1 // Copyright 2014 Google Inc. All Rights Reserved. 2 // 3 // Use of this source code is governed by a BSD-style license 4 // that can be found in the COPYING file in the root of the source 5 // tree. An additional intellectual property rights grant can be found 6 // in the file PATENTS. All contributing project authors may 7 // be found in the AUTHORS file in the root of the source tree. 8 // ----------------------------------------------------------------------------- 9 // 10 // MIPS common macros 11 12 #ifndef WEBP_DSP_MIPS_MACRO_H_ 13 #define WEBP_DSP_MIPS_MACRO_H_ 14 15 #if defined(__GNUC__) && defined(__ANDROID__) && LOCAL_GCC_VERSION == 0x409 16 #define WORK_AROUND_GCC 17 #endif 18 19 #define STR(s) #s 20 #define XSTR(s) STR(s) 21 22 // O0[31..16 | 15..0] = I0[31..16 | 15..0] + I1[31..16 | 15..0] 23 // O1[31..16 | 15..0] = I0[31..16 | 15..0] - I1[31..16 | 15..0] 24 // O - output 25 // I - input (macro doesn't change it) 26 #define ADD_SUB_HALVES(O0, O1, \ 27 I0, I1) \ 28 "addq.ph %[" #O0 "], %[" #I0 "], %[" #I1 "] \n\t" \ 29 "subq.ph %[" #O1 "], %[" #I0 "], %[" #I1 "] \n\t" 30 31 // O - output 32 // I - input (macro doesn't change it) 33 // I[0/1] - offset in bytes 34 #define LOAD_IN_X2(O0, O1, \ 35 I0, I1) \ 36 "lh %[" #O0 "], " #I0 "(%[in]) \n\t" \ 37 "lh %[" #O1 "], " #I1 "(%[in]) \n\t" 38 39 // I0 - location 40 // I1..I9 - offsets in bytes 41 #define LOAD_WITH_OFFSET_X4(O0, O1, O2, O3, \ 42 I0, I1, I2, I3, I4, I5, I6, I7, I8, I9) \ 43 "ulw %[" #O0 "], " #I1 "+" XSTR(I9) "*" #I5 "(%[" #I0 "]) \n\t" \ 44 "ulw %[" #O1 "], " #I2 "+" XSTR(I9) "*" #I6 "(%[" #I0 "]) \n\t" \ 45 "ulw %[" #O2 "], " #I3 "+" XSTR(I9) "*" #I7 "(%[" #I0 "]) \n\t" \ 46 "ulw %[" #O3 "], " #I4 "+" XSTR(I9) "*" #I8 "(%[" #I0 "]) \n\t" 47 48 // O - output 49 // IO - input/output 50 // I - input (macro doesn't change it) 51 #define MUL_SHIFT_SUM(O0, O1, O2, O3, O4, O5, O6, O7, \ 52 IO0, IO1, IO2, IO3, \ 53 I0, I1, I2, I3, I4, I5, I6, I7) \ 54 "mul %[" #O0 "], %[" #I0 "], %[kC2] \n\t" \ 55 "mul %[" #O1 "], %[" #I0 "], %[kC1] \n\t" \ 56 "mul %[" #O2 "], %[" #I1 "], %[kC2] \n\t" \ 57 "mul %[" #O3 "], %[" #I1 "], %[kC1] \n\t" \ 58 "mul %[" #O4 "], %[" #I2 "], %[kC2] \n\t" \ 59 "mul %[" #O5 "], %[" #I2 "], %[kC1] \n\t" \ 60 "mul %[" #O6 "], %[" #I3 "], %[kC2] \n\t" \ 61 "mul %[" #O7 "], %[" #I3 "], %[kC1] \n\t" \ 62 "sra %[" #O0 "], %[" #O0 "], 16 \n\t" \ 63 "sra %[" #O1 "], %[" #O1 "], 16 \n\t" \ 64 "sra %[" #O2 "], %[" #O2 "], 16 \n\t" \ 65 "sra %[" #O3 "], %[" #O3 "], 16 \n\t" \ 66 "sra %[" #O4 "], %[" #O4 "], 16 \n\t" \ 67 "sra %[" #O5 "], %[" #O5 "], 16 \n\t" \ 68 "sra %[" #O6 "], %[" #O6 "], 16 \n\t" \ 69 "sra %[" #O7 "], %[" #O7 "], 16 \n\t" \ 70 "addu %[" #IO0 "], %[" #IO0 "], %[" #I4 "] \n\t" \ 71 "addu %[" #IO1 "], %[" #IO1 "], %[" #I5 "] \n\t" \ 72 "subu %[" #IO2 "], %[" #IO2 "], %[" #I6 "] \n\t" \ 73 "subu %[" #IO3 "], %[" #IO3 "], %[" #I7 "] \n\t" 74 75 // O - output 76 // I - input (macro doesn't change it) 77 #define INSERT_HALF_X2(O0, O1, \ 78 I0, I1) \ 79 "ins %[" #O0 "], %[" #I0 "], 16, 16 \n\t" \ 80 "ins %[" #O1 "], %[" #I1 "], 16, 16 \n\t" 81 82 // O - output 83 // I - input (macro doesn't change it) 84 #define SRA_16(O0, O1, O2, O3, \ 85 I0, I1, I2, I3) \ 86 "sra %[" #O0 "], %[" #I0 "], 16 \n\t" \ 87 "sra %[" #O1 "], %[" #I1 "], 16 \n\t" \ 88 "sra %[" #O2 "], %[" #I2 "], 16 \n\t" \ 89 "sra %[" #O3 "], %[" #I3 "], 16 \n\t" 90 91 // temp0[31..16 | 15..0] = temp8[31..16 | 15..0] + temp12[31..16 | 15..0] 92 // temp1[31..16 | 15..0] = temp8[31..16 | 15..0] - temp12[31..16 | 15..0] 93 // temp0[31..16 | 15..0] = temp0[31..16 >> 3 | 15..0 >> 3] 94 // temp1[31..16 | 15..0] = temp1[31..16 >> 3 | 15..0 >> 3] 95 // O - output 96 // I - input (macro doesn't change it) 97 #define SHIFT_R_SUM_X2(O0, O1, O2, O3, O4, O5, O6, O7, \ 98 I0, I1, I2, I3, I4, I5, I6, I7) \ 99 "addq.ph %[" #O0 "], %[" #I0 "], %[" #I4 "] \n\t" \ 100 "subq.ph %[" #O1 "], %[" #I0 "], %[" #I4 "] \n\t" \ 101 "addq.ph %[" #O2 "], %[" #I1 "], %[" #I5 "] \n\t" \ 102 "subq.ph %[" #O3 "], %[" #I1 "], %[" #I5 "] \n\t" \ 103 "addq.ph %[" #O4 "], %[" #I2 "], %[" #I6 "] \n\t" \ 104 "subq.ph %[" #O5 "], %[" #I2 "], %[" #I6 "] \n\t" \ 105 "addq.ph %[" #O6 "], %[" #I3 "], %[" #I7 "] \n\t" \ 106 "subq.ph %[" #O7 "], %[" #I3 "], %[" #I7 "] \n\t" \ 107 "shra.ph %[" #O0 "], %[" #O0 "], 3 \n\t" \ 108 "shra.ph %[" #O1 "], %[" #O1 "], 3 \n\t" \ 109 "shra.ph %[" #O2 "], %[" #O2 "], 3 \n\t" \ 110 "shra.ph %[" #O3 "], %[" #O3 "], 3 \n\t" \ 111 "shra.ph %[" #O4 "], %[" #O4 "], 3 \n\t" \ 112 "shra.ph %[" #O5 "], %[" #O5 "], 3 \n\t" \ 113 "shra.ph %[" #O6 "], %[" #O6 "], 3 \n\t" \ 114 "shra.ph %[" #O7 "], %[" #O7 "], 3 \n\t" 115 116 // precrq.ph.w temp0, temp8, temp2 117 // temp0 = temp8[31..16] | temp2[31..16] 118 // ins temp2, temp8, 16, 16 119 // temp2 = temp8[31..16] | temp2[15..0] 120 // O - output 121 // IO - input/output 122 // I - input (macro doesn't change it) 123 #define PACK_2_HALVES_TO_WORD(O0, O1, O2, O3, \ 124 IO0, IO1, IO2, IO3, \ 125 I0, I1, I2, I3) \ 126 "precrq.ph.w %[" #O0 "], %[" #I0 "], %[" #IO0 "] \n\t" \ 127 "precrq.ph.w %[" #O1 "], %[" #I1 "], %[" #IO1 "] \n\t" \ 128 "ins %[" #IO0 "], %[" #I0 "], 16, 16 \n\t" \ 129 "ins %[" #IO1 "], %[" #I1 "], 16, 16 \n\t" \ 130 "precrq.ph.w %[" #O2 "], %[" #I2 "], %[" #IO2 "] \n\t" \ 131 "precrq.ph.w %[" #O3 "], %[" #I3 "], %[" #IO3 "] \n\t" \ 132 "ins %[" #IO2 "], %[" #I2 "], 16, 16 \n\t" \ 133 "ins %[" #IO3 "], %[" #I3 "], 16, 16 \n\t" 134 135 // preceu.ph.qbr temp0, temp8 136 // temp0 = 0 | 0 | temp8[23..16] | temp8[7..0] 137 // preceu.ph.qbl temp1, temp8 138 // temp1 = temp8[23..16] | temp8[7..0] | 0 | 0 139 // O - output 140 // I - input (macro doesn't change it) 141 #define CONVERT_2_BYTES_TO_HALF(O0, O1, O2, O3, O4, O5, O6, O7, \ 142 I0, I1, I2, I3) \ 143 "preceu.ph.qbr %[" #O0 "], %[" #I0 "] \n\t" \ 144 "preceu.ph.qbl %[" #O1 "], %[" #I0 "] \n\t" \ 145 "preceu.ph.qbr %[" #O2 "], %[" #I1 "] \n\t" \ 146 "preceu.ph.qbl %[" #O3 "], %[" #I1 "] \n\t" \ 147 "preceu.ph.qbr %[" #O4 "], %[" #I2 "] \n\t" \ 148 "preceu.ph.qbl %[" #O5 "], %[" #I2 "] \n\t" \ 149 "preceu.ph.qbr %[" #O6 "], %[" #I3 "] \n\t" \ 150 "preceu.ph.qbl %[" #O7 "], %[" #I3 "] \n\t" 151 152 // temp0[31..16 | 15..0] = temp0[31..16 | 15..0] + temp8[31..16 | 15..0] 153 // temp0[31..16 | 15..0] = temp0[31..16 <<(s) 7 | 15..0 <<(s) 7] 154 // temp1..temp7 same as temp0 155 // precrqu_s.qb.ph temp0, temp1, temp0: 156 // temp0 = temp1[31..24] | temp1[15..8] | temp0[31..24] | temp0[15..8] 157 // store temp0 to dst 158 // IO - input/output 159 // I - input (macro doesn't change it) 160 #define STORE_SAT_SUM_X2(IO0, IO1, IO2, IO3, IO4, IO5, IO6, IO7, \ 161 I0, I1, I2, I3, I4, I5, I6, I7, \ 162 I8, I9, I10, I11, I12, I13) \ 163 "addq.ph %[" #IO0 "], %[" #IO0 "], %[" #I0 "] \n\t" \ 164 "addq.ph %[" #IO1 "], %[" #IO1 "], %[" #I1 "] \n\t" \ 165 "addq.ph %[" #IO2 "], %[" #IO2 "], %[" #I2 "] \n\t" \ 166 "addq.ph %[" #IO3 "], %[" #IO3 "], %[" #I3 "] \n\t" \ 167 "addq.ph %[" #IO4 "], %[" #IO4 "], %[" #I4 "] \n\t" \ 168 "addq.ph %[" #IO5 "], %[" #IO5 "], %[" #I5 "] \n\t" \ 169 "addq.ph %[" #IO6 "], %[" #IO6 "], %[" #I6 "] \n\t" \ 170 "addq.ph %[" #IO7 "], %[" #IO7 "], %[" #I7 "] \n\t" \ 171 "shll_s.ph %[" #IO0 "], %[" #IO0 "], 7 \n\t" \ 172 "shll_s.ph %[" #IO1 "], %[" #IO1 "], 7 \n\t" \ 173 "shll_s.ph %[" #IO2 "], %[" #IO2 "], 7 \n\t" \ 174 "shll_s.ph %[" #IO3 "], %[" #IO3 "], 7 \n\t" \ 175 "shll_s.ph %[" #IO4 "], %[" #IO4 "], 7 \n\t" \ 176 "shll_s.ph %[" #IO5 "], %[" #IO5 "], 7 \n\t" \ 177 "shll_s.ph %[" #IO6 "], %[" #IO6 "], 7 \n\t" \ 178 "shll_s.ph %[" #IO7 "], %[" #IO7 "], 7 \n\t" \ 179 "precrqu_s.qb.ph %[" #IO0 "], %[" #IO1 "], %[" #IO0 "] \n\t" \ 180 "precrqu_s.qb.ph %[" #IO2 "], %[" #IO3 "], %[" #IO2 "] \n\t" \ 181 "precrqu_s.qb.ph %[" #IO4 "], %[" #IO5 "], %[" #IO4 "] \n\t" \ 182 "precrqu_s.qb.ph %[" #IO6 "], %[" #IO7 "], %[" #IO6 "] \n\t" \ 183 "usw %[" #IO0 "], " XSTR(I13) "*" #I9 "(%[" #I8 "]) \n\t" \ 184 "usw %[" #IO2 "], " XSTR(I13) "*" #I10 "(%[" #I8 "]) \n\t" \ 185 "usw %[" #IO4 "], " XSTR(I13) "*" #I11 "(%[" #I8 "]) \n\t" \ 186 "usw %[" #IO6 "], " XSTR(I13) "*" #I12 "(%[" #I8 "]) \n\t" 187 188 #define OUTPUT_EARLY_CLOBBER_REGS_10() \ 189 : [temp1]"=&r"(temp1), [temp2]"=&r"(temp2), [temp3]"=&r"(temp3), \ 190 [temp4]"=&r"(temp4), [temp5]"=&r"(temp5), [temp6]"=&r"(temp6), \ 191 [temp7]"=&r"(temp7), [temp8]"=&r"(temp8), [temp9]"=&r"(temp9), \ 192 [temp10]"=&r"(temp10) 193 194 #define OUTPUT_EARLY_CLOBBER_REGS_18() \ 195 OUTPUT_EARLY_CLOBBER_REGS_10(), \ 196 [temp11]"=&r"(temp11), [temp12]"=&r"(temp12), [temp13]"=&r"(temp13), \ 197 [temp14]"=&r"(temp14), [temp15]"=&r"(temp15), [temp16]"=&r"(temp16), \ 198 [temp17]"=&r"(temp17), [temp18]"=&r"(temp18) 199 200 #endif // WEBP_DSP_MIPS_MACRO_H_ 201