def runComparison(arguments):
print "Comparing parameters for (" +(str(arguments.name) if arguments.save else "")+ "): ( (" +str(arguments.pos[0])+","+str(arguments.pos[1])+"), ",
print str(arguments.zoom)+", ("+str(arguments.dim[0])+", "+str(arguments.dim[1])+") )"
cpuTime = call_utils.callCPU(arguments.pos,arguments.zoom,arguments.dim,arguments.name,iterations=arguments.iter,save=arguments.save)
try:
results, cudaTime, retblock, retthread = call_utils.callCUDA(arguments.pos,arguments.zoom,arguments.dim,arguments.name,iterations=arguments.iter,
block=arguments.blocks,thread=arguments.threads,save=arguments.save,mode=arguments.mode)
except Exception, e:
print e
cudaTime = 'NA'
pass
def runGeneration(arguments):
if arguments.procCuda:
print("Doing generation ("+arguments.name+") using CUDA")
result, time, blocks, threads = call_utils.callCUDA(arguments.pos,arguments.zoom,arguments.dim,arguments.name,iterations=arguments.iter,
block=arguments.blocks,thread=arguments.threads,save=arguments.save)
elif arguments.procCpu:
print("Doing generation ("+arguments.name+") using the CPU")
time = call_utils.callCPU(arguments.pos,arguments.zoom,arguments.dim,arguments.name,iterations=arguments.iter,save=arguments.save)
print "("+("CUDA" if arguments.procCuda else "CPU")+") run took "+str(time)+"s."
def runQueueLoopComparison(args):
"""
wherein we investiagte the relative advantages of queueing blocks
vs having bigger for-loops in order to get the same amount of work
done.
here we fix a thread-per-block count, solve for the set of integer
values of blocks and pixels-per-thread that tile a fixed size
image, and time the runs.
"""
dimx,dimy=args.dim
resultL = allocate_cores(dimx, dimy, args.threads, silent=True)
#resultL = ( (12, 1024, 2496 ), (6, 1024, 4992) )
#resultL = ( (195, 1024, 2496 ), (97, 1024, 4992) )
if len(resultL)==0:
print 'No valid integer solutions to dimx*dimy = blocks*threads*ppt'
exit(0)
if args.mode != 4:
timeL = []
pptL = []
blocksL = []
for ppt, threads, blocks in resultL:
# eventually call 3-5 times and average
try:
result, time,blocksA, threadsA = call_utils.callCUDA(args.pos,args.zoom, (dimx,dimy),args.name,iterations=args.iter,
block=blocks,thread=threads,save=args.save,
mode=args.mode)
except ValueError, e:
print e
continue
if args.mode != 4:
timeL.append(time)
blocksL.append(blocks)
pptL.append(ppt)
print '%6d,%6d: %6d (%14s) %4d (%12s) %5d %f'%(dimx, dimy, blocks, blocksA, threads, threadsA, ppt, time)
else:
# should be zero, on average, really want to see if there are any zeros or numbers > 2
# overlap = np.sum(result)-(result.shape[0]*result.shape[1])
overlap = np.prod( result )
print '%6d,%6d: %6d (%14s) %4d (%12s) %5d %d (%d %d)'%(dimx, dimy, blocks, blocksA, threads, threadsA, ppt, overlap, np.amin(result), np.amax(result))
def cudaCollect(position,zoom,dimensions,execData,mode=0,iterations=100):
"""
Run callCUDA over a range of block and thread shapes and sizes, and collect data on time spent.
"""
# keep here so we only compile as needed
global _data_file
data = _data_file.root.TimingData.data
meta = _data_file.root.TimingData.meta
index = alreadyRan(position, dimensions, zoom, mode)
# TODO: if index, check versions, and WARN if mismatch
if not index:
# need a new entry
index = _get_new_meta_index()
meta.row['index'] = index
meta.row['pos_x'] = position[0]
meta.row['pos_y'] = position[1]
meta.row['dimensions_x'] = dimensions[0]
meta.row['dimensions_y'] = dimensions[1]
meta.row['zoom'] = zoom
meta.row['mode'] = mode
meta.row['iterations'] = iterations
verD = get_version_info()
for sym in ('os', 'nvidia', 'cuda_device', 'cuda_toolkit', 'gcc',
'python', 'numpy', 'pycuda', 'pytables', 'code_git'):
meta.row['versioninfo/%s'%sym] = verD[sym]
meta.row.append()
meta.flush()
for block in execData['blocks']:
for thread in execData['threads']:
# TODO: check to see if we have done this combo already for the given metadata
try:
name=str(block)+", "+str(thread)
result,time,block_dim,thread_dim = callCUDA(position,zoom,dimensions,name,
block=block,thread=thread,save=False,mode=mode)
except ValueError:
continue
print "GOOD \t"+str(block)+", "+str(thread)+": "+str(time)
data.row['metaIndexFK'] = index
data.row['time'] = time
data.row['block_x'] = block_dim[0]
data.row['block_y'] = block_dim[1]
data.row['blocks'] = block
data.row['thread_x'] = thread_dim[0]
data.row['thread_y'] = thread_dim[1]
data.row['threads'] = thread
if mode==4:
data.row['overlap'] = np.sum(result)-(result.shape[0]*result.shape[1])
else:
data.row['overlap']=0
data.row.append()
data.flush()
return index
