Radeon Instinct MI300X vs R9 390

Primary details

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

Place in the ranking	304	not rated
Place by popularity	not in top-100	not in top-100
Cost-effectiveness evaluation	10.12	no data
Power efficiency	5.90	no data
Architecture	GCN 2.0 (2013−2017)	CDNA 3.0 (2023−2024)
GPU code name	Grenada	Aqua Vanjaram
Market segment	Desktop	Workstation
Design	reference	no data
Release date	18 June 2015 (10 years ago)	6 December 2023 (2 years ago)
Launch price (MSRP)	$329	no data

Cost-effectiveness evaluation

The higher the ratio, the better. We use the manufacturer's recommended prices.

Performance to price scatter graph

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	2560	19456
Core clock speed	no data	1000 MHz
Boost clock speed	1000 MHz	2100 MHz
Number of transistors	6,200 million	153,000 million
Manufacturing process technology	28 nm	5 nm
Power consumption (TDP)	275 Watt	750 Watt
Texture fill rate	160.0	2,554
Floating-point processing power	5.12 TFLOPS	81.72 TFLOPS
ROPs	64	no data
TMUs	160	1216
Tensor Cores	no data	1216
L1 Cache	640 KB	4.8 MB
L2 Cache	1024 KB	16 MB
L3 Cache	no data	256 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).

Bus support	PCIe 3.0	no data
Interface	PCIe 3.0 x16	PCIe 5.0 x16
Length	275 mm	no data
Width	2-slot	OAM Module
Supplementary power connectors	1 x 6-pin, 1 x 8-pin	None
Bridgeless CrossFire	+	-

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	GDDR5	HBM3
High bandwidth memory (HBM)	-	no data
Maximum RAM amount	0 MB	192 GB
Memory bus width	512 Bit	8192 Bit
Memory clock speed	1000 MHz	2525 MHz
Memory bandwidth	384 GB/s	5,171 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	2x DVI, 1x HDMI, 1x DisplayPort	No outputs
Eyefinity	+	-
Number of Eyefinity displays	6	no data
HDMI	+	-
DisplayPort support	+	-

Supported technologies

Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.

CrossFire	+	-
FreeSync	+	-
PowerTune	+	-
TrueAudio	+	-
VCE	+	-
DDMA audio	+	no data

API and SDK support

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

DirectX	DirectX® 12	N/A
Shader Model	6.3	N/A
OpenGL	4.6	N/A
OpenCL	2.0	3.0
Vulkan	+	N/A
Mantle	+	-
DLSS	-	+

Pros & cons summary

---

Recency	18 June 2015	6 December 2023
Chip lithography	28 nm	5 nm
Power consumption (TDP)	275 Watt	750 Watt