Report an Error

NVIDIA RTX A40

Graphics Processor
GA102
Cores
10752
TMUs
336
ROPs
112
Memory Size
48 GB
Memory Type
GDDR6
Bus Width
384 bit
This product is not released yet.
Data on this page may change in the future.
The RTX A40 will be a professional graphics card by NVIDIA, that is expected to launch in 2021. Built on the 8 nm process, and based on the GA102 graphics processor, 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. It features 10752 shading units, 336 texture mapping units, and 112 ROPs. Also included are 336 tensor cores which help improve the speed of machine learning applications. The card also has 84 raytracing acceleration cores. NVIDIA has paired 48 GB GDDR6 memory with the RTX A40, which are connected using a 384-bit memory interface. The GPU is operating at a frequency of 1305 MHz, which can be boosted up to 1755 MHz, memory is running at 1812 MHz (14.5 Gbps effective).
Being a dual-slot card, the NVIDIA RTX A40 draws power from an 8-pin EPS power connector, with power draw rated at 300 W maximum. Display outputs include: 3x DisplayPort. RTX A40 is connected to the rest of the system using a PCI-Express 4.0 x16 interface. The card measures 267 mm in length, 112 mm in width, and features a dual-slot cooling solution.

Graphics Processor

GPU Name
GA102
Architecture
Ampere
Foundry
Samsung
Process Size
8 nm
Transistors
28,300 million
Die Size
628 mm²

Graphics Card

Release Date
2021
Availability
2021
Generation
Quadro
(Ax000)
Production
Unreleased
Bus Interface
PCIe 4.0 x16

Relative Performance

1%
GeForce 210
1%
GeForce 9400 GT
1%
Radeon HD 4550
1%
Radeon HD 5450
1%
Radeon HD 6450
1%
GeForce GT 520
2%
GeForce GT 220
2%
GeForce GT 430
2%
Radeon HD 5570
2%
Radeon HD 4670
2%
GeForce GT 440
3%
GeForce GT 240
3%
GeForce 9600 GT
3%
Radeon HD 5670
3%
GeForce GT 640
3%
GeForce 9800 GT
4%
Radeon HD 6670
4%
Radeon HD 4830
4%
Radeon HD 4770
4%
Radeon HD 4850
4%
GeForce GTS 250
4%
GeForce GTS 450
4%
Radeon HD 5750
5%
Radeon HD 7750
5%
Radeon HD 5770
5%
GeForce GTX 260
5%
Radeon HD 4870
5%
Radeon Vega 8
5%
GeForce GTX 550 Ti
5%
GeForce GTX 650
6%
Radeon HD 5830
6%
Radeon HD 6790
6%
Radeon HD 4890
6%
GeForce GTX 460
6%
Radeon RX Vega 11
6%
GeForce GT 1030
7%
GeForce GTX 275
7%
Radeon HD 7770 GHz Edition
7%
GeForce GTX 280
7%
GeForce GTX 465
7%
Radeon HD 6850
7%
GeForce GTX 285
8%
Radeon HD 5850
8%
GeForce GTX 650 Ti
8%
Radeon HD 7790
8%
Radeon RX 550
8%
GeForce GTX 470
8%
Radeon HD 6870
9%
Radeon HD 5870
9%
GeForce GTX 560 Ti
9%
Radeon HD 4870 X2
10%
GeForce GTX 750 Ti
10%
Radeon HD 6950
10%
GeForce GTX 295
10%
GeForce GTX 650 Ti Boost
10%
Radeon HD 7850
10%
GeForce GTX 480
11%
Radeon HD 6970
11%
Radeon R7 265
11%
Radeon RX 460
11%
Radeon R7 370
11%
GeForce GTX 660
11%
GeForce GTX 570
11%
Radeon RX 560
12%
GeForce GTX 950
12%
Radeon HD 7870 GHz Edition
12%
Radeon R9 270X
13%
GeForce GTX 660 Ti
13%
GeForce GTX 580
13%
GeForce GTX 1050
13%
Radeon HD 7950
13%
Radeon HD 5970
13%
GeForce GTX 760
14%
GeForce GTX 670
15%
GeForce GTX 960
15%
Radeon R9 380
15%
Radeon R9 285
15%
Radeon HD 7970
16%
GeForce GTX 680
16%
GeForce GTX 1050 Ti
16%
GeForce GTX 770
17%
Radeon HD 6990
17%
Radeon R9 280X
17%
GeForce GTX 590
17%
Radeon HD 7970 GHz Edition
19%
GeForce GTX 780
20%
GeForce GTX 1650
21%
Radeon RX 470
22%
Radeon R9 290
23%
Radeon RX 570
23%
Radeon R9 390
23%
Radeon R9 290X
23%
GeForce GTX 970
24%
GeForce GTX TITAN
24%
GeForce GTX 780 Ti
24%
Radeon R9 390X
25%
Radeon HD 7990
25%
Radeon RX 480
25%
GeForce GTX 690
26%
GeForce GTX 1060 6 GB
26%
Radeon RX 5500 OEM
26%
Radeon RX 580
26%
Radeon RX 5500 XT
27%
GeForce GTX 980
27%
GeForce GTX 1650 SUPER
27%
Radeon R9 FURY
28%
Radeon RX 590
30%
Radeon R9 295X2
30%
GeForce GTX 1660
30%
Radeon R9 FURY X
31%
GeForce GTX 980 Ti
32%
GeForce GTX TITAN X
34%
GeForce GTX 1660 SUPER
34%
GeForce GTX 1660 Ti
34%
GeForce GTX 1070
37%
Radeon RX Vega 56
39%
GeForce GTX 1070 Ti
40%
Radeon RX Vega 64
40%
GeForce RTX 2060
40%
GeForce GTX 1080
42%
Radeon RX 5700
45%
GeForce RTX 2060 SUPER
47%
GeForce RTX 2070
48%
Radeon RX 5700 XT
49%
Radeon VII
50%
TITAN X Pascal
52%
GeForce GTX 1080 Ti
52%
GeForce RTX 2070 SUPER
55%
GeForce RTX 2080
59%
GeForce RTX 2080 SUPER
65%
GeForce RTX 2080 Ti
86%
GeForce RTX 3080
94%
GeForce RTX 3090
100%
RTX A40
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
1305 MHz
Boost Clock
1755 MHz
Memory Clock
1812 MHz
14.5 Gbps effective

Memory

Memory Size
48 GB
Memory Type
GDDR6
Memory Bus
384 bit
Bandwidth
695.8 GB/s

Render Config

Shading Units
10752
TMUs
336
ROPs
112
SM Count
84
Tensor Cores
336
RT Cores
84
L1 Cache
128 KB (per SM)
L2 Cache
6 MB

Theoretical Performance

Pixel Rate
196.6 GPixel/s
Texture Rate
589.7 GTexel/s
FP16 (half) performance
37.74 TFLOPS (1:1)
FP32 (float) performance
37.74 TFLOPS
FP64 (double) performance
1,179 GFLOPS (1:32)

Board Design

Slot Width
Dual-slot
Length
267 mm
10.5 inches
Width
112 mm
4.4 inches
TDP
300 W
Suggested PSU
700 W
Outputs
3x DisplayPort
Power Connectors
8-pin EPS

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
2.0
Vulkan
1.2
CUDA
8.5
Shader Model
6.5