Hello,
I have quite some problems implementing immediate stream compaction using compute shader and I'm sure you can help me out.
First of all I would like to explain what I'm heading for. I'm sorry if it is a long read.
Target :
I need immediate stream compaction to write only useful data to a Buffer because I use a Linear bounding volume hierarchy which writes a Null where no further processing is required.If I write directly into a compacted output then I can save memory and take use of it in form of a deeper hierarchy.
Steps I've already done:
- Labeling every Thread which has useful data with a 1 and every thread which does not require further processing with a 0
- I write all Labels to a temporary RWStructuredBuffer and perform a scan in shared memory
Steps I can't implement:
- I Scanned Every Block in TGSM but now I need for example Take The "maximum count of Block 0" and add it to the whole "Block 1"
so the TGSM block is added with the maximum count of it's left neighbour
-My problem is that I cannot access The Maximum count of block0 for block1 because it is TGSM and not readable between other blocks
I tried to write it to a temporary RWStructuredbuffer and acces it from there also I tried DeviceMemoryBarrier() or AllMemoryBarrier() and [Globally Coherent] to make the written TGSM result in the RWStructuredBuffer visible to every thread.
My Code so far is like this :
const int index = threadId;
if(threadId==0)
{
_TestBuffer[0] = 0;
}
if(GIndex!=0)
{
Label = NodeBuffer[index].Label==0;//Label every usefull Thread
}
_TestBuffer[index] = Label;
shared_StreamCompaction[GIndex] = 0 ; //// WRITE WITH GIndex
GroupMemoryBarrierWithGroupSync();
uint temp = 0;
for(uint i = 0; i<=GIndex;i++) //0-Blocksize(1024)
{
//Scann in Shared Memory
uint result = _TestBuffer[index-min(i,max(0,GIndex))]+ shared_StreamCompaction[GIndex];
shared_StreamCompaction[GIndex] = result;
}
GroupMemoryBarrierWithGroupSync();
//Write Shared to Global cannout acces any blocks but the ones shared within a Thread Group
_TestBuffer[index] = shared_StreamCompaction[GIndex];
// Acces Somehow neighbouring Blocks ??
Thank you for your time! I hope you can help me solve this problem so I can do deeper hierarchies:) Thanks!
Paper Reference :
- Improving SIMD Efficiency for Parallel Monte Carlo Light Transport on the GPU by the awesome Dietger van Antwerpen
- GPU Gems 3 Chapter 39.Parallel Prefix Sum (Scan) with Cuda