Riva TNT2 vs CMP 90HX

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the ranking	not rated	1587
Place by popularity	not in top-100	not in top-100
Architecture	Ampere (2020−2025)	Fahrenheit (1998−2000)
GPU code name	GA102	NV5
Market segment	Workstation	Desktop
Release date	28 July 2021 (4 years ago)	12 October 1999 (26 years ago)

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.

Pipelines / CUDA cores	6400	no data
Core clock speed	1500 MHz	125 MHz
Boost clock speed	1710 MHz	no data
Number of transistors	28,300 million	15 million
Manufacturing process technology	8 nm	250 nm
Power consumption (TDP)	320 Watt	no data
Texture fill rate	342.0	0.25
Floating-point processing power	21.89 TFLOPS	no data
ROPs	80	2
TMUs	200	2
Tensor Cores	200	no data
Ray Tracing Cores	50	no data
L1 Cache	6.3 MB	no data
L2 Cache	5 MB	no data

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Interface	PCIe 1.0 x4	AGP 4x
Length	285 mm	no data
Width	2-slot	1-slot
Supplementary power connectors	2x 8-pin	None

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory type	GDDR6X	SDR
Maximum RAM amount	10 GB	16 MB
Memory bus width	320 Bit	128 Bit
Memory clock speed	1188 MHz	150 MHz
Memory bandwidth	760.3 GB/s	2.4 GB/s
Resizable BAR	+	-

Connectivity and outputs

This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.

Display Connectors

No outputs

1x VGA

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX	12 Ultimate (12_2)	6.0
Shader Model	6.8	no data
OpenGL	4.6	1.2
OpenCL	3.0	N/A
Vulkan	1.3	N/A
CUDA	8.6	-
DLSS	+	-

Pros & cons summary

---

Recency	28 July 2021	12 October 1999
Maximum RAM amount	10 GB	16 MB
Chip lithography	8 nm	250 nm

Vote for your favorite

Do you think we are right or mistaken in our choice? Vote by clicking "Like" button near your favorite graphics card.

---