/* * Copyright (c) 2012 * MIPS Technologies, Inc., California. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the MIPS Technologies, Inc., nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE MIPS TECHNOLOGIES, INC. ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE MIPS TECHNOLOGIES, INC. BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. * * Author: Nemanja Lukic (nlukic@mips.com) */ #include "pixman-mips-dspr2-asm.h" LEAF_MIPS_DSPR2(pixman_fill_buff16_mips) /* * a0 - *dest * a1 - count (bytes) * a2 - value to fill buffer with */ beqz a1, 3f andi t1, a0, 0x0002 beqz t1, 0f /* check if address is 4-byte aligned */ nop sh a2, 0(a0) addiu a0, a0, 2 addiu a1, a1, -2 0: srl t1, a1, 5 /* t1 how many multiples of 32 bytes */ replv.ph a2, a2 /* replicate fill value (16bit) in a2 */ beqz t1, 2f nop 1: addiu t1, t1, -1 beqz t1, 11f addiu a1, a1, -32 pref 30, 32(a0) sw a2, 0(a0) sw a2, 4(a0) sw a2, 8(a0) sw a2, 12(a0) sw a2, 16(a0) sw a2, 20(a0) sw a2, 24(a0) sw a2, 28(a0) b 1b addiu a0, a0, 32 11: sw a2, 0(a0) sw a2, 4(a0) sw a2, 8(a0) sw a2, 12(a0) sw a2, 16(a0) sw a2, 20(a0) sw a2, 24(a0) sw a2, 28(a0) addiu a0, a0, 32 2: blez a1, 3f addiu a1, a1, -2 sh a2, 0(a0) b 2b addiu a0, a0, 2 3: jr ra nop END(pixman_fill_buff16_mips) LEAF_MIPS32R2(pixman_fill_buff32_mips) /* * a0 - *dest * a1 - count (bytes) * a2 - value to fill buffer with */ beqz a1, 3f nop srl t1, a1, 5 /* t1 how many multiples of 32 bytes */ beqz t1, 2f nop 1: addiu t1, t1, -1 beqz t1, 11f addiu a1, a1, -32 pref 30, 32(a0) sw a2, 0(a0) sw a2, 4(a0) sw a2, 8(a0) sw a2, 12(a0) sw a2, 16(a0) sw a2, 20(a0) sw a2, 24(a0) sw a2, 28(a0) b 1b addiu a0, a0, 32 11: sw a2, 0(a0) sw a2, 4(a0) sw a2, 8(a0) sw a2, 12(a0) sw a2, 16(a0) sw a2, 20(a0) sw a2, 24(a0) sw a2, 28(a0) addiu a0, a0, 32 2: blez a1, 3f addiu a1, a1, -4 sw a2, 0(a0) b 2b addiu a0, a0, 4 3: jr ra nop END(pixman_fill_buff32_mips) LEAF_MIPS_DSPR2(pixman_composite_src_8888_0565_asm_mips) /* * a0 - dst (r5g6b5) * a1 - src (a8r8g8b8) * a2 - w */ beqz a2, 3f nop addiu t1, a2, -1 beqz t1, 2f nop li t4, 0xf800f800 li t5, 0x07e007e0 li t6, 0x001f001f 1: lw t0, 0(a1) lw t1, 4(a1) addiu a1, a1, 8 addiu a2, a2, -2 CONVERT_2x8888_TO_2x0565 t0, t1, t2, t3, t4, t5, t6, t7, t8 sh t2, 0(a0) sh t3, 2(a0) addiu t2, a2, -1 bgtz t2, 1b addiu a0, a0, 4 2: beqz a2, 3f nop lw t0, 0(a1) CONVERT_1x8888_TO_1x0565 t0, t1, t2, t3 sh t1, 0(a0) 3: j ra nop END(pixman_composite_src_8888_0565_asm_mips) LEAF_MIPS_DSPR2(pixman_composite_src_0565_8888_asm_mips) /* * a0 - dst (a8r8g8b8) * a1 - src (r5g6b5) * a2 - w */ beqz a2, 3f nop addiu t1, a2, -1 beqz t1, 2f nop li t4, 0x07e007e0 li t5, 0x001F001F 1: lhu t0, 0(a1) lhu t1, 2(a1) addiu a1, a1, 4 addiu a2, a2, -2 CONVERT_2x0565_TO_2x8888 t0, t1, t2, t3, t4, t5, t6, t7, t8, t9 sw t2, 0(a0) sw t3, 4(a0) addiu t2, a2, -1 bgtz t2, 1b addiu a0, a0, 8 2: beqz a2, 3f nop lhu t0, 0(a1) CONVERT_1x0565_TO_1x8888 t0, t1, t2, t3 sw t1, 0(a0) 3: j ra nop END(pixman_composite_src_0565_8888_asm_mips) LEAF_MIPS_DSPR2(pixman_composite_src_x888_8888_asm_mips) /* * a0 - dst (a8r8g8b8) * a1 - src (x8r8g8b8) * a2 - w */ beqz a2, 4f nop li t9, 0xff000000 srl t8, a2, 3 /* t1 = how many multiples of 8 src pixels */ beqz t8, 3f /* branch if less than 8 src pixels */ nop 1: addiu t8, t8, -1 beqz t8, 2f addiu a2, a2, -8 pref 0, 32(a1) lw t0, 0(a1) lw t1, 4(a1) lw t2, 8(a1) lw t3, 12(a1) lw t4, 16(a1) lw t5, 20(a1) lw t6, 24(a1) lw t7, 28(a1) addiu a1, a1, 32 or t0, t0, t9 or t1, t1, t9 or t2, t2, t9 or t3, t3, t9 or t4, t4, t9 or t5, t5, t9 or t6, t6, t9 or t7, t7, t9 pref 30, 32(a0) sw t0, 0(a0) sw t1, 4(a0) sw t2, 8(a0) sw t3, 12(a0) sw t4, 16(a0) sw t5, 20(a0) sw t6, 24(a0) sw t7, 28(a0) b 1b addiu a0, a0, 32 2: lw t0, 0(a1) lw t1, 4(a1) lw t2, 8(a1) lw t3, 12(a1) lw t4, 16(a1) lw t5, 20(a1) lw t6, 24(a1) lw t7, 28(a1) addiu a1, a1, 32 or t0, t0, t9 or t1, t1, t9 or t2, t2, t9 or t3, t3, t9 or t4, t4, t9 or t5, t5, t9 or t6, t6, t9 or t7, t7, t9 sw t0, 0(a0) sw t1, 4(a0) sw t2, 8(a0) sw t3, 12(a0) sw t4, 16(a0) sw t5, 20(a0) sw t6, 24(a0) sw t7, 28(a0) beqz a2, 4f addiu a0, a0, 32 3: lw t0, 0(a1) addiu a1, a1, 4 addiu a2, a2, -1 or t1, t0, t9 sw t1, 0(a0) bnez a2, 3b addiu a0, a0, 4 4: jr ra nop END(pixman_composite_src_x888_8888_asm_mips) LEAF_MIPS_DSPR2(pixman_composite_over_n_8888_8888_ca_asm_mips) /* * a0 - dst (a8r8g8b8) * a1 - src (32bit constant) * a2 - mask (a8r8g8b8) * a3 - w */ SAVE_REGS_ON_STACK 8, s0, s1, s2, s3, s4, s5 beqz a3, 4f nop li t6, 0xff addiu t7, zero, -1 /* t7 = 0xffffffff */ srl t8, a1, 24 /* t8 = srca */ li t9, 0x00ff00ff addiu t1, a3, -1 beqz t1, 3f /* last pixel */ nop beq t8, t6, 2f /* if (srca == 0xff) */ nop 1: /* a1 = src */ lw t0, 0(a2) /* t0 = mask */ lw t1, 4(a2) /* t1 = mask */ or t2, t0, t1 beqz t2, 12f /* if (t0 == 0) && (t1 == 0) */ addiu a2, a2, 8 and t3, t0, t1 move t4, a1 /* t4 = src */ move t5, a1 /* t5 = src */ lw t2, 0(a0) /* t2 = dst */ beq t3, t7, 11f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */ lw t3, 4(a0) /* t3 = dst */ MIPS_2xUN8x4_MUL_2xUN8x4 a1, a1, t0, t1, t4, t5, t9, s0, s1, s2, s3, s4, s5 MIPS_2xUN8x4_MUL_2xUN8 t0, t1, t8, t8, t0, t1, t9, s0, s1, s2, s3, s4, s5 11: not t0, t0 not t1, t1 MIPS_2xUN8x4_MUL_2xUN8x4 t2, t3, t0, t1, t2, t3, t9, s0, s1, s2, s3, s4, s5 addu_s.qb t2, t4, t2 addu_s.qb t3, t5, t3 sw t2, 0(a0) sw t3, 4(a0) 12: addiu a3, a3, -2 addiu t1, a3, -1 bgtz t1, 1b addiu a0, a0, 8 b 3f nop 2: /* a1 = src */ lw t0, 0(a2) /* t0 = mask */ lw t1, 4(a2) /* t1 = mask */ or t2, t0, t1 beqz t2, 22f /* if (t0 == 0) & (t1 == 0) */ addiu a2, a2, 8 and t2, t0, t1 move t4, a1 beq t2, t7, 21f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */ move t5, a1 lw t2, 0(a0) /* t2 = dst */ lw t3, 4(a0) /* t3 = dst */ MIPS_2xUN8x4_MUL_2xUN8x4 a1, a1, t0, t1, t4, t5, t9, s0, s1, s2, s3, s4, s5 not t0, t0 not t1, t1 MIPS_2xUN8x4_MUL_2xUN8x4 t2, t3, t0, t1, t2, t3, t9, s0, s1, s2, s3, s4, s5 addu_s.qb t4, t4, t2 addu_s.qb t5, t5, t3 21: sw t4, 0(a0) sw t5, 4(a0) 22: addiu a3, a3, -2 addiu t1, a3, -1 bgtz t1, 2b addiu a0, a0, 8 3: blez a3, 4f nop /* a1 = src */ lw t1, 0(a2) /* t1 = mask */ beqz t1, 4f nop move t2, a1 /* t2 = src */ beq t1, t7, 31f lw t0, 0(a0) /* t0 = dst */ MIPS_UN8x4_MUL_UN8x4 a1, t1, t2, t9, t3, t4, t5, t6 MIPS_UN8x4_MUL_UN8 t1, t8, t1, t9, t3, t4, t5 31: not t1, t1 MIPS_UN8x4_MUL_UN8x4 t0, t1, t0, t9, t3, t4, t5, t6 addu_s.qb t0, t2, t0 sw t0, 0(a0) 4: RESTORE_REGS_FROM_STACK 8, s0, s1, s2, s3, s4, s5 j ra nop END(pixman_composite_over_n_8888_8888_ca_asm_mips) LEAF_MIPS_DSPR2(pixman_composite_over_n_8888_0565_ca_asm_mips) /* * a0 - dst (r5g6b5) * a1 - src (32bit constant) * a2 - mask (a8r8g8b8) * a3 - w */ SAVE_REGS_ON_STACK 20, s0, s1, s2, s3, s4, s5, s6, s7, s8 beqz a3, 4f nop li t5, 0xf800f800 li t6, 0x07e007e0 li t7, 0x001F001F li t9, 0x00ff00ff srl t8, a1, 24 /* t8 = srca */ addiu t1, a3, -1 beqz t1, 3f /* last pixel */ nop li s0, 0xff /* s0 = 0xff */ addiu s1, zero, -1 /* s1 = 0xffffffff */ beq t8, s0, 2f /* if (srca == 0xff) */ nop 1: /* a1 = src */ lw t0, 0(a2) /* t0 = mask */ lw t1, 4(a2) /* t1 = mask */ or t2, t0, t1 beqz t2, 12f /* if (t0 == 0) && (t1 == 0) */ addiu a2, a2, 8 and t3, t0, t1 move s2, a1 /* s2 = src */ move s3, a1 /* s3 = src */ lhu t2, 0(a0) /* t2 = dst */ beq t3, s1, 11f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */ lhu t3, 2(a0) /* t3 = dst */ MIPS_2xUN8x4_MUL_2xUN8x4 a1, a1, t0, t1, s2, s3, t9, t4, s4, s5, s6, s7, s8 MIPS_2xUN8x4_MUL_2xUN8 t0, t1, t8, t8, t0, t1, t9, t4, s4, s5, s6, s7, s8 11: not t0, t0 not t1, t1 CONVERT_2x0565_TO_2x8888 t2, t3, s4, s5, t6, t7, t4, s6, s7, s8 MIPS_2xUN8x4_MUL_2xUN8x4 s4, s5, t0, t1, s4, s5, t9, t4, s6, s7, s8, t0, t1 addu_s.qb s2, s2, s4 addu_s.qb s3, s3, s5 CONVERT_2x8888_TO_2x0565 s2, s3, t2, t3, t5, t6, t7, s4, s5 sh t2, 0(a0) sh t3, 2(a0) 12: addiu a3, a3, -2 addiu t1, a3, -1 bgtz t1, 1b addiu a0, a0, 4 b 3f nop 2: /* a1 = src */ lw t0, 0(a2) /* t0 = mask */ lw t1, 4(a2) /* t1 = mask */ or t2, t0, t1 beqz t2, 22f /* if (t0 == 0) & (t1 == 0) */ addiu a2, a2, 8 and t3, t0, t1 move t2, a1 beq t3, s1, 21f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */ move t3, a1 lhu t2, 0(a0) /* t2 = dst */ lhu t3, 2(a0) /* t3 = dst */ MIPS_2xUN8x4_MUL_2xUN8x4 a1, a1, t0, t1, s2, s3, t9, t4, s4, s5, s6, s7, s8 not t0, t0 not t1, t1 CONVERT_2x0565_TO_2x8888 t2, t3, s4, s5, t6, t7, t4, s6, s7, s8 MIPS_2xUN8x4_MUL_2xUN8x4 s4, s5, t0, t1, s4, s5, t9, t4, s6, s7, s8, t2, t3 addu_s.qb t2, s2, s4 addu_s.qb t3, s3, s5 21: CONVERT_2x8888_TO_2x0565 t2, t3, t0, t1, t5, t6, t7, s2, s3 sh t0, 0(a0) sh t1, 2(a0) 22: addiu a3, a3, -2 addiu t1, a3, -1 bgtz t1, 2b addiu a0, a0, 4 3: blez a3, 4f nop /* a1 = src */ lw t1, 0(a2) /* t1 = mask */ beqz t1, 4f nop move t2, a1 /* t2 = src */ beq t1, t7, 31f lhu t0, 0(a0) /* t0 = dst */ MIPS_UN8x4_MUL_UN8x4 a1, t1, t2, t9, t3, t4, t5, t6 MIPS_UN8x4_MUL_UN8 t1, t8, t1, t9, t3, t4, t5 31: not t1, t1 CONVERT_1x0565_TO_1x8888 t0, s1, s2, s3 MIPS_UN8x4_MUL_UN8x4 s1, t1, t3, t9, t4, t5, t6, t7 addu_s.qb t0, t2, t3 CONVERT_1x8888_TO_1x0565 t0, s1, s2, s3 sh s1, 0(a0) 4: RESTORE_REGS_FROM_STACK 20, s0, s1, s2, s3, s4, s5, s6, s7, s8 j ra nop END(pixman_composite_over_n_8888_0565_ca_asm_mips) LEAF_MIPS_DSPR2(pixman_composite_over_n_8_8888_asm_mips) /* * a0 - dst (a8r8g8b8) * a1 - src (32bit constant) * a2 - mask (a8) * a3 - w */ SAVE_REGS_ON_STACK 4, s0, s1, s2, s3, s4 beqz a3, 4f nop li t4, 0x00ff00ff li t5, 0xff addiu t0, a3, -1 beqz t0, 3f /* last pixel */ srl t6, a1, 24 /* t6 = srca */ not s4, a1 beq t5, t6, 2f /* if (srca == 0xff) */ srl s4, s4, 24 1: /* a1 = src */ lbu t0, 0(a2) /* t0 = mask */ lbu t1, 1(a2) /* t1 = mask */ or t2, t0, t1 beqz t2, 111f /* if (t0 == 0) && (t1 == 0) */ addiu a2, a2, 2 and t3, t0, t1 lw t2, 0(a0) /* t2 = dst */ beq t3, t5, 11f /* if (t0 == 0xff) && (t1 == 0xff) */ lw t3, 4(a0) /* t3 = dst */ MIPS_2xUN8x4_MUL_2xUN8 a1, a1, t0, t1, s0, s1, t4, t6, t7, t8, t9, s2, s3 not s2, s0 not s3, s1 srl s2, s2, 24 srl s3, s3, 24 MIPS_2xUN8x4_MUL_2xUN8 t2, t3, s2, s3, t2, t3, t4, t0, t1, t6, t7, t8, t9 addu_s.qb s2, t2, s0 addu_s.qb s3, t3, s1 sw s2, 0(a0) b 111f sw s3, 4(a0) 11: MIPS_2xUN8x4_MUL_2xUN8 t2, t3, s4, s4, t2, t3, t4, t0, t1, t6, t7, t8, t9 addu_s.qb s2, t2, a1 addu_s.qb s3, t3, a1 sw s2, 0(a0) sw s3, 4(a0) 111: addiu a3, a3, -2 addiu t0, a3, -1 bgtz t0, 1b addiu a0, a0, 8 b 3f nop 2: /* a1 = src */ lbu t0, 0(a2) /* t0 = mask */ lbu t1, 1(a2) /* t1 = mask */ or t2, t0, t1 beqz t2, 222f /* if (t0 == 0) && (t1 == 0) */ addiu a2, a2, 2 and t3, t0, t1 beq t3, t5, 22f /* if (t0 == 0xff) && (t1 == 0xff) */ nop lw t2, 0(a0) /* t2 = dst */ lw t3, 4(a0) /* t3 = dst */ OVER_2x8888_2x8_2x8888 a1, a1, t0, t1, t2, t3, \ t6, t7, t4, t8, t9, s0, s1, s2, s3 sw t6, 0(a0) b 222f sw t7, 4(a0) 22: sw a1, 0(a0) sw a1, 4(a0) 222: addiu a3, a3, -2 addiu t0, a3, -1 bgtz t0, 2b addiu a0, a0, 8 3: blez a3, 4f nop /* a1 = src */ lbu t0, 0(a2) /* t0 = mask */ beqz t0, 4f /* if (t0 == 0) */ addiu a2, a2, 1 move t3, a1 beq t0, t5, 31f /* if (t0 == 0xff) */ lw t1, 0(a0) /* t1 = dst */ MIPS_UN8x4_MUL_UN8 a1, t0, t3, t4, t6, t7, t8 31: not t2, t3 srl t2, t2, 24 MIPS_UN8x4_MUL_UN8 t1, t2, t1, t4, t6, t7, t8 addu_s.qb t2, t1, t3 sw t2, 0(a0) 4: RESTORE_REGS_FROM_STACK 4, s0, s1, s2, s3, s4 j ra nop END(pixman_composite_over_n_8_8888_asm_mips) LEAF_MIPS_DSPR2(pixman_composite_over_n_8_0565_asm_mips) /* * a0 - dst (r5g6b5) * a1 - src (32bit constant) * a2 - mask (a8) * a3 - w */ SAVE_REGS_ON_STACK 24, v0, s0, s1, s2, s3, s4, s5, s6, s7, s8 beqz a3, 4f nop li t4, 0x00ff00ff li t5, 0xff li t6, 0xf800f800 li t7, 0x07e007e0 li t8, 0x001F001F addiu t1, a3, -1 beqz t1, 3f /* last pixel */ srl t0, a1, 24 /* t0 = srca */ not v0, a1 beq t0, t5, 2f /* if (srca == 0xff) */ srl v0, v0, 24 1: /* a1 = src */ lbu t0, 0(a2) /* t0 = mask */ lbu t1, 1(a2) /* t1 = mask */ or t2, t0, t1 beqz t2, 111f /* if (t0 == 0) && (t1 == 0) */ addiu a2, a2, 2 lhu t2, 0(a0) /* t2 = dst */ lhu t3, 2(a0) /* t3 = dst */ CONVERT_2x0565_TO_2x8888 t2, t3, s0, s1, t7, t8, t9, s2, s3, s4 and t9, t0, t1 beq t9, t5, 11f /* if (t0 == 0xff) && (t1 == 0xff) */ nop MIPS_2xUN8x4_MUL_2xUN8 a1, a1, t0, t1, s2, s3, t4, t9, s4, s5, s6, s7, s8 not s4, s2 not s5, s3 srl s4, s4, 24 srl s5, s5, 24 MIPS_2xUN8x4_MUL_2xUN8 s0, s1, s4, s5, s0, s1, t4, t9, t0, t1, s6, s7, s8 addu_s.qb s4, s2, s0 addu_s.qb s5, s3, s1 CONVERT_2x8888_TO_2x0565 s4, s5, t2, t3, t6, t7, t8, s0, s1 sh t2, 0(a0) b 111f sh t3, 2(a0) 11: MIPS_2xUN8x4_MUL_2xUN8 s0, s1, v0, v0, s0, s1, t4, t9, t0, t1, s6, s7, s8 addu_s.qb s4, a1, s0 addu_s.qb s5, a1, s1 CONVERT_2x8888_TO_2x0565 s4, s5, t2, t3, t6, t7, t8, s0, s1 sh t2, 0(a0) sh t3, 2(a0) 111: addiu a3, a3, -2 addiu t0, a3, -1 bgtz t0, 1b addiu a0, a0, 4 b 3f nop 2: CONVERT_1x8888_TO_1x0565 a1, s0, s1, s2 21: /* a1 = src */ lbu t0, 0(a2) /* t0 = mask */ lbu t1, 1(a2) /* t1 = mask */ or t2, t0, t1 beqz t2, 222f /* if (t0 == 0) && (t1 == 0) */ addiu a2, a2, 2 and t9, t0, t1 move s2, s0 beq t9, t5, 22f /* if (t0 == 0xff) && (t2 == 0xff) */ move s3, s0 lhu t2, 0(a0) /* t2 = dst */ lhu t3, 2(a0) /* t3 = dst */ CONVERT_2x0565_TO_2x8888 t2, t3, s2, s3, t7, t8, s4, s5, s6, s7 OVER_2x8888_2x8_2x8888 a1, a1, t0, t1, s2, s3, \ t2, t3, t4, t9, s4, s5, s6, s7, s8 CONVERT_2x8888_TO_2x0565 t2, t3, s2, s3, t6, t7, t8, s4, s5 22: sh s2, 0(a0) sh s3, 2(a0) 222: addiu a3, a3, -2 addiu t0, a3, -1 bgtz t0, 21b addiu a0, a0, 4 3: blez a3, 4f nop /* a1 = src */ lbu t0, 0(a2) /* t0 = mask */ beqz t0, 4f /* if (t0 == 0) */ nop lhu t1, 0(a0) /* t1 = dst */ CONVERT_1x0565_TO_1x8888 t1, t2, t3, t7 beq t0, t5, 31f /* if (t0 == 0xff) */ move t3, a1 MIPS_UN8x4_MUL_UN8 a1, t0, t3, t4, t7, t8, t9 31: not t6, t3 srl t6, t6, 24 MIPS_UN8x4_MUL_UN8 t2, t6, t2, t4, t7, t8, t9 addu_s.qb t1, t2, t3 CONVERT_1x8888_TO_1x0565 t1, t2, t3, t7 sh t2, 0(a0) 4: RESTORE_REGS_FROM_STACK 24, v0, s0, s1, s2, s3, s4, s5, s6, s7, s8 j ra nop END(pixman_composite_over_n_8_0565_asm_mips) LEAF_MIPS_DSPR2(pixman_scaled_bilinear_scanline_8888_8_8888_OVER_asm_mips) /* * a0 - dst (a8r8g8b8) * a1 - mask (a8) * a2 - src_top (a8r8g8b8) * a3 - src_bottom (a8r8g8b8) * 16(sp) - wt * 20(sp) - wb * 24(sp) - vx * 28(sp) - unit_x * 32(sp) - w */ SAVE_REGS_ON_STACK 28, v0, v1, s0, s1, s2, s3, s4, s5, s6, s7, s8 lw v1, 60(sp) /* v1 = w(sp + 32 + 28 save regs stack offset)*/ beqz v1, 1f nop lw s0, 44(sp) /* s0 = wt */ lw s1, 48(sp) /* s1 = wb */ lw s2, 52(sp) /* s2 = vx */ lw s3, 56(sp) /* s3 = unit_x */ li v0, 256 li s8, 0x00ff00ff 0: andi t4, s2, 0xffff /* t4 = (short)vx */ srl t4, t4, 8 /* t4 = vx >> 8 */ subu t5, v0, t4 /* t5 = ( 256 - (vx>>8)) */ mul s4, s0, t5 /* s4 = wt*(256-(vx>>8)) */ mul s5, s0, t4 /* s5 = wt*(vx>>8) */ mul s6, s1, t5 /* s6 = wb*(256-(vx>>8)) */ mul s7, s1, t4 /* s7 = wb*(vx>>8) */ sra t9, s2, 16 sll t9, t9, 2 addiu t8, t9, 4 lwx t0, t9(a2) /* t0 = tl */ lwx t1, t8(a2) /* t1 = tr */ addiu v1, v1, -1 lwx t2, t9(a3) /* t2 = bl */ lwx t3, t8(a3) /* t3 = br */ BILINEAR_INTERPOLATE_SINGLE_PIXEL t0, t1, t2, t3, \ t4, t5, t6, t7, t8, t9, s4, s5, s6, s7 lbu t1, 0(a1) /* t1 = mask */ lw t2, 0(a0) /* t2 = dst */ addiu a1, a1, 1 OVER_8888_8_8888 t0, t1, t2, t0, s8, t3, t4, t5, t6 addu s2, s2, s3 /* vx += unit_x; */ sw t0, 0(a0) bnez v1, 0b addiu a0, a0, 4 1: RESTORE_REGS_FROM_STACK 28, v0, v1, s0, s1, s2, s3, s4, s5, s6, s7, s8 j ra nop END(pixman_scaled_bilinear_scanline_8888_8_8888_OVER_asm_mips)