Radeon Instinct MI100 vs GeForce GTX 1080 Ti

Primary details

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

Place in the ranking	95	not rated
Place by popularity	53	not in top-100
Cost-effectiveness evaluation	19.19	no data
Power efficiency	13.80	no data
Architecture	Pascal (2016−2021)	CDNA 1.0 (2020)
GPU code name	GP102	Arcturus
Market segment	Desktop	Workstation
Release date	10 March 2017 (9 years ago)	16 November 2020 (5 years ago)
Launch price (MSRP)	$699	no data

Cost-effectiveness evaluation

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

Performance to price scatter graph

Currently popular graphics cards are shown for comparison.

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.

Pipelines / CUDA cores	3584	7680
Core clock speed	1481 MHz	1000 MHz
Boost clock speed	1582 MHz	1502 MHz
Number of transistors	11,800 million	50,000 million
Manufacturing process technology	16 nm	7 nm
Power consumption (TDP)	250 Watt	300 Watt
Maximum GPU temperature	91 °C	no data
Texture fill rate	354.4	721.0
Floating-point processing power	11.34 TFLOPS	23.07 TFLOPS
ROPs	88	64
TMUs	224	480
L1 Cache	1.3 MB	1.9 MB
L2 Cache	2.75 MB	8 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	PCIe 3.0 x16	PCIe 4.0 x16
Length	267 mm	267 mm
Width	2-slot	2-slot
Recommended system power (PSU)	600 Watt	no data
Supplementary power connectors	1x 6-pin + 1x 8-pin	2x 8-pin
SLI options	+	-

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	GDDR5X	HBM2
Maximum RAM amount	11 GB	32 GB
Memory bus width	352 Bit	4096 Bit
Memory clock speed	1376 MHz	1200 MHz
Memory bandwidth	484.4 GB/s	1,229 GB/s
Shared memory	-	-
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 HDMI 2.0, 3x DisplayPort 1.4a	No outputs
Multi monitor support	+	no data
HDMI	+	-
G-SYNC support	+	-

Supported technologies

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

GPU Boost	3.0	no data
Ansel	+	-

API and SDK support

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

DirectX	12 (12_1)	N/A
Shader Model	6.8	N/A
OpenGL	4.5	N/A
OpenCL	3.0	2.1
Vulkan	+	N/A
CUDA	+	-

Pros & cons summary

---

Recency	10 March 2017	16 November 2020
Maximum RAM amount	11 GB	32 GB
Chip lithography	16 nm	7 nm
Power consumption (TDP)	250 Watt	300 Watt