" \
+ "lbu %[temp18], " #D "(%[" #TEMP1 "]) \n\t" \
+ "lbu %[temp19], " #D "(%[" #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"
// 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" \
- "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"
+#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" \
+ "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"
static void FTransform(const uint8_t* src, const uint8_t* ref, int16_t* out) {
int temp0, temp1, temp2, temp3, temp4, temp5, temp6, temp7, temp8;
@@ -622,14 +622,14 @@ int VP8GetResidualCostMIPS32(int ctx0, const VP8Residual* const res) {
}
#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" \