how to understand burst sizes info from profiler

[Altera_Forum]

hi, 

 The profiler is showing me the following measurements for the read on the "K_contributors" global arg:  Bandwidth: 0.1 MB/s, 100 % efficiency Average Burst Size: 2.0 (Max Burst size: 16 )    // THIS IS A SINGLE WORK-ITEM KERNEL# define MAX_CONTRIBUTORS 8128 void Krnl_IntraE(... __global const char3* restrict K_contributors, ) { __local char3 localcache ; for (ushort i=0; i<MAX_CONTRIBUTORS; i++) { localcache = K_contributors ; } ... }   As the loop-index "i" is increased consecutively, I expected larger burst sizes than 2. is there any explanation for this?

[Altera_Forum]

You should unroll the loop so that the compiler would infer a wider port to memory, allowing for larger burst size. There is little to no runtime coalescing done for single work-item kernels and hence, you should not expect a large burst size without unrolling, just because the accesses are consecutive.

[Altera_Forum]

1. Why Bandwidth is 0.1MB/s??Is there something wrong with profiler? I also encounter this problem in quartus 17.0 

 2. I have my kernel code like  typedef struct{  float a[20]; }A  __kernel foo(__global *A data){  A localdata[100];  for(i=0;i<100;i++){  localdata[i]=data[i+index];  } }  I expect every memory access will bust coalescing read global memory for 20 float, so Average Burst Size suppose larger than 1. but in profiler Average Burst Size shows only 4~6. how to increase my access efficiency?