L40 vs ATI Radeon 9800

Place in the ranking	1489	61
Place by popularity	not in top-100	not in top-100
Power efficiency	0.29	13.75
Architecture	R300 (2003−2008)	Ada Lovelace (2022−2024)
GPU code name	R350	AD102
Market segment	Desktop	Workstation
Release date	1 March 2003 (22 years ago)	13 October 2022 (3 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	no data	18176
Core clock speed	325 MHz	735 MHz
Boost clock speed	no data	2490 MHz
Number of transistors	117 million	76,300 million
Manufacturing process technology	150 nm	4 nm
Power consumption (TDP)	37 Watt	300 Watt
Texture fill rate	2.600	1,414
Floating-point processing power	no data	90.52 TFLOPS
ROPs	8	192
TMUs	8	568
Tensor Cores	no data	568
Ray Tracing Cores	no data	142
L1 Cache	no data	17.8 MB
L2 Cache	no data	96 MB

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	AGP 8x	PCIe 4.0 x16
Length	no data	267 mm
Width	1-slot	2-slot
Supplementary power connectors	1x Molex	1x 16-pin

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	DDR	GDDR6
Maximum RAM amount	128 MB	48 GB
Memory bus width	256 Bit	384 Bit
Memory clock speed	290 MHz	2250 MHz
Memory bandwidth	18.56 GB/s	864.0 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

1x DVI, 1x VGA, 1x S-Video

4x DisplayPort 1.4a

API and SDK support

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

DirectX	9.0 (9_0)	12 Ultimate (12_2)
Shader Model	no data	6.7
OpenGL	2.0	4.6
OpenCL	N/A	3.0
Vulkan	N/A	1.3
CUDA	-	8.9
DLSS	-	+

Synthetic benchmarks

Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.

Combined synthetic benchmark score

This is our combined benchmark score.

ATI 9800 0.14

L40 53.72
+38271%

Passmark

This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.

ATI 9800 57
Samples: 1

L40 22466
+39314%

Gaming performance

Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.

Pros & cons summary

Performance score	0.14	53.72
Recency	1 March 2003	13 October 2022
Maximum RAM amount	128 MB	48 GB
Chip lithography	150 nm	4 nm
Power consumption (TDP)	37 Watt	300 Watt

ATI 9800 has 710.8% lower power consumption.

L40, on the other hand, has a 38271.4% higher aggregate performance score, an age advantage of 19 years, a 38300% higher maximum VRAM amount, and a 3650% more advanced lithography process.

The L40 is our recommended choice as it beats the Radeon 9800 in performance tests.

Be aware that Radeon 9800 is a desktop graphics card while L40 is a workstation one.