AMD Instinct MI355X vs Intel Arc 130T Mobile Comparison

Head-to-Head Benchmarks

The recorded data contains no direct benchmark comparisons between the AMD Instinct MI355X and the Intel Arc 130T Mobile. Both products have an empty head-to-head benchmark array, and neither holds a win count in direct competition. This absence of measured results is itself informative: the two devices occupy entirely different segments of the hardware landscape, and no shared workload has been recorded in the database to produce a comparative score.

The average benchmark score for both entries is zero, and both sit at the 50th percentile against all GPUs in the database. This percentile figure reflects the lack of recorded performance data rather than a true performance parity. Without measured frames per second, compute throughput, or synthetic scores, any direct numerical comparison would be fabricated. The database simply has no such measurements to present.

What can be stated from the specification data is the theoretical compute gap. The MI355X delivers 78.64 TFLOPS of FP32 performance, while the Arc 130T Mobile delivers 3.942 TFLOPS. That is a 74.698 TFLOPS difference in favor of the AMD part. In FP16, the MI355X again outputs 78.64 TFLOPS (1:1 ratio), whereas the Intel part reaches 7.885 TFLOPS (2:1 ratio). The AMD accelerator exceeds the Intel mobile GPU by a factor of roughly 20 in FP32 throughput based on the recorded figures.

Texture rate tells a similar story. The MI355X processes 2,457.6 GTexel/s, compared to 123.2 GTexel/s for the Arc 130T Mobile. Pixel rate, however, flips in the other direction: the Intel part shows 61.60 GPixel/s, while the MI355X shows 0 MPixel/s, reflecting its lack of traditional raster output units. The AMD part has 1,024 texture mapping units and 16,384 shading units, while the Intel part has 56 TMUs and 896 shading units.

FAQ

Q: Why does the AMD Instinct MI355X have a 0 MPixel/s pixel rate?

A: The MI355X lists 0 ROPs (raster output units) in its specification, and the pixel rate is recorded as 0 MPixel/s. This indicates the accelerator is not designed for traditional rasterized graphics output, consistent with its role as a compute-focused Instinct product with no display outputs.

Q: What memory configuration does each product use?

A: The MI355X uses 288 GB of HBM3e memory on an 8192-bit bus, delivering 8.19 TB/s of bandwidth. The Arc 130T Mobile uses System Shared memory, with the memory type, bus width, and bandwidth all listed as System Dependent.

Q: Which product supports DirectX and Vulkan?

A: The Arc 130T Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The MI355X lists N/A for DirectX, OpenGL, and Vulkan, meaning no graphics API support is recorded for the AMD part.

Q: What is the clock speed difference between the two?

A: The MI355X has a base clock of 1000 MHz and a boost clock of 2400 MHz. The Arc 130T Mobile has a base clock of 300 MHz and a boost clock of 2200 MHz. The AMD part's boost clock is 200 MHz higher, and its base clock is 700 MHz higher.

Q: Are both products currently in production?

A: The Arc 130T Mobile has a production status of Active. The MI355X has a null production status in the database, so no current production status is recorded for it.

Q: What is the power draw of each product?

A: The MI355X has a TDP of 1400 W with a suggested PSU of 1800 W. The Arc 130T Mobile has a TDP of 35 W and no suggested PSU listed.

Architecture Differences

The two products come from fundamentally different architectural lineages. The MI355X is built on CDNA 4.0 architecture, AMD's compute-focused design for data center accelerators. The chip is designated MI350 256CU, part of the Instinct (MIx) generation. The Arc 130T Mobile uses Xe-LPG+ architecture, Intel's graphics architecture for mobile integrated GPUs, built on the Arrow Lake-H chip and part of the Arc Graphics-M (Arrow Lake) generation.

The manufacturing processes differ. The MI355X uses a 3 nm process node at TSMC, while the Arc 130T Mobile uses a 5 nm process node, also at TSMC. The AMD part integrates 185,000 million transistors on a 2380 mm² die, yielding a transistor density of 77.7M per mm². The Intel part has unknown transistor count and die size in the recorded data.

Compute resources diverge sharply. The MI355X contains 16,384 shading units, 1,024 TMUs, and zero ROPs. The Arc 130T Mobile contains 896 shading units, 56 TMUs, and 28 ROPs. The Intel part additionally includes 7 ray tracing cores, while the MI355X lists no RT cores. Neither product lists tensor cores in the database.

Memory architecture is another division point. The MI355X uses dedicated HBM3e memory totaling 288 GB with a 8192-bit bus. The Arc 130T Mobile relies on System Shared memory, with bandwidth described only as System Dependent. This means the Intel GPU shares system memory with the CPU, while the AMD accelerator has its own high-bandwidth memory pool.

The MI355X has a memory clock of 2000 MHz (8 Gbps effective), while the Arc 130T Mobile has no dedicated memory clock, listing System Shared instead. The AMD part connects via PCIe 5.0 x16, whereas the Intel part is an IGP, meaning it is integrated into the processor package and does not use a discrete bus interface.

Graphical features also separate the two. The MI355X has no display outputs and no graphics API support. The Arc 130T Mobile has display outputs described as Portable Device Dependent and supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4. This positions the Intel product for mobile graphics rendering, while the AMD product is a pure compute accelerator.

Specification Differences

The physical form factors differ. The MI355X is an OAM Module with dimensions of 102 mm in length and 165 mm in width. The Arc 130T Mobile is an IGP with no recorded dimensions. The AMD module has no power connectors listed, while the Intel IGP has a null power connector field.

The MI355X has a release date of 2025-06-11, and the Arc 130T Mobile has a release date of 2025-01-12. The Intel part was released earlier by roughly five months. The MI355X predecessor is Radeon Instinct, and the Arc 130T Mobile predecessor is HD Graphics-M. Neither has a recorded successor.

The MI355X TDP is 1400 W, versus 35 W for the Arc 130T Mobile. The suggested PSU for the AMD part is 1800 W, and the Intel part has no suggested PSU. The MI355X has a null launch MSRP, and the Arc 130T Mobile also has a null launch MSRP, so no price data exists for either.

The FP16 ratios differ. The MI355X achieves FP16 at a 1:1 ratio relative to FP32, meaning both are 78.64 TFLOPS. The Arc 130T Mobile achieves FP16 at a 2:1 ratio, meaning FP16 throughput is 7.885 TFLOPS, double its 3.942 TFLOPS FP32 figure. This indicates the Intel architecture uses packed FP16 math, while the AMD architecture does not.

The MI355X has no RT cores, while the Arc 130T Mobile has 7. The MI355X has 0 ROPs, the Arc 130T Mobile has 28. The MI355X has 1,024 TMUs, the Arc 130T Mobile has 56. The MI355X has 16,384 shading units, the Arc 130T Mobile has 896.

Where Each One Wins

From the specification data, the AMD Instinct MI355X wins in every compute throughput category. FP32 performance is 78.64 TFLOPS versus 3.942 TFLOPS. FP16 performance is 78.64 TFLOPS versus 7.885 TFLOPS. Texture rate is 2,457.6 GTexel/s versus 123.2 GTexel/s. Memory bandwidth is 8.19 TB/s versus System Dependent. Memory capacity is 288 GB versus System Shared. The MI355X also has a smaller process node at 3 nm versus 5 nm, a higher boost clock at 2400 MHz versus 2200 MHz, and a higher base clock at 1000 MHz versus 300 MHz.

The Intel Arc 130T Mobile wins in areas related to graphics output and power efficiency. It has 28 ROPs versus 0, delivering a 61.60 GPixel/s pixel rate compared to 0 MPixel/s. It supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, whereas the MI355X has no graphics API support. It has 7 ray tracing cores, while the AMD part has none. Its TDP is 35 W versus 1400 W, a difference of 1365 W, which makes it suitable for mobile integration. It also has a production status of Active, whereas the MI355X has no recorded production status.

The Arc 130T Mobile is an IGP, meaning it is integrated into a processor and uses system memory. This makes it appropriate for portable devices where separate memory and discrete power delivery are not available. The MI355X is an OAM Module with dedicated memory and a 1400 W TDP, indicating a data center accelerator designed for sustained compute workloads.

The Verdict

The data indicates two products with no overlapping use cases. The AMD Instinct MI355X delivers 78.64 TFLOPS FP32 performance, 288 GB of HBM3e memory, and 8.19 TB/s of bandwidth, all within a 1400 W TDP. This configuration targets high-performance compute environments where massive memory capacity and bandwidth are required. The Intel Arc 130T Mobile delivers 3.942 TFLOPS FP32, 7.885 TFLOPS FP16, and 61.60 GPixel/s pixel rate within a 35 W TDP, with graphics API support and ray tracing cores for mobile rendering.

For compute-intensive workloads such as large-scale matrix operations, the MI355X is the only viable choice based on the recorded figures. Its FP32 throughput is approximately 20 times that of the Intel part, and its memory system is dedicated rather than shared. The 288 GB capacity and 8192-bit bus provide a memory subsystem that the System Shared configuration of the Arc 130T Mobile cannot match.

For graphics-oriented tasks on portable devices, the Arc 130T Mobile is the appropriate selection. It has ROPs, ray tracing cores, and full DirectX 12 Ultimate support, none of which the MI355X offers. The 35 W TDP allows integration into laptops and other mobile form factors, while the 1400 W TDP of the MI355X requires data center infrastructure.

The MI355X has no display outputs and no graphics APIs, so it cannot drive a display. The Arc 130T Mobile has display outputs described as Portable Device Dependent, meaning it can output to displays on devices where it is installed. This fundamental difference determines the product choice: the MI355X is for compute servers, the Arc 130T Mobile is for client devices.

Neither product has a recorded launch MSRP, and neither has recorded benchmark scores. The nearest rivals arrays are empty for both, so no comparative percentile data against specific competitors exists. The 50th percentile ranking for both against all GPUs reflects the absence of benchmark data, not a measured performance position. Buyers should rely on the architectural and specification differences outlined above, as no direct performance measurements are available in the database.