Embedded MXM Modules
ADLINK Technology Inc. (ADLINK)
ADLINK’s Embedded MXM GPU modules - based on NVIDIA's embedded GPUs - can boost the performance of a wide range of workloads, including image processing and analysis, computing acceleration, and artificial intelligence (AI). ADLINK’s Embedded MXM GPU modules offer high performance, high data bandwidth, power efficiency, and longevity support in a reduced hardware footprint, well-suited for size, weight, and power (SWaP) constrained applications. ADLINK’s Embedded MXM GPU modules can increase system responsiveness and accuracy, as well as decrease latency, and are an ideal fit for industrial automation, healthcare, transportation, aerospace and defense, gaming, and telecom applications.
-
product
Embedded MXM GPU Module with NVIDIA® Quadro® Embedded T1000
EGX-MXM-T1000
The EGX-MXM-T1000 module features advanced NVIDIA® Turing™ GPU technology in MXM 3.1 Type A form factor. It’s compact, slim and reliable design makes it suitable for mission critical environment. EGX-MXM-T1000 provides improved performance per watt. This MXM GPU module offers a flexible and easy solution for deep learning solutions for applications including medical, image processing, and gaming applications.
-
product
Embedded MXM GPU Module with NVIDIA® Quadro® Embedded RTX3000
EGX-MXM-RTX3000
The EGX-MXM-RTX3000 module features advanced NVIDIA® Turing™ GPU technology in MXM 3.1 Type B form factor. It’s compact, slim and reliable design makes it suitable for mission critical environment. With Quadro® Turing™ TU106 processing cores, EGX-MXM-RTX3000 supports 4 DP1.4 displays offering a flexible and easy solution for medical and gaming applications.
-
product
Embedded MXM GPU Module with NVIDIA® Quadro® Embedded RTX5000
EGX-MXM-RTX5000
The EGX-MXM-RTX5000 module features advanced NVIDIA® Turing™ GPU technology in MXM 3.1 Type B+ form factor. It’s compact, slim and reliable design makes it suitable for mission critical environment. EGX-MXM-RTX5000 supports 4 DP 1.4b displays offering a flexible and easy solution for medical and gaming applications.
-
product
Embedded MXM GPU Module with Embedded NVIDIA RTX™ A500
EGX-MXM-A500
- NVIDIA Ampere Architecture- Standard MXM 3.1 Type A (82 x 70 mm)- PCIe Gen 4 x4 interface- 2048 CUDA® cores, 16 RT Cores, and 64 Tensor Cores- 6.54 TFLOPS Peak FP32 performance
-
product
Embedded MXM GPU Module with Embedded NVIDIA RTX™ A1000
EGX-MXM-A1000
- NVIDIA Ampere Architecture- Standard MXM 3.1 Type A (82 x 70 mm)- PCIe Gen 4 x8 interface- 2048 CUDA® cores, 16 RT Cores, and 64 Tensor Cores- 6.66TFLOPS peak FP32 performance- 4GB GDDR6 memory, 128-bit- 192GB/s maximal memory bandwidth- 5-year availability
-
product
Embedded MXM GPU Module with NVIDIA RTX™ A2000
EGX-MXM-A2000
- NVIDIA Ampere Architecture- Standard MXM 3.1 Type A (82x70mm)- PCIe Gen 4 x8 interface- 2560 CUDA® cores, 20 RT Cores, and 80 Tensor Cores- 8.25 TFLOPS peak FP32 performance
-
product
Embedded MXM GPU Module with Embedded NVIDIA RTX™ A4500
EGX-MXM-A4500
- NVIDIA Ampere Architecture- Standard MXM 3.1 Type B (82x105 mm)- PCIe Gen 4 x16 interface- 5888 CUDA® cores, 46 RT Cores, and 184 Tensor Cores- 17.66 TFLOPS peak FP32 performance
-
product
PCIe-to-MXM adapter supporting ADLINK Mobile PCI Express Modules with NVIDIA® Quadro® embedded GPUs
EGX-MXM-AD
The EGX-MXM-AD is an PCIe adapter supporting ADLINK NVIDIA® Quadro® MXM 3.1 Type A, Type B, and Type B+ GPU modules for quick validation and early development purposes on your AI applications. The following modules are supported: EGX-MXM-P1000, EGX-MXM-P2000, EGX-MXM-T1000, EGX-MXM-RTX3000, and EGX-MXM-RTX5000. A reference thermal solution is available.
-
product
Embedded MXM GPU Module with NVIDIA® Quadro® Embedded P1000
EGX-MXM-P1000
The EGX-MXM-P1000 features advanced NVIDIA Quadro GPU with NVIDIA Pascal™ Architecture technology in MXM 3.1 Type A form factor. The EGX-MXM-P1000 has 512 NVIDIA CUDA cores and a peak single-precision floating-point performance of 1.8 TFLOPS. The EGX-MXM-P1000 has 4GB of GDDR5 memory and supports NVIDIA GPUDirect™ RDMA which helps increase data throughput by up to 80% and consequently system responsiveness by up to 60%*. Additionally, 4 UHD display outputs and an extended operating temperature range of -40°C to 85°C are supported. The embedded graphics product is suitable for mission-critical harsh-environment edge computing applications with size, weight, and power (SWaP) and network connectivity constraints.
-
product
Embedded MXM GPU Modules with NVIDIA® Quadro® Embedded P2000
EGX-MXM-P2000
The EGX-MXM-P2000 features advanced NVIDIA Quadro GPU with NVIDIA Pascal™ Architecture technology in MXM 3.1 Type A form factor. The EGX-MXM-P2000 has 768 NVIDIA CUDA cores and a peak single-precision floating-point performance of 2.3 TFLOPS. The EGX-MXM-P2000 has 4GB of GDDR5 memory and supports NVIDIA GPUDirect™ RDMA which helps increase data throughput by up to 80% and consequently system responsiveness by up to 60%*. Additionally, 4 UHD display outputs and an extended operating temperature range of -40°C to 85°C are supported. The embedded graphics product is suitable for mission-critical harshenvironment edge computing applications with size, weight, and power (SWaP) and network connectivity constraints.
-
product
MXM 3.1 Type A based on Intel® Arc™ GPU
MXM-AXe
Integrating Intel’s latest line of powerful, discrete graphics — Intel® Arc™ — ADLINK introduces its MXM-AXe, one of the industry’s first MXM (R3.1) Type A discrete GPU modules. Packing hardware ray tracing, AI acceleration, and support for 4x 4K displays, the module enhances responsiveness, precision, and reliability for graphics-demanding, time-sensitive edge applications in commercial gaming, healthcare, media processing, and transportation. ADLINK MXM-AXe provides up to 8 hardware ray-tracing cores, 128 execution units, 4GB GDDR6, and 8x PCIe Gen4 at maximum 35W TGP and the industry’s first full AV1 hardware encoding.
-
product
Embedded MXM GPU Module With NVIDIA RTX™ ADA 5000
EGX-MXM-AD5000
- NVIDIA Ada Lovelace Architecture- Standard MXM 3.1 Type B (82x105 mm)- PCIe Gen4x16 interface- 9728 CUDA® Cores, 76 RT Cores, and 304 Tensor Cores- 42.6 TFLOPS peak FP32 performance- 16GB GDDR6 memory, 256-bit- 576GB/s maximal memory bandwidth- 5-year Availability
-
product
Embedded MXM GPU Module With NVIDIA RTX™ ADA 3500
EGX-MXM-AD3500
- NVIDIA Ada Lovelace Architecture- Standard MXM 3.1 Type B (82x105 mm)- PCIe Gen 4 x16 Interface- 5120 CUDA® Cores, 40 RT Cores, and 160 Tensor Cores- 23 TFLOPS peak FP32 performance
-
product
Embedded MXM GPU Module With NVIDIA RTX™ ADA 2000
EGX-MXM-AD2000
- NVIDIA Ada Lovelace Architecture- Standard MXM 3.1 Type A (82x70 mm)- PCIe Gen 4 x8 Interface- 3072 CUDA® Cores, 24 RT Cores, and 96 Tensor Cores- 14.5 TFLOPS peak FP32 performance
-
product
PCI Express Graphics Card With NVIDIA RTX 6000 Ada
NVIDIA RTX 6000 Ada
- NVIDIA Ada Lovelace Architecture- Full height, full length design- PCIe Gen4x16 interface- 48GB GDDR6 Memory, 384-bit Bandwidth- 18176 CUDA Cores, 91.1 TFLOPS SP Peak
-
product
PCI Express Graphics Card With NVIDIA RTX 5000 Ada
NVIDIA RTX 5000 Ada
- NVIDIA Ada Lovelace Architecture- Full height, full length design- PCIe Gen4x16 interface- 32GB GDDR6 Memory, 256-bit Bandwidth- 12800 CUDA Cores, 65.3 TFLOPS SP Peak
-
product
PCI Express Graphics Card With NVIDIA RTX 4500 Ada
NVIDIA RTX 4500 Ada
- NVIDIA Ada Lovelace Architecture- Full height, full length design- PCIe Gen4x16 interface- 24GB GDDR6 Memory, 192-bit Bandwidth- 7680 CUDA Cores, 39.6 TFLOPS SP Peak
-
product
PCI Express Graphic Card NVIDIA RTX 4000E Ada
NVIDIA RTX 4000E Ada
- NVIDIA Ada Lovelace Architecture- 5-year Longevity Support- Full height, full length design- PCIe Gen4x16 interface- 20GB GDDR6 Memory, 160-bit Bandwidth- 6144 CUDA Cores, 26.7 TFLOPS SP Peak
-
product
PCI Express Graphics Cards With NVIDIA RTX 4000 SFF Ada
NVIDIA RTX 4000 SFF Ada
- NVIDIA Ada Lovelace Architecture- Half height, half length design- PCIe Gen4x16 interface- 20GB GDDR6 Memory, 160-bit Bandwidth- 6144 CUDA Cores, 19.2 TFLOPS SP Peak- 192 Tensor Cores, 106.8 TFLOPS- 4 x mDP (mini Display Port 1.4), 1 x USB-C
-
product
PCI Express Graphic Card With NVIDIA RTX 2000E Ada
NVIDIA RTX 2000E Ada
- NVIDIA Ada Lovelace Architecture- 5-year Longevity Support- Half height, half length design- PCIe Gen4x8 Interface- 16GB GDDR6 Memory, 128-bit Bandwidth- 2816 CUDA Cores, 12 TFLOPS SP Peak- 88 Tensor Cores, 191.9 TFLOPS- 4 x mDP (mini Display Port 1.4)
-
product
PCI Express Graphics Card With NVIDIA RTX 2000 Ada
NVIDIA RTX 2000 Ada
- NVIDIA Ada Lovelace Architecture- Half height, half length design- PCIe Gen4x8 interface- 16GB GDDR6 Memory, 128-bit Bandwidth- 2816 CUDA Cores, 12 TFLOPS SP Peak- 88 Tensor Cores, 191.9 TFLOPS- 4 x mDP (mini Display Port 1.4), 1 x USB-C
