Report an Error

AMD Radeon Pro 450

Graphics Processor
Baffin
Cores
640
TMUs
40
ROPs
16
Memory Size
2 GB
Memory Type
GDDR5
Bus Width
128 bit
The Radeon Pro 450 is a professional graphics card by AMD, launched in October 2016. Built on the 14 nm process, and based on the Baffin graphics processor, in its Baffin LE variant, the card supports DirectX 12.0. The Baffin graphics processor is an average sized chip with a die area of 123 mm² and 3,000 million transistors. Unlike the fully unlocked Radeon RX 460 1024SP, which uses the same GPU but has all 1024 shaders enabled, AMD has disabled some shading units on the Radeon Pro 450 to reach the product's target shader count. It features 640 shading units, 40 texture mapping units and 16 ROPs. AMD has placed 2,048 MB GDDR5 memory on the card, which are connected using a 128-bit memory interface. The GPU is operating at a frequency of 800 MHz, memory is running at 1270 MHz.
Being a mxm module card, its power draw is rated at 35 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Radeon Pro 450 is connected to the rest of the system using a PCI-Express 3.0 x8 interface.

Graphics Processor

GPU Name
Baffin
GPU Variant
Baffin LE
Architecture
GCN 4.0
Foundry
TSMC
Process Size
14 nm
Transistors
3,000 million
Die Size
123 mm²

Graphics Card

Release Date
Oct 30th, 2016
Generation
Radeon Pro
(400)
Production
Active
Bus Interface
PCIe 3.0 x8

Relative Performance

8%
GeForce 210
10%
GeForce 9400 GT
12%
Radeon HD 4550
15%
Radeon HD 5450
18%
Radeon HD 6450
19%
GeForce GT 520
24%
GeForce GT 220
31%
GeForce GT 430
31%
Radeon HD 5570
34%
Radeon HD 4670
36%
GeForce GT 440
37%
GeForce GT 240
42%
GeForce 9600 GT
45%
Radeon HD 5670
48%
GeForce GT 640
49%
GeForce 9800 GT
51%
Radeon HD 6670
53%
Radeon HD 4830
57%
Radeon HD 4770
60%
Radeon HD 4850
61%
GeForce GTS 250
63%
GeForce GTS 450
65%
Radeon HD 5750
74%
Radeon HD 7750
75%
Radeon HD 5770
76%
GeForce GTX 260
77%
Radeon HD 4870
77%
Radeon Vega 8
78%
GeForce GTX 550 Ti
79%
GeForce GTX 650
83%
Radeon HD 5830
88%
Radeon HD 6790
89%
Radeon HD 4890
92%
GeForce GTX 460
93%
Radeon RX Vega 11
94%
GeForce GT 1030
95%
GeForce GTX 275
95%
Radeon HD 7770 GHz Edition
95%
GeForce GTX 280
97%
GeForce GTX 465
100%
Radeon Pro 450
102%
Radeon HD 6850
104%
GeForce GTX 285
111%
Radeon HD 5850
113%
GeForce GTX 650 Ti
113%
Radeon HD 7790
118%
Radeon RX 550
119%
GeForce GTX 470
123%
Radeon HD 6870
131%
Radeon HD 5870
135%
GeForce GTX 560 Ti
136%
Radeon HD 4870 X2
138%
GeForce GTX 750 Ti
139%
Radeon HD 6950
144%
GeForce GTX 295
146%
GeForce GTX 650 Ti Boost
147%
Radeon HD 7850
149%
GeForce GTX 480
156%
Radeon HD 6970
159%
Radeon R7 265
162%
Radeon RX 460
162%
Radeon R7 370
162%
GeForce GTX 660
163%
GeForce GTX 570
166%
Radeon RX 560
176%
GeForce GTX 950
177%
Radeon HD 7870 GHz Edition
182%
Radeon R9 270X
184%
GeForce GTX 660 Ti
185%
GeForce GTX 580
186%
GeForce GTX 1050
187%
Radeon HD 7950
190%
Radeon HD 5970
196%
GeForce GTX 760
211%
GeForce GTX 670
216%
GeForce GTX 960
222%
Radeon R9 380
223%
Radeon R9 285
225%
Radeon HD 7970
227%
GeForce GTX 680
233%
GeForce GTX 1050 Ti
239%
GeForce GTX 770
244%
Radeon HD 6990
250%
Radeon R9 280X
254%
GeForce GTX 590
254%
Radeon HD 7970 GHz Edition
281%
GeForce GTX 780
291%
GeForce GTX 1650
310%
Radeon RX 470
314%
Radeon R9 290
331%
Radeon RX 570
335%
Radeon R9 390
337%
Radeon R9 290X
341%
GeForce GTX 970
346%
GeForce GTX TITAN
350%
GeForce GTX 780 Ti
355%
Radeon R9 390X
357%
Radeon HD 7990
359%
Radeon RX 480
362%
GeForce GTX 690
381%
Radeon RX 580
389%
GeForce GTX 980
394%
Radeon R9 FURY
394%
GeForce GTX 1060 6 GB
412%
Radeon RX 590
433%
Radeon R9 295X2
436%
GeForce GTX 1660
441%
Radeon R9 FURY X
448%
GeForce GTX 980 Ti
460%
GeForce GTX TITAN X
500%
GeForce GTX 1660 Ti
500%
GeForce GTX 1070
533%
Radeon RX Vega 56
565%
GeForce GTX 1070 Ti
581%
Radeon RX Vega 64
589%
GeForce GTX 1080
589%
GeForce RTX 2060
613%
Radeon RX 5700
662%
GeForce RTX 2060 SUPER
686%
GeForce RTX 2070
702%
Radeon RX 5700 XT
710%
Radeon VII
729%
TITAN X Pascal
750%
GeForce GTX 1080 Ti
759%
GeForce RTX 2070 SUPER
807%
GeForce RTX 2080
855%
GeForce RTX 2080 SUPER
944%
GeForce RTX 2080 Ti
Based on TPU review data: "Performance Summary" at 1920x1080
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

GPU Clock
800 MHz
Memory Clock
1270 MHz
5080 MHz effective

Memory

Memory Size
2 GB
Memory Type
GDDR5
Memory Bus
128 bit
Bandwidth
81.28 GB/s

Render Config

Shading Units
640
TMUs
40
ROPs
16
Compute Units
10
L1 Cache
16 KB (per CU)
L2 Cache
1024 KB

Theoretical Performance

Pixel Rate
12.80 GPixel/s
Texture Rate
32.00 GTexel/s
FP16 (half) performance
1,024 GFLOPS (1:1)
FP32 (float) performance
1,024 GFLOPS
FP64 (double) performance
64.00 GFLOPS (1:16)

Board Design

Slot Width
MXM Module
TDP
35 W
Outputs
No outputs

Graphics Features

DirectX
12.0 (12_0)
OpenGL
4.6
OpenCL
2.0
Vulkan
1.1.119
Shader Model
6.4

Baffin GPU Notes

Architecture Codename: Arctic Islands
Codename: Polaris 11 (Kauai/Maui / RacerX)
CLRX Version: GCN 1.2
Graphics/Compute: GFX8 (gfx803)
Display Core Engine: 11.2
Unified Video Decoder: 6.3
Video Compression Engine: 3.4