NVIDIA-AI-IOT / CUDA-PointPillars

Hello everyone,

Some of these const variables in kernel.h are saying that they depends on params.h but I don't clearly understand which one is equivalent of the one in params.h.

CUDA-PointPillars/include/kernel.h

Lines 28 to 33 in 092affc

    
           const int POINTS_PER_VOXEL = 32;      // depands on "params.h" 
        
           const int WARP_SIZE = 32;             // one warp(32 threads) for one pillar 
        
           const int WARPS_PER_BLOCK = 4;        // four warp for one block 
        
           const int FEATURES_SIZE = 10;         // features maps number depands on "params.h" 
        
           const int PILLARS_PER_BLOCK = 64;     // one thread deals with one pillar and a block has PILLARS_PER_BLOCK threads 
        
           const int PILLAR_FEATURE_SIZE = 64;   // feature count for one pillar depands on "params.h"

Does anyone have idea about it ?

shouldn't these variables be updated based on params.h ?

	const int POINTS_PER_VOXEL = 32; // depands on "params.h"
	const int WARP_SIZE = 32; // one warp(32 threads) for one pillar
	const int WARPS_PER_BLOCK = 4; // four warp for one block
	const int FEATURES_SIZE = 10; // features maps number depands on "params.h"
	const int PILLARS_PER_BLOCK = 64; // one thread deals with one pillar and a block has PILLARS_PER_BLOCK threads
	const int PILLAR_FEATURE_SIZE = 64; // feature count for one pillar depands on "params.h"

About hard coded const variables in kernel.h