# Speed - Global memory access vs. bitwise operation **URL:** \ **Category:** CUDA Programming and Performance\ **Created:** [October 23, 2011, 3:40pm UTC](https://forums.developer.nvidia.com/t/speed-global-memory-access-vs-bitwise-operation/24700 "2011-10-23T15:40:46Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![perry](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@perry](https://forums.developer.nvidia.com/u/perry)\ **Post date:** [October 23, 2011, 3:40pm UTC](https://forums.developer.nvidia.com/t/speed-global-memory-access-vs-bitwise-operation/24700/1 "2011-10-23T15:40:46Z")
What is faster in Cuda 4.0, 2.0 device… write / read global memory OR bitwise operation (shifts) during runtime (more than once… in loop). Operation will be done on 64bit numbers (or even “simulated” 128bit, by struct). So far I am using global memory, but efficiency is realy poor. I have stack stored in global memory, but stack is only from 4bit numbers (well… in stack stored as char), so I thought, store stack as 64bit number and use logical operation instead of array access to global memory. If I use 64bit number as stack for 4 bit numbers, i got capacity 16, which is enough for me for most cases. ---
**Author:** ![wlangdon](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@wlangdon](https://forums.developer.nvidia.com/u/wlangdon)\ **Post date:** [October 24, 2011, 7:53pm UTC](https://forums.developer.nvidia.com/t/speed-global-memory-access-vs-bitwise-operation/24700/2 "2011-10-24T19:53:45Z")
> [@](#): > > So far I am using global memory, but efficiency is realy poor. I have stack stored in global memory, Do you have to use global memory? In the past I placed the stack in shared memory (each thread had its own stack). [http://www.cs.bham.ac.uk/~wbl/biblio/gp-html/langdon\_2010\_eurogp.html](http://www.cs.bham.ac.uk/~wbl/biblio/gp-html/langdon_2010_eurogp.html) Today I would be tempted to place each thread’s stack in local memory and rely on top of the stack being in cache most of the time. If that does not work: how deep does your stack have to be? If you only have 4 bits per item could you fake a stack by shifting a register or two left-right 4 bits for each pop-push? Bill Dr. W. B. Langdon, ``` Department of Computer Science, University College London Gower Street, London WC1E 6BT, UK http://www.cs.ucl.ac.uk/staff/W.Langdon/ ``` CIGPU 2012 [CIGPU-2012 WCCI-2012 IJCNN-2012, CEC2012](http://www.cs.ucl.ac.uk/staff/W.Langdon/cigpu) EvoPAR 2012 [EvoPAR 2012 EvoStar track on Parallel Architectures and Distributed Infrastructures](http://www.cs.ucl.ac.uk/staff/W.Langdon/evopar) EuroGP 2012 30 Nov RNAnet [http://bioinformatics.essex.ac.uk/users/wlangdon/rnanet/](http://bioinformatics.essex.ac.uk/users/wlangdon/rnanet/) A Field Guide to Genetic Programming ``` http://www.gp-field-guide.org.uk/ ``` GP EM [http://www.springer.com/10710](http://www.springer.com/10710) GP Bibliography [http://www.cs.bham.ac.uk/~wbl/biblio/](http://www.cs.bham.ac.uk/~wbl/biblio/)