Sandy Bridge Memory analysis problems
Language English Trying to use the analysis type "Memory access - Sandy Bridge and Ivy Bridge" in VTune 2013 on an application. App runs fine, and results are collected and processed but the...
View ArticleSupport of Intel Xeon Phi ?
Language English Hi,Is there some plan to support Intel Xeon Phi with OpenCL ?If yes, is there some way for companies/partners etc... to test their application with it ? At least for profiling and...
View ArticleKnights Corner and OpenCL
Language English Will OpenCL be the preferd method for programming Knights Corner devices or OpenMP or both?
View ArticleBenchmark app. Looking for testers
Language English I have written a small application that tests the double-precision floating point performance of Android phones. My application is written using the NDK and compiled for both x86 and...
View ArticleDumping HD4000 assembler for OpenCL kernel
Language English Hi,is there a way similiar to NVIDIA's PTX dump in Intel's OpenCL SDK to dump the code generated for IVB's iGPU?Thanks,Alex
View ArticleFeature request: Profiling L3 cache on processor graphics
Language English Is it possible to add a profiling feature to measure L3 cache miss rate on the processor graphics side?This is for read/write from OpenCL buffers.
View ArticleMapping of OpenCL work groups to EUs
Language English I wanted to clarify how work groups are mapped to HD 4000 hardware. My understanding is that a workgroup maps to a single EU, and each EU can run multiple workgroups in parallel. Is...
View ArticleEU peak flops
Language English AFAIK Intel has not provided any documentation about the peak ALU throughput of each EU. My understanding is that each EU has 2 FPUs, each capable of 8 flops/cycle (4 MACs per cycle...
View ArticleFeature requests
Language English Just wanted to add two feature requests:1. FP64 support has already been mentioned and would be the most important request for me.2. Memory migration APIs from OpenCL 1.2 would be very...
View ArticleAbout GPU OpenCL support:D3D11 interop, FP64 support etc..
Language English Hi,I'm seeing articles on IVB GPU and seems currently GPUOpenCL support is lacking double precision support which is supported in GPU HW.. In directcompute is supported but seems no in...
View ArticleEU peak flops
AFAIK Intel has not provided any documentation about the peak ALU throughput of each EU. My understanding is that each EU has 2 FPUs, each capable of 8 flops/cycle (4 MACs per cycle per FPU pipe). Thus...
View ArticleFeature request: Profiling L3 cache on processor graphics
Is it possible to add a profiling feature to measure L3 cache miss rate on the processor graphics side?This is for read/write from OpenCL buffers.
View ArticleDumping HD4000 assembler for OpenCL kernel
Hi,is there a way similiar to NVIDIA's PTX dump in Intel's OpenCL SDK to dump the code generated for IVB's iGPU?Thanks,Alex
View ArticleBenchmark app. Looking for testers
I have written a small application that tests the double-precision floating point performance of Android phones. My application is written using the NDK and compiled for both x86 and ARMv7 CPUs....
View ArticleSupport of Intel Xeon Phi ?
Hi,Is there some plan to support Intel Xeon Phi with OpenCL ?If yes, is there some way for companies/partners etc... to test their application with it ? At least for profiling and debugging ?BTW, I...
View ArticleSandy Bridge Memory analysis problems
Trying to use the analysis type "Memory access - Sandy Bridge and Ivy Bridge" in VTune 2013 on an application. App runs fine, and results are collected and processed but the application opens the...
View ArticleOpenCL GPU analysis working partially
First of all, many thanks to the VTune team to implementing OpenCL GPU profiling to the tool.I was trying out the tool on a command-line OpenCL application running on the HD 4000. I followed the...
View ArticleFP64 support on GPU of 4th Gen Core (Haswell)
Now that the Haswell NDA has been lifted, I wanted to know1. Do any of the GPUs (Iris Pro 5200, Iris 5100, HD 5000, HD 4600) support cl_khr_fp64 (or perhaps some custom fp64 extension) in OpenCL?2. If...
View ArticleD3D 11.2 mapping default buffers: Intel support?
D3D 11.2 introduced a cool new feature that allows you to map default buffers. This can be very useful for compute, particularly on integrated GPUs. Wondering which Intel platforms will support this...
View ArticleDirectX ExtendedDoublesShaderInstructions on Intel?
Do any of the Intel GPUs support ExtendedDoublesShaderInstructions under Direct3D?
View Article
More Pages to Explore .....