What revision you compiled from, BTW?

Assuming you changed maxregisters up to 64 as you stated elsewhere, try dialling it back to 32.

Hmmm, so you're using a LapTop with an External video card?

If you're seeing inconclusives directly as a result of switching maxregcount, then you have Cuda kernels failing silently (and so looking quick) due to launch restrictions in Drivers and hardware.....

Okay, I just searched the Xbranch folder from the last build and found;
$(cuda_cu_objs): cuda/$(@:.o=.cu)
$(NVCC) -c cuda/$(@:.o=.cu) -o $@ -Icuda $(DEFS) $(DEFAULT_INCLUDES) $(INCLUDES) -I$(top_srcdir)/db $(BOINC_CFLAGS) --maxrregcount=32 $(NVCCFLAGS) $(CUDA_CFLAGS)

Since changing it has never been mentioned before, All the Apps have been built with the default which appears to be 32.

Hmmm, I might try setting it to 64 the next time I have the urge to pull all the 750s out and boot to Mountain Lion....just to see how it works on the 750s.

Any other suggestions?

In cudaAcceleration.cu the stock code is

96 bool cudaAcc_setBlockingSync(int device)
97 {
98 // CUdevice hcuDevice;
99 // CUcontext hcuContext;
100
101 /* CUresult status = cuInit(0);
102 if(status != CUDA_SUCCESS)
103 return false;
104
105 status = cuDeviceGet( &hcuDevice, device);
106 if(status != CUDA_SUCCESS)
107 return false;
108
109 status = cuCtxCreate( &hcuContext, 0x4, hcuDevice ); //0x4 is CU_CTX_BLOCKING_SYNC
110 if(status != CUDA_SUCCESS)
111 return false;*/
112
113 #if CUDART_VERSION < 4000
114 CUDA_ACC_SAFE_CALL(cudaSetDeviceFlags(cudaDeviceBlockingSync),false);
115 // CUDA_ACC_SAFE_CALL(cudaSetDeviceFlags(cudaDeviceScheduleYield),false);
116 #else
117 CUDA_ACC_SAFE_CALL(cudaSetDeviceFlags(cudaDeviceScheduleBlockingSync),false);
118 // CUDA_ACC_SAFE_CALL(cudaSetDeviceFlags(cudaDeviceScheduleYield),false);
119 #endif
120 return true;
121 }


my code is different. Try using the same as in stock.

Anyone using the older versions might want to try the newer versions and see if they are any better.

TBar the setiathome_x41zi_x86_64-apple-darwin_cuda65 app is 50% more faster compared with the MBv8_8.05r3346_nvidia_ssse3_x86_64-apple-darwin and uses 25% CPU against 33% the OpenCL app. It's a very good result.

On my GTX750Ti the shorties are about the same as with OpenCL but the longer tasks are significantly faster with cuda65. Task taking around 1100 secs in OpenCL finish in a little under 800 secs in cuda65. The cuda42 App is a little slower but is still faster than OpenCL on the longer tasks with my 750Ti. Testing the cuda42 App in Mountain Lion with my GTS250 gives about the same times as it was receiving in Windows 8.1. The cuda42 App should work with the Pre-Fermi GPUs in Snow Leopard to Mavericks. CUDA 6.5 required by Yosemite Will Not work with the Pre-Fermi GPUs.