NVIDIA CMP 90HX
- Graphics Processor
- GA102
- Cores
- 6400
- TMUs
- 200
- ROPs
- 80
- Memory Size
- 10 GB
- Memory Type
- GDDR6X
- Bus Width
- 320 bit
The CMP 90HX is a professional graphics card by NVIDIA, launched on July 28th, 2021. Built on the 8 nm process, and based on the GA102 graphics processor, in its GA102-100-A1 variant, the card supports DirectX 12 Ultimate. The GA102 graphics processor is a large chip with a die area of 628 mm² and 28,300 million transistors. Unlike the fully unlocked GeForce RTX 3090 Ti, which uses the same GPU but has all 10752 shaders enabled, NVIDIA has disabled some shading units on the CMP 90HX to reach the product's target shader count. It features 6400 shading units, 200 texture mapping units, and 80 ROPs. Also included are 200 tensor cores which help improve the speed of machine learning applications. The card also has 50 raytracing acceleration cores. NVIDIA has paired 10 GB GDDR6X memory with the CMP 90HX, which are connected using a 320-bit memory interface. The GPU is operating at a frequency of 1500 MHz, which can be boosted up to 1710 MHz, memory is running at 1188 MHz (19 Gbps effective).
Being a dual-slot card, the NVIDIA CMP 90HX draws power from 2x 8-pin power connectors, with power draw rated at 320 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. CMP 90HX is connected to the rest of the system using a PCI-Express 4.0 x16 interface. The card measures 285 mm in length, 112 mm in width, and features a dual-slot cooling solution.
Being a dual-slot card, the NVIDIA CMP 90HX draws power from 2x 8-pin power connectors, with power draw rated at 320 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. CMP 90HX is connected to the rest of the system using a PCI-Express 4.0 x16 interface. The card measures 285 mm in length, 112 mm in width, and features a dual-slot cooling solution.
Graphics Processor
Graphics Card
Relative Performance
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.
Clock Speeds
- Base Clock
- 1500 MHz
- Boost Clock
- 1710 MHz
- Memory Clock
-
1188 MHz
19 Gbps effective
Memory
- Memory Size
- 10 GB
- Memory Type
- GDDR6X
- Memory Bus
- 320 bit
- Bandwidth
- 760.3 GB/s
Render Config
- Shading Units
- 6400
- TMUs
- 200
- ROPs
- 80
- SM Count
- 50
- Tensor Cores
- 200
- RT Cores
- 50
- L1 Cache
- 128 KB (per SM)
- L2 Cache
- 5 MB
Theoretical Performance
- Pixel Rate
- 136.8 GPixel/s
- Texture Rate
- 342.0 GTexel/s
- FP16 (half) performance
- 21.89 TFLOPS (1:1)
- FP32 (float) performance
- 21.89 TFLOPS
- FP64 (double) performance
- 342.0 GFLOPS (1:64)
Board Design
- Slot Width
- Dual-slot
- Length
- 285 mm
11.2 inches
- Width
- 112 mm
4.4 inches
- TDP
- 320 W
- Suggested PSU
- 700 W
- Outputs
- No outputs
- Power Connectors
- 2x 8-pin
- Board Number
- PG132 SKU 100
Graphics Features
- DirectX
- 12 Ultimate (12_2)
- OpenGL
- 4.6
- OpenCL
- 3.0
- Vulkan
- 1.2
- CUDA
- 8.6
- Shader Model
- 6.6