AMD Instinct MI300X vs Intel UHD Graphics 770 Mobile Comparison

FAQ

Q: What is the core architectural difference between the AMD Instinct MI300X and the Intel UHD Graphics 770 Mobile?

A: The AMD Instinct MI300X uses the CDNA 3.0 architecture on a 5 nm TSMC process, while the Intel UHD Graphics 770 Mobile uses Generation 12.2 architecture on Intel’s 10 nm process.

Q: How do the two compare in terms of memory capacity and bandwidth?

A: The MI300X has 192 GB of HBM3 memory on an 8192-bit bus, delivering 5.32 TB/s of bandwidth. The Intel UHD Graphics 770 Mobile uses System Shared memory with System Dependent bandwidth, meaning its memory subsystem depends entirely on the host system.

Q: What is the performance percentile ranking for each GPU?

A: The MI300X is at the 100th percentile among all GPUs in the database, while the Intel UHD Graphics 770 Mobile sits at the 50th percentile.

Q: Does the Intel UHD Graphics 770 Mobile support modern graphics APIs?

A: Yes, it supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The MI300X has no graphics API support, with DirectX, OpenGL, and Vulkan all listed as N/A.

Q: What is the difference in shading units and texture mapping units?

A: The MI300X has 19,456 shading units and 1,216 TMUs, while the Intel UHD Graphics 770 Mobile has 256 shading units and 16 TMUs.

Q: Which GPU has a higher boost clock?

A: The MI300X boosts to 2100 MHz from a 1000 MHz base. The Intel UHD Graphics 770 Mobile boosts to 1600 MHz from a 300 MHz base.

Where Each One Wins

The AMD Instinct MI300X dominates in raw compute workloads. Its 81.72 TFLOPS FP32 performance and 81.72 TFLOPS FP16 (1:1) performance place it in a category that the Intel UHD Graphics 770 Mobile cannot approach. The MI300X also delivers 2,553.6 GTexel/s texture rate, whereas the Intel part manages only 25.60 GTexel/s. Any workload that scales with shading units, memory bandwidth, or FP32 throughput belongs to the MI300X.

The Intel UHD Graphics 770 Mobile wins in systems that need a built-in display solution. It provides display outputs (portable device dependent) and full graphics API support, including DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The MI300X has no display outputs and no graphics API support, making it unsuitable for any interactive graphics role. The Intel part also carries a 15 W TDP, which makes it practical for mobile platforms. The MI300X uses 750 W and is an OAM module, requiring a server-class chassis.

The data shows a clean split: compute acceleration versus integrated graphics functionality.

Architecture Differences

The MI300X is built on CDNA 3.0, AMD’s compute-focused architecture. It uses the Aqua Vanjaram chip and is manufactured by TSMC on a 5 nm process. The die contains 153,000 million transistors on a 1017 mm² die, giving a transistor density of 150.4M per mm². This is a dedicated accelerator with no display engine and no graphics API stack.

The Intel UHD Graphics 770 Mobile uses Generation 12.2 architecture from the Raptor Lake family. It is an integrated graphics processor (IGP) built on Intel’s 10 nm process. The database does not list transistor count, die size, or transistor density for this part. Its memory interface is System Shared, meaning it uses the host system’s memory rather than dedicated VRAM. The MI300X uses 192 GB of HBM3 across an 8192-bit bus.

The two parts also differ in their API support. The MI300X lists DirectX, OpenGL, and Vulkan as N/A, confirming it is not designed for rasterization or graphics rendering. The Intel part supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, making it a full-featured graphics solution for mobile systems.

The MI300X has no ROPs and a pixel rate of 0 MPixel/s, while the Intel part has 8 ROPs and a 12.80 GPixel/s pixel rate. This difference reinforces the compute-versus-graphics split between the two architectures.

Specification Differences

The MI300X has a base clock of 1000 MHz and a boost clock of 2100 MHz. The Intel UHD Graphics 770 Mobile has a base clock of 300 MHz and a boost clock of 1600 MHz. Memory clock differs as well: the MI300X runs at 1300 MHz with 5.2 Gbps effective, while the Intel part relies on System Shared memory.

Shading units: 19,456 on the MI300X versus 256 on the Intel part. TMUs: 1,216 versus 16. ROPs: 0 versus 8. The MI300X produces a texture rate of 2,553.6 GTexel/s versus 25.60 GTexel/s for the Intel part. Pixel rate: 0 MPixel/s versus 12.80 GPixel/s. FP32: 81.72 TFLOPS versus 819.2 GFLOPS. FP16: 81.72 TFLOPS (1:1) versus 1.638 TFLOPS (2:1).

Power and form factor differ dramatically. The MI300X has a 750 W TDP, is an OAM Module, and requires a suggested PSU of 1150 W. The Intel part has a 15 W TDP and is an IGP. The MI300X uses PCIe 5.0 x16 as its bus interface, while the Intel part uses a Ring Bus. The MI300X has no display outputs; the Intel part has display outputs that are portable device dependent.

Release dates differ by roughly 11 months. The MI300X launched on 2023-12-05, while the Intel UHD Graphics 770 Mobile launched on 2023-01-03. The Intel part is marked Active in production status and has a successor, Arc Graphics-M. The MI300X has no listed production status and no successor. Its predecessor is Radeon Instinct.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries between these two GPUs. The MI300X has a single recorded OpenCL benchmark score of 317,994 in Geekbench, placing it at the 100th percentile of all GPUs. The Intel UHD Graphics 770 Mobile has no recorded benchmark scores and an average benchmark score of 0.

Without direct comparison data, the nearest rivals for the MI300X provide context. The NVIDIA H200 NVL scores 334,891, which is 5% higher than the MI300X. The NVIDIA B200 scores 345,482, 8% higher. The NVIDIA L40S scores 295,763, 7.5% lower. The NVIDIA RTX 6000 Ada Generation scores 287,237, 10.7% lower. These deltas show the MI300X sits in the upper tier of compute accelerators, within single-digit percentages of the fastest NVIDIA parts in the database.

The Intel UHD Graphics 770 Mobile has no rivals listed and no benchmark scores. Its 50th percentile ranking places it in the middle of the database, but the absence of recorded scores means the database has no quantitative performance data for it.

The FP32 figures illustrate the scale of the gap. The MI300X delivers 81.72 TFLOPS, which is 100 times the 819.2 GFLOPS of the Intel part. The texture rate difference is similar: 2,553.6 GTexel/s versus 25.60 GTexel/s, a 100x gap. Memory bandwidth is 5.32 TB/s for the MI300X, while the Intel part is System Dependent.

The Verdict

The recorded data points to two entirely different products. The AMD Instinct MI300X is a server-class compute accelerator with 192 GB of HBM3 memory, 5.32 TB/s bandwidth, 81.72 TFLOPS FP32, and a 100th percentile benchmark ranking. Its OpenCL score of 317,994 places it within 8% of the fastest NVIDIA accelerators in the database. It has no display outputs, no graphics API support, and consumes 750 W.

The Intel UHD Graphics 770 Mobile is an integrated graphics processor for mobile systems. It uses system shared memory, has a 15 W TDP, and supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. It provides display outputs and has a 50th percentile ranking, but the database contains no benchmark scores for it.

Anyone selecting a GPU for compute workloads should choose the MI300X based on its FP32 throughput, memory capacity, and benchmark percentile. Anyone building a mobile system that needs integrated display output and graphics API support should use the Intel UHD Graphics 770 Mobile. There is no overlap in their intended roles.