ATI WinTurbo vs RTX A40

Primary details

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

Place in the ranking	not rated	not rated
Place by popularity	not in top-100	not in top-100
Architecture	Ampere (2020−2025)	Mach (1992−1997)
GPU code name	GA102	Mach64
Market segment	Workstation	Desktop
Release date	5 October 2020 (5 years ago)	1995 (31 years ago)
Launch price (MSRP)	no data	$699

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	10752	no data
Core clock speed	1305 MHz	40 MHz
Boost clock speed	1755 MHz	no data
Number of transistors	28,300 million	1 million
Manufacturing process technology	8 nm	600 nm
Power consumption (TDP)	300 Watt	no data
Texture fill rate	589.7	no data
Floating-point processing power	37.74 TFLOPS	no data
ROPs	112	1
TMUs	336	no data
Tensor Cores	336	no data
Ray Tracing Cores	84	no data
L1 Cache	10.5 MB	no data
L2 Cache	6 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 4.0 x16	PCI
Length	267 mm	no data
Width	2-slot	1-slot
Supplementary power connectors	8-pin EPS	no data

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	GDDR6	VRAM
Maximum RAM amount	48 GB	2 MB
Memory bus width	384 Bit	64 Bit
Memory clock speed	1812 MHz	40 MHz
Memory bandwidth	695.8 GB/s	320.0 MB/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

3x DisplayPort

1x VGA

API and SDK support

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

DirectX	12 Ultimate (12_2)	N/A
Shader Model	6.5	no data
OpenGL	4.6	N/A
OpenCL	2.0	N/A
Vulkan	1.2	N/A
CUDA	8.6	-
DLSS	+	-

Pros & cons summary

---

Maximum RAM amount	48 GB	2 MB
Chip lithography	8 nm	600 nm