Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:architecture
|
| gptkbp:appliesTo |
GPU programming
|
| gptkbp:contrastsWith |
gptkb:MIMD_architecture
|
| gptkbp:enables |
data-parallel workloads
massively parallel execution warp-based execution |
| gptkbp:executedBy |
multiple threads with a single instruction stream
warps of threads |
| gptkbp:hasFeature |
hardware thread scheduling
predication for control flow |
| https://www.w3.org/2000/01/rdf-schema#label |
SIMT architecture
|
| gptkbp:introduced |
gptkb:NVIDIA
|
| gptkbp:introducedIn |
gptkb:NVIDIA_G80_GPU
|
| gptkbp:relatedTo |
gptkb:SIMD_architecture
|
| gptkbp:standsFor |
gptkb:Single_Instruction,_Multiple_Threads
|
| gptkbp:supports |
thread divergence
|
| gptkbp:usedBy |
gptkb:NVIDIA_GPUs
|
| gptkbp:usedFor |
high-throughput computing
|
| gptkbp:usedIn |
gptkb:CUDA_programming_model
gptkb:OpenCL_programming_model parallel computing |
| gptkbp:bfsParent |
gptkb:CUDA
|
| gptkbp:bfsLayer |
6
|