我主要是一个非常高级的程序员，所以考虑 CPU 局部性之类的事情对我来说是非常新的。
我正在研究一个基本的双线性去马赛克（用于 RGGB 传感器数据），并且我的算法是正确的（从结果来看），但它的性能不如我希望的那样（~210Mpix/s）。
这是我的代码（输入是一个 4640x3472 的图像，单通道 RGGB）：
def get_bilinear_debayer(input_raw, print_nest=False):
x, y, c = Var(), Var(), Var()
# Clamp and move to 32 bit for lots of space for averaging.
input = Func()
input[x,y] = cast(
UInt(32),
input_raw[
clamp(x,0,input_raw.width()-1),
clamp(y,0,input_raw.height()-1)]
)
# Interpolate vertically
vertical = Func()
vertical[x,y] = (input[x,y-1] + input[x,y+1])/2
# Interpolate horizontally
horizontal = Func()
horizontal[x,y] = (input[x-1,y] + input[x+1,y])/2
# Interpolate on diagonals
diagonal_average = Func()
diagonal_average[x, y] = (
input[x+1,y-1] +
input[x+1,y+1] +
input[x-1,y-1] +
input[x-1,y+1])/4
# Interpolate on adjacents
adjacent_average = Func()
adjacent_average[x, y] = (horizontal[x,y] + vertical[x,y])/2
red, green, blue = Func(), Func(), Func()
# Calculate the red channel
red[x, y, c] = select(
# Red photosite
c == 0, input[x, y],
# Green photosite
c == 1, select(x%2 == 0, vertical[x,y],
horizontal[x,y]),
# Blue photosite
diagonal_average[x,y]
)
# Calculate the blue channel
blue[x, y, c] = select(
# Blue photosite
c == 2, input[x, y],
# Green photosite
c == 1, select(x%2 == 1, vertical[x,y],
horizontal[x,y]),
# Red photosite
diagonal_average[x,y]
)
# Calculate the green channel
green[x, y, c] = select(
# Green photosite
c == 1, input[x,y],
# Red/Blue photosite
adjacent_average[x,y]
)
# Switch color interpolator based on requested color.
# Specify photosite as third argument, calculated as [x, y, z] = (0, 0, 0), (0, 1, 1), (1, 0, 1), (1, 1, 2)
# Happily works out to a sum of x mod 2 and y mod 2.
debayer = Func()
debayer[x, y, c] = select(c == 0, red[x, y, x%2 + y%2],
c == 1, green[x, y, x%2 + y%2],
blue[x, y, x%2 + y%2])
# Scheduling
x_outer, y_outer, x_inner, y_inner, tile_index = Var(), Var(), Var(), Var(), Var()
bits = input_raw.get().type().bits
output = Func()
# Cast back to the original colour space
output[x,y,c] = cast(UInt(bits), debayer[x,y,c])
# Reorder so that colours are calculated in order (red runs, then green, then blue)
output.reorder_storage(c, x, y)
# Tile in 128x128 squares
output.tile(x, y, x_outer, y_outer, x_inner, y_inner, 128, 128)
# Vectorize based on colour
output.bound(c, 0, 3)
output.vectorize(c)
# Fuse and parallelize
output.fuse(x_outer, y_outer, tile_index)
output.parallel(tile_index)
# Debugging
if print_nest:
output.print_loop_nest()
debayer.print_loop_nest()
red.print_loop_nest()
green.print_loop_nest()
blue.print_loop_nest()
return output
老实说，我不知道我在这里做什么，而且我对此太陌生，不知道在哪里或看什么。
关于如何改进日程安排的任何建议都是有帮助的。我仍在学习，但很难找到反馈。
我的时间表是我能做的最好的，但它几乎完全是反复试验。
编辑：我通过直接在函数中进行整个相邻平均求和并在 x_inner 而不是颜色上进行矢量化，从而增加了额外的 30Mpix/s。
编辑：新时间表：
# Set input bounds.
output.bound(x, 0, (input_raw.width()/2)*2)
output.bound(y, 0, (input_raw.height()/2)*2)
output.bound(c, 0, 3)
# Reorder so that colours are calculated in order (red runs, then green, then blue)
output.reorder_storage(c, x, y)
output.reorder(c, x, y)
# Tile in 128x128 squares
output.tile(x, y, x_outer, y_outer, x_inner, y_inner, 128, 128)
output.unroll(x_inner, 2).unroll(y_inner,2)
# Vectorize based on colour
output.unroll(c)
output.vectorize(c)
# Fuse and parallelize
output.fuse(x_outer, y_outer, tile_index)
output.parallel(tile_index)
编辑：现在击败（640MP / s）在比我强大两倍的 CPU 上运行的Intel Performance Primitive 基准测试的最终时间表：
output = Func()
# Cast back to the original colour space
output[x,y,c] = cast(UInt(bits), debayer[x,y,c])
# Set input bounds.
output.bound(x, 0, (input_raw.width()/2)*2)
output.bound(y, 0, (input_raw.height()/2)*2)
output.bound(c, 0, 3)
# Tile in 128x128 squares
output.tile(x, y, x_outer, y_outer, x_inner, y_inner, 128, 128)
output.unroll(x_inner, 2).unroll(y_inner, 2)
# Vectorize based on colour
output.vectorize(x_inner, 16)
# Fuse and parallelize
output.fuse(x_outer, y_outer, tile_index)
output.parallel(tile_index)
target = Target()
target.arch = X86
target.os = OSX
target.bits = 64
target.set_feature(AVX)
target.set_feature(AVX2)
target.set_feature(SSE41)
output.compile_jit(target)