AMD Radeon R9 M375X vs Intel UHD Graphics 750 Comparison

Where Each One Wins

The benchmark separation between the AMD Radeon R9 M375X and the Intel UHD Graphics 750 is clear but not absolute. The AMD part wins in both recorded workloads, but the margin varies sharply by API. In Geekbench OpenCL, the R9 M375X scores 8273 against 6743 for the Intel part, a 22.7% advantage. That is a decisive, workload-class difference. In Geekbench Vulkan, the gap narrows to just 2.9%: AMD scores 8377, Intel scores 8138. So the R9 M375X is the stronger choice for compute-heavy OpenCL workloads, while the Vulkan result suggests the Intel iGPU can compete much more closely when the API leans on modern driver and hardware scheduling.

The AMD Radeon R9 M375X also wins on overall average benchmark score. Its average is 8325, while the Intel UHD Graphics 750 averages 7441. That is a 884-point difference in the database. The AMD part sits at the 43rd percentile of all GPUs, the Intel part at the 40th. Neither is a high-flying performer, but the AMD part holds a measurable edge in aggregate.

Where the Intel part might be more attractive is not in raw score but in platform context. It is an integrated graphics processor with a 15 W TDP, a Ring Bus interface, and system-shared memory. The AMD part is a discrete mobile GPU with 2 GB of dedicated GDDR5. For a user who already owns a Rocket Lake CPU, the Intel UHD Graphics 750 costs nothing extra and delivers a usable Vulkan score. For a user comparing standalone GPU capability, the R9 M375X is the clear winner in both recorded tests.

Architecture Differences

The two parts come from different architectural generations and design philosophies. The AMD Radeon R9 M375X uses the Tropo chip built on GCN 1.0 architecture, manufactured on a 28 nm process at TSMC. It packs 1,500 million transistors on a 123 mm² die, giving a transistor density of 12.2 million per square millimeter. The Intel UHD Graphics 750 uses the Rocket Lake chip with Generation 12.1 architecture, manufactured on Intel's 14 nm+++ process. The database does not list transistor count or die size for the Intel part, so no direct comparison is possible there.

Compute resources differ substantially. The AMD part has 640 shading units, 40 texture mapping units, and 16 ROPs. The Intel part has 256 shading units, 16 TMUs, and 8 ROPs. That is 2.5 times more shaders, 2.5 times more TMUs, and 2 times more ROPs on the AMD side. Pixel rate reflects this: the R9 M375X outputs 16.24 GPixel/s versus 10.40 GPixel/s for the Intel part. Texture rate is similarly lopsided: 40.60 GTexel/s versus 20.80 GTexel/s. FP32 compute is 1,299.2 GFLOPS for AMD versus 665.6 GFLOPS for Intel, so AMD has roughly double the single-precision throughput. However, the Intel part lists FP16 at 1,331.2 GFLOPS with a 2:1 ratio, a feature the AMD part does not record.

Clocks differ by design. The AMD R9 M375X runs at a 925 MHz base with a 1015 MHz boost. The Intel UHD Graphics 750 runs at a 300 MHz base with a 1300 MHz boost. The Intel part has a much higher boost ceiling, but the AMD part starts far higher at base. Memory is a major divide: the AMD part uses 2 GB of GDDR5 on a 128-bit bus, delivering 72.00 GB/s of bandwidth. The Intel part uses system-shared memory with system-dependent bandwidth, so its memory performance relies entirely on the host platform. The AMD memory clock is 1125 MHz, or 4.5 Gbps effective.

API support is similar but not identical. Both support OpenGL 4.6. The AMD part supports DirectX 12 (11_1) and Vulkan 1.2.170. The Intel part supports DirectX 12 (12_1) and Vulkan 1.4. So Intel has a more modern DirectX feature level and a newer Vulkan revision, which may explain its relatively strong Vulkan showing despite lower raw compute.

The AMD part connects via PCIe 3.0 x16, while the Intel part uses a Ring Bus and is an IGP. The Intel TDP is listed at 15 W; the AMD TDP is not recorded. The AMD part is marked end-of-life with a release date of May 2015, while the Intel part is also end-of-life with a release date of March 2021.

Head-to-Head Benchmarks

The database records two direct comparisons between these GPUs. The first is Geekbench OpenCL. The AMD Radeon R9 M375X scores 8273, the Intel UHD Graphics 750 scores 6743. The AMD part wins by 22.7%. This is the largest margin in the matchup. OpenCL is a general-purpose compute API, and the AMD part's higher shader count and dedicated memory bandwidth appear to dominate. The Intel part's system-shared memory and lower FP32 throughput are likely limiting factors here.

The second test is Geekbench Vulkan. The AMD Radeon R9 M375X scores 8377, the Intel UHD Graphics 750 scores 8138. The AMD part still wins, but only by 2.9%. That is a narrow margin, well within the range of driver or platform variation. The Intel part's Vulkan 1.4 support, versus AMD's 1.2.170, may help it close the gap. Also, the Intel part's higher boost clock of 1300 MHz, compared to AMD's 1015 MHz, could matter more in a driver-optimized graphics workload than in raw compute.

Looking at the nearest rival data for each part gives context. The AMD R9 M375X sits between the NVIDIA Quadro K1200, which averages 8265, and the NVIDIA GeForce GTX 675MX, which averages 8427. The delta to the Quadro is +0.7%, and to the GTX 675MX it is -1.2%. The AMD part is also just behind the AMD Radeon 880M by -1.3% and the NVIDIA GeForce MX330 by -1.6%. So the R9 M375X is competitive with a cluster of mid-range mobile and workstation GPUs, all within a 1.6% range.

The Intel UHD Graphics 750 sits near the AMD Radeon HD 8850M, which averages 7447, a delta of -0.1%. It is also close to the AMD Radeon R7 350 at 7425, a delta of +0.2%. The nearest rivals list includes the NVIDIA GeForce GTX 1650 at 7472, a delta of -0.4%, and the Intel Arc A310 at 7550, a delta of -1.4%. Notably, the GTX 1650 is a discrete desktop GPU, yet the Intel iGPU is only 0.4% behind it in average score. That is a strong result for an integrated part.

The head-to-head wins tally is 2 for the AMD Radeon R9 M375X and 0 for the Intel UHD Graphics 750. But the Vulkan result at 2.9% is close enough that a different driver build or platform memory configuration could plausibly flip it.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R9 M375X averages 8325, while the Intel UHD Graphics 750 averages 7441. The AMD part is ahead by 884 points.

Q: How large is the AMD lead in OpenCL?

A: In Geekbench OpenCL, the AMD Radeon R9 M375X scores 8273 versus 6743 for the Intel UHD Graphics 750, which is a 22.7% advantage.

Q: Is the Intel part competitive in any workload?

A: Yes, in Geekbench Vulkan the Intel UHD Graphics 750 scores 8138 against 8377 for the AMD Radeon R9 M375X, a margin of only 2.9%.

Q: What memory does each GPU use?

A: The AMD Radeon R9 M375X uses 2 GB of GDDR5 on a 128-bit bus with 72.00 GB/s bandwidth. The Intel UHD Graphics 750 uses system-shared memory with system-dependent bandwidth.

Q: How do the shading units compare?

A: The AMD Radeon R9 M375X has 640 shading units, 40 TMUs, and 16 ROPs. The Intel UHD Graphics 750 has 256 shading units, 16 TMUs, and 8 ROPs.

Q: What is the percentile ranking of each GPU?

A: The AMD Radeon R9 M375X is at the 43rd percentile of all GPUs, and the Intel UHD Graphics 750 is at the 40th percentile.

The Verdict

The data points to a straightforward conclusion for most use cases: the AMD Radeon R9 M375X is the faster GPU. It wins both recorded benchmarks, holds a higher average score, and offers more than double the FP32 compute and texture rate of the Intel part. Its dedicated 2 GB GDDR5 frame buffer with 72.00 GB/s bandwidth is a structural advantage over system-shared memory. Anyone comparing these two purely on graphics capability should pick the AMD part.

That said, the Intel UHD Graphics 750 is not a poor performer in context. Its Vulkan score sits just 2.9% behind the AMD part, and its nearest rival list includes the discrete NVIDIA GeForce GTX 1650 with only a 0.4% gap. The Intel part also carries a 15 W TDP, which is remarkably low, and it supports DirectX 12 (12_1) and Vulkan 1.4, both newer than the AMD part's API versions. For a system builder who already has a Rocket Lake CPU, the UHD Graphics 750 is a zero-cost, low-power solution that handles Vulkan workloads respectably.

The AMD Radeon R9 M375X, however, is a discrete part from 2015 with an end-of-life status. It is not a modern solution. Its strengths lie in raw compute and memory bandwidth, which show clearly in OpenCL. Its nearest rivals are all within a tight 1.6% band, indicating it is a mid-tier performer among older mobile GPUs.

The verdict depends on the platform. For a standalone GPU comparison, choose the AMD Radeon R9 M375X. For an integrated solution with minimal power draw and modern API support, the Intel UHD Graphics 750 is the sensible pick, provided the workload favors Vulkan over OpenCL. The database shows two wins for AMD, but the narrow Vulkan margin means the Intel part deserves consideration in API-specific scenarios.