我发现RenderScript中缺少良好的文档,据我所知,RS中的forEach
是为分配中的每个项目执行root()。
我正在尝试为执行图像处理的Renderscript创建一个库,作为一个起点,我达到了这个great answer。但问题在于,模糊操作在每个像素上,并且每个像素需要另一个循环(n具有模糊宽度)的计算。尽管在多核上运行,但它仍然有点太慢。
我正在尝试修改它以允许(两次通过)盒式过滤器,但这需要处理单个行或列而不是单元格。那么,有没有办法让foreach将数组发送到root()?
答案 0 :(得分:16)
rsForEach只能在分配时运行。
如果你想让rsForEach函数为每个图像行调用root(),你必须传入一个大小与行数长度相同的分配,然后找出你应该在哪一行在root()内部运行(类似于在每个列上运行)。然后,RenderScript应该将工作分配给可用资源(在多核设备上同时处理多行)。
您可以这样做的一种方法是传入一个分配,该分配给出图像行的偏移量(在图像数据数组中)。 root()中的v_in参数将是行偏移量。由于rsForEach调用操作的分配不是图像数据,因此无法使用v_out参数写出图像,并且必须单独绑定输出图像。
以下是一些显示此内容的RenderScript:
#pragma version(1)
#pragma rs java_package_name(com.android.example.hellocompute)
rs_allocation gIn;
rs_allocation gOut;
rs_script gScript;
int mImageWidth;
const uchar4 *gInPixels;
uchar4 *gOutPixels;
void init() {
}
static const int kBlurWidth = 20;
//
// This is called per row.
// The row indices are passed in as v_in or you could also use the x argument and multiply it by image width.
//
void root(const int32_t *v_in, int32_t *v_out, const void *usrData, uint32_t x, uint32_t y) {
float3 blur[kBlurWidth];
float3 cur_colour = {0.0f, 0.0f, 0.0f};
for ( int i = 0; i < kBlurWidth; i++) {
float3 init_colour = {0.0f, 0.0f, 0.0f};
blur[i] = init_colour;
}
int32_t row_index = *v_in;
int blur_index = 0;
for ( int i = 0; i < mImageWidth; i++) {
float4 pixel_colour = rsUnpackColor8888(gInPixels[i + row_index]);
cur_colour -= blur[blur_index];
blur[blur_index] = pixel_colour.rgb;
cur_colour += blur[blur_index];
blur_index += 1;
if ( blur_index >= kBlurWidth) {
blur_index = 0;
}
gOutPixels[i + row_index] = rsPackColorTo8888(cur_colour/(float)kBlurWidth);
//gOutPixels[i + row_index] = rsPackColorTo8888(pixel_colour);
}
}
void filter() {
rsDebug("Number of rows:", rsAllocationGetDimX(gIn));
rsForEach(gScript, gIn, gOut, NULL);
}
这将使用以下Java设置:
mBlurRowScript = new ScriptC_blur_row(mRS, getResources(), R.raw.blur_row);
int row_width = mBitmapIn.getWidth();
//
// Create an allocation that indexes each row.
//
int num_rows = mBitmapIn.getHeight();
int[] row_indices = new int[num_rows];
for ( int i = 0; i < num_rows; i++) {
row_indices[i] = i * row_width;
}
Allocation row_indices_alloc = Allocation.createSized( mRS, Element.I32(mRS), num_rows, Allocation.USAGE_SCRIPT);
row_indices_alloc.copyFrom(row_indices);
//
// The image data has to be bound to the pointers within the RenderScript so it can be accessed
// from the root() function.
//
mBlurRowScript.bind_gInPixels(mInAllocation);
mBlurRowScript.bind_gOutPixels(mOutAllocation);
// Pass in the image width
mBlurRowScript.set_mImageWidth(row_width);
//
// Pass in the row indices Allocation as the input. It is also passed in as the output though the output is not used.
//
mBlurRowScript.set_gIn(row_indices_alloc);
mBlurRowScript.set_gOut(row_indices_alloc);
mBlurRowScript.set_gScript(mBlurRowScript);
mBlurRowScript.invoke_filter();