AMD Instinct MI355X vs Intel Arc 130V Mobile Comparison

Head-to-Head Benchmarks

The recorded data for the AMD Instinct MI355X and the Intel Arc 130V Mobile shows no benchmark entries for either part. Neither product has a single submitted benchmark score, an average benchmark score, or a list of nearest rivals. The head-to-head benchmark table is empty, and the win counts for each side are zero. This absence of measured performance data means that a direct numerical comparison of frame rates, compute throughput, or application-specific results cannot be constructed from the database.

The only quantifiable performance indicators available are the theoretical peak rates listed in the specification fields. The AMD Instinct MI355X delivers 78.64 TFLOPS of FP32 compute and the same 78.64 TFLOPS for FP16, with a 1:1 ratio. The Intel Arc 130V Mobile delivers 3.315 TFLOPS of FP32 and 6.630 TFLOPS of FP16, with a 2:1 ratio. The FP32 gap is significant: the AMD part is roughly 23.7 times higher in raw single-precision throughput. In FP16, the AMD part is about 11.9 times higher. These figures represent theoretical peaks, not measured application results, but they are the only comparable numeric data points in the pack.

Texture and pixel rates follow the same pattern. The AMD Instinct MI355X has a texture rate of 2,457.6 GTexel/s, while the Intel Arc 130V Mobile reaches 103.6 GTexel/s. The AMD part is roughly 23.7 times higher in texture throughput. Pixel rate is a more complicated case. The AMD part lists 0 MPixel/s because it has no ROPs, while the Intel part lists 51.80 GPixel/s from its 28 ROPs. In this one metric, the Intel product holds a clear advantage, since the AMD accelerator is not designed for rasterized pixel output at all.

Memory bandwidth is another area with a stark divide. The AMD Instinct MI355X uses 288 GB of HBM3e on an 8192-bit bus, producing 8.19 TB/s of bandwidth. The Intel Arc 130V Mobile uses system shared memory with system dependent bandwidth, a configuration that cannot match the dedicated accelerator's memory subsystem. The Intel part's memory performance is entirely dependent on the host system, while the AMD part has a fixed, specified bandwidth.

Clock speeds differ substantially. The AMD part has a base clock of 1000 MHz and a boost of 2400 MHz. The Intel part has a base of 300 MHz and a boost of 1850 MHz. The higher boost on the AMD part contributes to its compute advantage, but the architectural differences are far more important than the clock delta.

Where Each One Wins

The AMD Instinct MI355X wins in raw compute throughput. Its FP32 and FP16 figures of 78.64 TFLOPS each are the highest numbers in the comparison, and its texture rate of 2,457.6 GTexel/s dominates the Intel part's 103.6 GTexel/s. The memory subsystem is also a clear win for AMD. The 8.19 TB/s of bandwidth from HBM3e is a dedicated, fixed resource, whereas the Intel part relies on shared system memory with no guaranteed bandwidth. For workloads that scale with FP32 or FP16 arithmetic, texture filtering, or memory bandwidth, the data points to the AMD accelerator as the stronger part.

The Intel Arc 130V Mobile wins in the areas where the AMD part is not designed to compete. It has 28 ROPs and a pixel rate of 51.80 GPixel/s, while the AMD part has zero ROPs and a pixel rate of 0 MPixel/s. The Intel part also supports modern graphics APIs: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The AMD part lists N/A for all three APIs. The Intel part is an IGP with portable device dependent display outputs, meaning it can drive displays in a mobile system. The AMD part has no display outputs at all. For any rasterization, pixel processing, or graphics API compatibility, the Intel part is the only one with capabilities in the recorded data.

The Intel part also wins on power envelope. It has a TDP of 37 W, while the AMD part has a TDP of 1400 W. The AMD part requires a suggested PSU of 1800 W and uses an OAM module slot with no power connectors (power is presumably delivered through the module interface). The Intel part is an IGP with no separate power connector and no suggested PSU. These figures do not speak to performance per watt, but they do indicate that the Intel part is designed for a low-power mobile context, while the AMD part is designed for an accelerator chassis with substantial power delivery.

Architecture Differences

The two parts come from different architectural lineages. The AMD Instinct MI355X uses the CDNA 4.0 architecture on the MI350 256CU chip. The Intel Arc 130V Mobile uses the Xe2-LPG architecture on the Lunar Lake chip. Both are fabricated on a 3 nm process at TSMC, which is the only shared node detail in the pack.

The AMD chip is much larger. The die size is 2380 mm² with 185,000 million transistors, giving a transistor density of 77.7 million per mm². The Intel chip has a die size of 172 mm², and its transistor count is listed as unknown, so density cannot be calculated. The AMD die is about 13.8 times larger by area.

Compute resources differ sharply. The AMD part has 16,384 shading units, 1,024 TMUs, and zero ROPs. The Intel part has 896 shading units, 56 TMUs, and 28 ROPs. The AMD part also has 7 ray tracing cores listed as null, while the Intel part lists 7 RT cores. Neither part lists tensor cores. The AMD part has no pixel rate because of its zero ROP count, while the Intel part has a functional pixel pipeline.

Memory architecture is fundamentally different. The AMD part uses 288 GB of HBM3e on an 8192-bit bus with a fixed 8.19 TB/s bandwidth and a memory clock of 2000 MHz (8 Gbps effective). The Intel part uses system shared memory, with no dedicated VRAM, no fixed bus width, and bandwidth described only as system dependent. The AMD memory clock is specified, the Intel memory clock is not.

Form factors and interfaces diverge. The AMD part is an OAM module, 102 mm long and 165 mm wide, using PCIe 5.0 x16, with no display outputs. The Intel part is an IGP with an IGP bus interface, no dimensions listed, and display outputs described as portable device dependent. The AMD part has no power connectors, while the Intel part has no power connector field filled. The AMD part has no DirectX, OpenGL, or Vulkan support listed, while the Intel part supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Release timing differs. The AMD part has a release date of June 11, 2025, and its predecessor is Radeon Instinct. The Intel part has a release date of September 23, 2024, and its predecessor is HD Graphics-M. The Intel part is marked as Active in production status, while the AMD part has no production status listed.

FAQ

Q: Which GPU has higher FP32 compute?

A: The AMD Instinct MI355X has an FP32 throughput of 78.64 TFLOPS, compared to 3.315 TFLOPS for the Intel Arc 130V Mobile.

Q: Does the AMD Instinct MI355X support DirectX?

A: No. The database lists DirectX as N/A for the AMD part, while the Intel Arc 130V Mobile supports DirectX 12 Ultimate (12_2).

Q: How much memory does each GPU have?

A: The AMD Instinct MI355X has 288 GB of HBM3e. The Intel Arc 130V Mobile uses system shared memory, with the size, type, bus width, and bandwidth all depending on the host system.

Q: What is the power requirement for the AMD Instinct MI355X?

A: The AMD part has a TDP of 1400 W and a suggested PSU of 1800 W. The Intel Arc 130V Mobile has a TDP of 37 W and no suggested PSU listed.

Q: Can the Intel Arc 130V Mobile output to displays?

A: The database lists display outputs as portable device dependent. The AMD Instinct MI355X lists no display outputs.

Q: What process node do both chips use?

A: Both the AMD Instinct MI355X and the Intel Arc 130V Mobile are fabricated on a 3 nm process at TSMC.

Specification Differences

The following fields differ between the AMD Instinct MI355X and the Intel Arc 130V Mobile:

• Chip: MI350 256CU vs Lunar Lake
• Architecture: CDNA 4.0 vs Xe2-LPG
• Generation: Instinct (MIx) vs Arc Graphics-M (Lunar Lake)
• Process node: Both 3 nm, same foundry (TSMC) (no difference)
• Transistors: 185,000 million vs unknown
• Die size: 2380 mm² vs 172 mm²
• Base clock: 1000 MHz vs 300 MHz
• Boost clock: 2400 MHz vs 1850 MHz
• Memory clock: 2000 MHz (8 Gbps effective) vs system shared
• Memory size: 288 GB vs system shared
• Memory type: HBM3e vs system shared
• Memory bus width: 8192 bit vs system shared
• Memory bandwidth: 8.19 TB/s vs system dependent
• Shading units: 16,384 vs 896
• TMUs: 1,024 vs 56
• ROPs: 0 vs 28
• RT cores: null vs 7
• Pixel rate: 0 MPixel/s vs 51.80 GPixel/s
• Texture rate: 2,457.6 GTexel/s vs 103.6 GTexel/s
• FP32: 78.64 TFLOPS vs 3.315 TFLOPS
• FP16: 78.64 TFLOPS (1:1) vs 6.630 TFLOPS (2:1)
• TDP: 1400 W vs 37 W
• Slot width: OAM Module vs IGP
• Power connectors: None vs null
• Suggested PSU: 1800 W vs null
• Bus interface: PCIe 5.0 x16 vs IGP
• Display outputs: No outputs vs portable device dependent
• DirectX: N/A vs 12 Ultimate (12_2)
• OpenGL: N/A vs 4.6
• Vulkan: N/A vs 1.4
• Dimensions: 102 mm x 165 mm vs null
• Production status: null vs Active
• Release date: June 11, 2025 vs September 23, 2024
• Predecessor: Radeon Instinct vs HD Graphics-M

The Verdict

The recorded data shows two products with almost no overlap in purpose. The AMD Instinct MI355X is a dedicated accelerator with 288 GB of HBM3e, 8.19 TB/s of bandwidth, 78.64 TFLOPS of FP32, and 78.64 TFLOPS of FP16. It has no display outputs, no graphics API support, no ROPs, and a 1400 W TDP. The Intel Arc 130V Mobile is an integrated graphics processor with 28 ROPs, 7 RT cores, DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4 support, a 37 W TDP, and system shared memory.

For compute-heavy workloads that need maximum FP32 or FP16 throughput, large dedicated memory capacity, and high memory bandwidth, the AMD part is the only option in this comparison. Its numbers are orders of magnitude higher in every compute and memory metric. For a mobile system that needs graphics API support, pixel output, ray tracing, and low power consumption, the Intel part is the only option. The database contains no benchmark scores or rival comparisons for either product, so these conclusions rest entirely on the specification data. The choice depends on the workload: an accelerator environment for the AMD part, a portable display environment for the Intel part.