OpenCL IP
Filter
Compare
56
IP
from
4
vendors
(1
-
10)
-
4-cluster Power Consumption & Performance Efficiency Enhanced Series6XT 3D/2D/Compute GPU including OpenGL ES 3.0, DX10_0 Feature Level and OpenCL Support, 10-bit YUV, YUV framebuffer, ASTC
- Significant performance increases compared to equivalent configurations of Series6 GPUs
- Deep Colour support for Ultra HD resolutions
- Extra FP16 GFLOPS for low-power rendering
- ASTC compression format (LDR and HDR) (optional)
-
2-cluster Power Consumption & Performance Efficiency Enhanced Series6XT 3D/2D/Compute GPU including OpenGL ES 3.0, DX10_0 Feature Level and OpenCL Support , 10-bit YUV, YUV framebuffer, ASTC
- Significant performance increases compared to equivalent configurations of Series6 GPUs
- Deep Colour support for Ultra HD resolutions
- Extra FP16 GFLOPS for low-power rendering
- ASTC compression format (LDR and HDR) (optional)
-
2-cluster Series6XT 3D/2D/Compute GPU including OpenGL ES 3.0, DX10_0 Feature Level and OpenCL Support , 10-bit YUV, YUV framebuffer
- Significant performance increases compared to equivalent configurations of Series6 GPUs
- Deep Colour support for Ultra HD resolutions
- Extra FP16 GFLOPS for low-power rendering
- ASTC compression format (LDR and HDR) (optional)
-
Advanced graphics and compute acceleration on power constrained devices
- Next Level Efficiency: Microarchitectural changes deliver 50% more geometry performance and better sustained performance compared to its predecessor, IMG DXT. Overall performance efficiency is boosted 20%.
- Optimised for Compute: With a memory structure configured for super-fast compute processing coupled with accelerated scheduling of compute workloads, Imagination DXTP is optimised for AI.
-
NPU IP for Data Center and Automotive
- 128-bit vector processing unit (shader + ext)
- OpenCL 1.2 shader instruction set
- Enhanced vision instruction set (EVIS)
- INT 8/16/32b, Float 16/32b in PPU
- Convolution layers
-
High Performance GPU for premium DTVs
- 10bits RGBA / YUV for HDR experiences
- Advanced image compression technology
- 4xMSAA for smoother image outlines
-
Efficient GPU ideal for integrating into smart home hubs, set-top boxes or mainstream DTVs
- 10bits RGBA / YUV for HDR experiences
- Advanced image compression technology
- 4xMSAA for smoother image outlines
- Fully secure GPU virtualisation with HyperLane
-
Smallest GPU to support native HDR applications, suitable for wearable devices, smart home hubs, or mainstream set-top boxes
- 10bits RGBA / YUV for HDR experiences
- Advanced image compression technology
- Fully secure GPU virtualisation with HyperLane
-
NPU IP for Wearable and IoT Market
- ML inference engine for deeply embedded system
NN Engine
Supports popular ML frameworks
Support wide range of NN algorithms and flexible in layer ordering
- ML inference engine for deeply embedded system
-
NPU IP for AI Vision and AI Voice
- 128-bit vector processing unit (shader + ext)
- OpenCL 3.0 shader instruction set
- Enhanced vision instruction set (EVIS)
- INT 8/16/32b, Float 16/32b
