diff options
Diffstat (limited to 'pixman/pixman/pixman-arm-simd-asm.S')
| -rw-r--r-- | pixman/pixman/pixman-arm-simd-asm.S | 47 |
1 files changed, 28 insertions, 19 deletions
diff --git a/pixman/pixman/pixman-arm-simd-asm.S b/pixman/pixman/pixman-arm-simd-asm.S index 8fe1b5038..b438001d3 100644 --- a/pixman/pixman/pixman-arm-simd-asm.S +++ b/pixman/pixman/pixman-arm-simd-asm.S @@ -355,49 +355,57 @@ pixman_asm_function pixman_composite_over_n_8_8888_asm_armv6 prefetch_braking_distance pixman_asm_function fname - W .req r0 - DST .req r1 - SRC .req r2 - VX .req r3 - UNIT_X .req ip - TMP1 .req r4 - TMP2 .req r5 - VXMASK .req r6 - PF_OFFS .req r7 + W .req r0 + DST .req r1 + SRC .req r2 + VX .req r3 + UNIT_X .req ip + TMP1 .req r4 + TMP2 .req r5 + VXMASK .req r6 + PF_OFFS .req r7 + SRC_WIDTH_FIXED .req r8 ldr UNIT_X, [sp] - push {r4, r5, r6, r7} + push {r4, r5, r6, r7, r8, r10} mvn VXMASK, #((1 << bpp_shift) - 1) + ldr SRC_WIDTH_FIXED, [sp, #28] /* define helper macro */ .macro scale_2_pixels ldr&t TMP1, [SRC, TMP1] - and TMP2, VXMASK, VX, lsr #(16 - bpp_shift) - add VX, VX, UNIT_X + and TMP2, VXMASK, VX, asr #(16 - bpp_shift) + adds VX, VX, UNIT_X str&t TMP1, [DST], #(1 << bpp_shift) +9: subpls VX, VX, SRC_WIDTH_FIXED + bpl 9b ldr&t TMP2, [SRC, TMP2] - and TMP1, VXMASK, VX, lsr #(16 - bpp_shift) - add VX, VX, UNIT_X + and TMP1, VXMASK, VX, asr #(16 - bpp_shift) + adds VX, VX, UNIT_X str&t TMP2, [DST], #(1 << bpp_shift) +9: subpls VX, VX, SRC_WIDTH_FIXED + bpl 9b .endm /* now do the scaling */ - and TMP1, VXMASK, VX, lsr #(16 - bpp_shift) - add VX, VX, UNIT_X + and TMP1, VXMASK, VX, asr #(16 - bpp_shift) + adds VX, VX, UNIT_X +9: subpls VX, VX, SRC_WIDTH_FIXED + bpl 9b subs W, W, #(8 + prefetch_braking_distance) blt 2f /* calculate prefetch offset */ mov PF_OFFS, #prefetch_distance mla PF_OFFS, UNIT_X, PF_OFFS, VX 1: /* main loop, process 8 pixels per iteration with prefetch */ - subs W, W, #8 + pld [SRC, PF_OFFS, asr #(16 - bpp_shift)] add PF_OFFS, UNIT_X, lsl #3 scale_2_pixels scale_2_pixels scale_2_pixels scale_2_pixels - pld [SRC, PF_OFFS, lsr #(16 - bpp_shift)] + subs W, W, #8 bge 1b 2: subs W, W, #(4 - 8 - prefetch_braking_distance) @@ -426,8 +434,9 @@ pixman_asm_function fname .unreq TMP2 .unreq VXMASK .unreq PF_OFFS + .unreq SRC_WIDTH_FIXED /* return */ - pop {r4, r5, r6, r7} + pop {r4, r5, r6, r7, r8, r10} bx lr .endfunc .endm |