Stack Overflow
Stack Overflow

Questions tagged [kepler]

A family of NVIDIA GPUs that can be used for graphics or compute purposes

Kepler, named after the famous scientist Johannes Kepler, is a name referring to a family of NVIDIA GPUs which appear in the GeForce (graphics), Quadro (professional graphics) and Tesla (compute) product families.

Kepler GPUs offer higher performance and other new features over previous previous NVIDIA GPU families (such as Fermi) including compute capabilities such as Hyper-Q and Dynamic Parallelism. The Kepler instruction set offers new instructions not found in previous families, such as funnel shift. Current Kepler GPUs have a compute capability of cc 3.0 or 3.5.

NVIDIA Home page

Wikipedia article link

65 questions
0
votes
1 answer

Why are dependencies missing after gradle import in eclipse kepler

I have imported the project JCPABE ( https://github.com/TU-Berlin-SNET/JCPABE ) via Buildship Gradle Integration in eclipse Kepler on Windows 10. Now, many packages show me similiar errors, concerning 5-10 classes that are not existing, seems like…
attr1bute
  • 21
  • 5
0
votes
1 answer

Faster Parallel Reductions on Kepler

I'm just a CUDA beginner and trying to use Faster Parallel Reductions on Kepler on my program, but I didn't get the result, below is a function of what I'm doing, the output is 0, I would be appreciated to know what is my mistake? #ifndef…
Mina
  • 33
  • 1
  • 7
0
votes
1 answer

Can't seem to open Eclipse Kepler [first time user]

I installed Java7(64bit), EclipseKepler(64bit) and my OS is Win10(64bit) also how can I fix this?
F.Satorre
  • 7
  • 1
0
votes
0 answers

Weblogic 12 c Eclipse Kepler Spring deploy error

I work with Eclipse Kepler, Weblogic 12.1.2, Spring 3.2.6.RELEASE. When I deploy the application from Eclipse Weblogic, I get the following error message ERROR: org.springframework.web.context.ContextLoader - Context initialization…
Carlota
  • 1,239
  • 3
  • 29
  • 59
0
votes
1 answer

(pool-2-thread-5) Got error closing channel JBREM00206

My eclipse (Kepler) got stuck while starting the deployment by clicking RUN ON SER server (JBOSS 7.0.1 final). I can successfully deploy the application through manual process (making war and copy the war to deployment directory and start the…
manish
  • 321
  • 4
  • 15
0
votes
1 answer

*Modified* Nvidia Maxwell, increased global memory instruction count

I had an experiment on both GTX760(Kepler) and GTX750Ti(Maxwell) using benchmarks(Parboil, Rodinia). Then I analyzed results using Nvidia visual profiler. In most of the applications, the number of global instructions are enormously increased up to…
hkim
  • 13
  • 2
0
votes
1 answer

CUDA: Thread-block Level Broadcast on K40 using Shuffle instrutions

indirectJ2[MAX_SUPER_SIZE] is a shared array. My cuda device kernel contains following statement (executed by all threads in the thread block): int nnz_col = indirectJ2[MAX_SUPER_SIZE - 1]; I suspect this would cause bank conflicts. Is there any…
arbitUser1401
  • 575
  • 2
  • 8
  • 25
0
votes
1 answer

Is there a GPU Architecture simulator that supports Kepler?

I am looking "GPGPU-sim"-like simulator that supports Kepler architecture.
Brian Cluff
  • 1
  • 1
0
votes
1 answer

Nvidia Jetson TK1 Development Board - Cuda Compute Capability

I have quite impressed with this deployment kit. Instead of buying a new CUDA card, which might require new main board and etc, this card seems provide all in one. At it's specs it says it has CUDA compute capability 3.2. AFAIK dynamic parallelism…
phoad
  • 1,801
  • 2
  • 20
  • 31
0
votes
1 answer

The efficiency and performance of ILP for the NVIDIA Kepler architecture

Quoting the "Kepler Tuning Guide" provided by NVIDIA: Also note that Kepler GPUs can utilize ILP in place of thread/warp-level parallelism (TLP) more readily than Fermi GPUs can. In my opinion, the following code snippet a = .....; a2 = f(a);…
user2968731
  • 117
  • 1
  • 9
0
votes
1 answer

CUDA Kepler: not enough ALUs

According to the Kepler whitepage, the warp size for a Kepler based GPU is 32 and each multiprocessor contains 4 warp schedulars which select two independant instructions from a chosen warp. This means that each clock cycle, 32*4*2 = 256…
PieterV
  • 816
  • 10
  • 23
0
votes
2 answers

HttpServlet is a restricted class. Please see the Google App Engine

I am getting the following error when running a basic servlet on Eclipse Kepler (Windows 7) with GAE SDK 1.9.3 and Java 7: java.lang.NoClassDefFoundError: javax.servlet.http.HttpServlet is a restricted class. Please see the Google App Engine…
user3582739
  • 1
0
votes
1 answer

On Double Precision Units (DPUs) on Kepler K20Xm

According to the Kepler architecture whitepaper, a SMX has 192 CUDA cores and 64 Double Precision Units (DPUs). For a K20Xm there are 14 SMXs totalling at 2688 cores, which means that only the CUDA cores are counted. What exactly is then the usage…
user2267896
  • 173
  • 2
  • 9
0
votes
1 answer

Increasing achieved occupancy doesn't enhance computation speed linearly

I had a CUDA program in which kernel registers were limiting maximum theoretical achieved occupancy to %50. So I decided to use shared memory instead of registers for those variables that were constant between block threads and were almost read-only…
Farzad
  • 3,288
  • 2
  • 29
  • 53
0
votes
1 answer

Error: External calls are not supported (found non-inlined call to cublasGetVersion_v2)

I'm trying to use the call cublasIdamax() but I got a similar error like the title. So I write a simple code to verify the version of cublas, to avoid a version mistake in signature of function. But even this simple code result in a compilation…
adiel
  • 13
  • 1
  • 3
1 2 3
4
5