H100 PCIe vs Radeon PRO WX 9100

Primary details

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

Place in the ranking	230	not rated
Place by popularity	not in top-100	not in top-100
Cost-effectiveness evaluation	3.73	no data
Power efficiency	9.46	no data
Architecture	GCN 5.0 (2017−2020)	Hopper (2022−2024)
GPU code name	Vega 10	GH100
Market segment	Workstation	Workstation
Release date	10 July 2017 (9 years ago)	22 March 2022 (4 years ago)
Launch price (MSRP)	$1,599	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	4096	7296
Core clock speed	1200 MHz	1065 MHz
Boost clock speed	1500 MHz	1650 MHz
Number of transistors	12,500 million	80,000 million
Manufacturing process technology	14 nm	4 nm
Power consumption (TDP)	230 Watt	350 Watt
Texture fill rate	384.0	752.4
Floating-point processing power	12.29 TFLOPS	24.08 TFLOPS
ROPs	64	24
TMUs	256	456
Tensor Cores	no data	456
L1 Cache	1 MB	21.4 MB
L2 Cache	4 MB	50 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 5.0 x16
Length	267 mm	267 mm
Width	2-slot	2-slot
Supplementary power connectors	1x 6-pin + 1x 8-pin	8-pin EPS

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	HBM2	HBM2e
Maximum RAM amount	16 GB	80 GB
Memory bus width	2048 Bit	5120 Bit
Memory clock speed	945 MHz	1000 MHz
Memory bandwidth	483.8 GB/s	1,280 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

6x mini-DisplayPort

No outputs

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	6.4	N/A
OpenGL	4.6	N/A
OpenCL	2.0	3.0
Vulkan	1.1.125	N/A
CUDA	-	9.0
DLSS	-	+

Synthetic benchmarks

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

---

---

Pros & cons summary

---

Recency	10 July 2017	22 March 2022
Maximum RAM amount	16 GB	80 GB
Chip lithography	14 nm	4 nm
Power consumption (TDP)	230 Watt	350 Watt