Đối với các nhân viên Google trong tương lai chọn cách tiếp cận NDK - tôi tìm thấy thuật toán stackblur được đề cập đáng tin cậy. Tôi đã tìm thấy triển khai C ++ không dựa vào SSE ở đây - http://www.antigrain.com/__code/include/agg_blur.h.html#stack_blur_rgba32 có chứa một số tối ưu hóa bằng cách sử dụng các bảng tĩnh như:
static unsigned short const stackblur_mul[255] =
{
512,512,456,512,328,456,335,512,405,328,271,456,388,335,292,512,
454,405,364,328,298,271,496,456,420,388,360,335,312,292,273,512,
482,454,428,405,383,364,345,328,312,298,284,271,259,496,475,456,
437,420,404,388,374,360,347,335,323,312,302,292,282,273,265,512,
497,482,468,454,441,428,417,405,394,383,373,364,354,345,337,328,
320,312,305,298,291,284,278,271,265,259,507,496,485,475,465,456,
446,437,428,420,412,404,396,388,381,374,367,360,354,347,341,335,
329,323,318,312,307,302,297,292,287,282,278,273,269,265,261,512,
505,497,489,482,475,468,461,454,447,441,435,428,422,417,411,405,
399,394,389,383,378,373,368,364,359,354,350,345,341,337,332,328,
324,320,316,312,309,305,301,298,294,291,287,284,281,278,274,271,
268,265,262,259,257,507,501,496,491,485,480,475,470,465,460,456,
451,446,442,437,433,428,424,420,416,412,408,404,400,396,392,388,
385,381,377,374,370,367,363,360,357,354,350,347,344,341,338,335,
332,329,326,323,320,318,315,312,310,307,304,302,299,297,294,292,
289,287,285,282,280,278,275,273,271,269,267,265,263,261,259
};
static unsigned char const stackblur_shr[255] =
{
9, 11, 12, 13, 13, 14, 14, 15, 15, 15, 15, 16, 16, 16, 16, 17,
17, 17, 17, 17, 17, 17, 18, 18, 18, 18, 18, 18, 18, 18, 18, 19,
19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 19, 20, 20, 20,
20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 21,
21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21,
21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 22, 22, 22, 22, 22, 22,
22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22,
22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 23,
23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23,
23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23,
23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23, 23,
23, 23, 23, 23, 23, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24,
24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24,
24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24,
24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24,
24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24
};
Tôi đã thực hiện sửa đổi thuật toán stackblur cho các hệ thống đa lõi - có thể tìm thấy ở đây http://vitiy.info/stackblur-alerskym-multi-threaded-blur-for-cpp/
Khi ngày càng nhiều thiết bị có 4 lõi - tối ưu hóa Lợi ích gấp 4 lần tốc độ.