我已經使用手寫合併分析器評估了代碼的內存訪問。評估顯示代碼較少利用合併。下面是你可能會發現有用的凝聚分析:
#include <stdio.h>
#include <malloc.h>
typedef struct dim3_t{
int x;
int y;
} dim3;
// KERNEL LAUNCH PARAMETERS
#define GRIDDIMX 4
#define GRIDDIMY 4
#define BLOCKDIMX 16
#define BLOCKDIMY 16
// ARCHITECTURE DEPENDENT
// number of threads aggregated for coalescing
#define COALESCINGWIDTH 32
// number of bytes in one coalesced transaction
#define CACHEBLOCKSIZE 128
#define CACHE_BLOCK_ADDR(addr,size) (addr*size)&(~(CACHEBLOCKSIZE-1))
int main(){
// fixed dim3 variables
// grid and block size
dim3 blockDim,gridDim;
blockDim.x=BLOCKDIMX;
blockDim.y=BLOCKDIMY;
gridDim.x=GRIDDIMX;
gridDim.y=GRIDDIMY;
// counters
int unq_accesses=0;
int *unq_addr=(int*)malloc(sizeof(int)*COALESCINGWIDTH);
int total_unq_accesses=0;
// iter over total number of threads
// and count the number of memory requests (the coalesced requests)
int I, II, III;
for(I=0; I<GRIDDIMX*GRIDDIMY; I++){
dim3 blockIdx;
blockIdx.x = I%GRIDDIMX;
blockIdx.y = I/GRIDDIMX;
for(II=0; II<BLOCKDIMX*BLOCKDIMY; II++){
if(II%COALESCINGWIDTH==0){
// new coalescing bunch
total_unq_accesses+=unq_accesses;
unq_accesses=0;
}
dim3 threadIdx;
threadIdx.x=II%BLOCKDIMX;
threadIdx.y=II/BLOCKDIMX;
////////////////////////////////////////////////////////
// Change this section to evaluate different accesses //
////////////////////////////////////////////////////////
// do your indexing here
#define BLOCK_SIZE_X BLOCKDIMX
#define BLOCK_SIZE_Y BLOCKDIMY
#define xdim 32
int i = threadIdx.x;
int j = threadIdx.y;
int idx = blockIdx.x*BLOCK_SIZE_X + threadIdx.x;
int idy = blockIdx.y*BLOCK_SIZE_Y + threadIdx.y;
int index1 = j*BLOCK_SIZE_Y+i;
int i1 = (index1)%(BLOCK_SIZE_X+1);
int j1 = (index1)/(BLOCK_SIZE_Y+1);
int i2 = (BLOCK_SIZE_X*BLOCK_SIZE_Y+index1)%(BLOCK_SIZE_X+1);
int j2 = (BLOCK_SIZE_X*BLOCK_SIZE_Y+index1)/(BLOCK_SIZE_Y+1);
// calculate the accessed location and offset here
// change the line "Ezx_h[(blockIdx.y*BLOCK_SIZE_Y+j1)*xdim+(blockIdx.x*BLOCK_SIZE_X+i1)];" to
int addr = (blockIdx.y*BLOCK_SIZE_Y+j1)*xdim+(blockIdx.x*BLOCK_SIZE_X+i1);
int size = sizeof(double);
//////////////////////////
// End of modifications //
//////////////////////////
printf("tid (%d,%d) from blockid (%d,%d) accessing to block %d\n",threadIdx.x,threadIdx.y,blockIdx.x,blockIdx.y,CACHE_BLOCK_ADDR(addr,size));
// check whether it can be merged with existing requests or not
short merged=0;
for(III=0; III<unq_accesses; III++){
if(CACHE_BLOCK_ADDR(addr,size)==CACHE_BLOCK_ADDR(unq_addr[III],size)){
merged=1;
break;
}
}
if(!merged){
// new cache block accessed over this coalescing width
unq_addr[unq_accesses]=CACHE_BLOCK_ADDR(addr,size);
unq_accesses++;
}
}
}
printf("%d threads make %d memory transactions\n",GRIDDIMX*GRIDDIMY*BLOCKDIMX*BLOCKDIMY, total_unq_accesses);
}
的代碼將網格的每個線程運行,計算合併請求,度量的存儲器存取合併的數量。
要使用分析器,請將代碼的索引計算部分粘貼到指定區域,然後將內存訪問(數組)分解爲'地址'和'大小'。我已經做到了這一點爲您的代碼,其中indexings是:
int i = threadIdx.x;
int j = threadIdx.y;
int idx = blockIdx.x*BLOCK_SIZE_X + threadIdx.x;
int idy = blockIdx.y*BLOCK_SIZE_Y + threadIdx.y;
int index1 = j*BLOCK_SIZE_Y+i;
int i1 = (index1)%(BLOCK_SIZE_X+1);
int j1 = (index1)/(BLOCK_SIZE_Y+1);
int i2 = (BLOCK_SIZE_X*BLOCK_SIZE_Y+index1)%(BLOCK_SIZE_X+1);
int j2 = (BLOCK_SIZE_X*BLOCK_SIZE_Y+index1)/(BLOCK_SIZE_Y+1);
和內存訪問:
Ezx_h_shared_ext[i1][j1]=Ezx_h[(blockIdx.y*BLOCK_SIZE_Y+j1)*xdim+(blockIdx.x*BLOCK_SIZE_X+i1)];
的分析報告4096個線程訪問4064個高速緩存塊。運行您的實際網格和塊大小的代碼並分析合併行爲。
很酷! NVIDIA還有一個SDK,可直接訪問芯片中的性能計數器。 https://developer.nvidia.com/nvidia-perfkit –
@RogerDahl不錯!內存合併是否在芯片中有任何計數器? – ahmad
我認爲合併是從其他計數器派生的東西之一。 Nsight剖析器提供了一些關於內存實驗的內容:「選擇這個實驗組以識別內核的與內存相關的性能瓶頸。對於CUDA內存層次結構的每個內存空間,收集關鍵指標,包括合併,組衝突,L1/L2緩存命中率,並實現帶寬。「 perf試劑盒文件有一些很好的圖表詳細說明計數器。那些可能可以用來找出如何計算合併。 –