AMD Radeon R7 M370 vs Intel UHD Graphics 750 Comparison

Intel UHD Graphics 750 and AMD Radeon R7 M370 represent two very different approaches to graphics: one is a modern integrated GPU riding on a 14 nm+++ process with a 15 W TDP, while the other is a dedicated mobile chip from 2015 built on TSMC's 28 nm node. The benchmark data shows a split decision, with each GPU taking one of the two available tests, making this a closer contest than the generational gap might suggest.

Head-to-Head Benchmarks

The two GPUs split their head-to-head matchups, with each claiming a decisive victory in one workload. In Geekbench OpenCL, the AMD Radeon R7 M370 posts a score of 7063 against Intel's 6743, a delta of -4.5% from Intel's perspective. That puts the AMD part ahead by roughly 320 points, a modest but real margin. The R7 M370's advantage here aligns with its dedicated GDDR5 memory and higher raw shading throughput — 737.3 GFLOPS FP32 versus Intel's 665.6 GFLOPS.

The Vulkan test tells a completely different story. Intel UHD Graphics 750 crushes the AMD part with a score of 8138 versus 6465, a commanding 25.9% lead. This is not a small gap; it is a substantial victory that reflects the modern architecture's superior driver overhead and API efficiency. Where the R7 M370 wins by a few percentage points in OpenCL, Intel answers with a victory more than five times larger in Vulkan.

Looking at average benchmark scores, Intel's 7441 average sits comfortably above AMD's 6764, a difference that puts the integrated part nearly 10% ahead overall. Intel's percentile ranking among all GPUs is 40, while AMD sits at 38. Intel's nearest rivals in the database include the AMD Radeon HD 8850M at 7447 (-0.1%), the AMD Radeon R7 350 at 7425 (+0.2%), and the NVIDIA GeForce GTX 1650 at 7472 (-0.4%). The R7 M370's closest competitors are the AMD FirePro M5100 at 6830 (-1%), NVIDIA GeForce GT 1010 at 6698 (+1%), and AMD Radeon R7 M460 at 6612 (+2.3%).

Where Each One Wins

The data points to clear use-case separation. The AMD Radeon R7 M370 wins in OpenCL compute workloads, where its 384 shading units and 24 texture mapping units provide a raw throughput advantage. This makes it the better choice for applications that leverage OpenCL for general-purpose GPU computing, such as older video encoding tools or physics simulations that predate widespread Vulkan adoption. Its 2 GB of dedicated GDDR5 memory on a 128-bit bus with 57.60 GB/s bandwidth also means it won't contend with system RAM for graphics data.

The Intel UHD Graphics 750 wins decisively in Vulkan-based workloads. The 25.9% margin in the Vulkan test suggests that modern game engines and applications built around Vulkan will run noticeably better on the Intel part. This is significant because Vulkan has become the standard for cross-platform graphics in recent years, and the Intel GPU's support for Vulkan 1.4 (versus AMD's 1.2.170) indicates a more current API implementation. For anyone running recent titles or emulators that prioritize Vulkan, the Intel part is the clear pick.

The average benchmark score of 7441 for Intel versus 6764 for AMD reinforces that the Intel GPU is the stronger overall performer despite losing the OpenCL test. The R7 M370's win is narrow and confined to one API, while Intel's win is broad and decisive.

Architecture Differences

The architectural gap between these two GPUs is generational. Intel UHD Graphics 750 uses Generation 12.1 architecture, built on Intel's 14 nm+++ process at 15 W TDP. It integrates 256 shading units, 16 TMUs, and 8 ROPs, with a boost clock of 1300 MHz. The AMD Radeon R7 M370 uses GCN 1.0 architecture on TSMC's 28 nm process, packing 384 shading units, 24 TMUs, and 8 ROPs, with a boost clock of 960 MHz. AMD's chip contains 950 million transistors on a 77 mm² die, giving a transistor density of 12.3M per mm².

The process node difference is stark: 14 nm+++ versus 28 nm. This explains how Intel achieves competitive performance with fewer shading units — 256 versus 384 — and a lower power envelope. Intel's 1300 MHz boost clock is substantially higher than AMD's 960 MHz, and the newer architecture extracts more instructions per clock. Intel's pixel rate of 10.40 GPixel/s exceeds AMD's 7.680 GPixel/s despite having the same 8 ROPs, a direct consequence of the higher clock speed. Texture rate favors AMD slightly at 23.04 GTexel/s versus Intel's 20.80 GTexel/s, thanks to its 24 TMUs.

FP32 throughput favors AMD at 737.3 GFLOPS versus Intel's 665.6 GFLOPS, which explains the OpenCL result. Intel supports FP16 at 1,331.2 GFLOPS with a 2:1 ratio, while AMD lists no FP16 capability — a meaningful difference for machine learning workloads that utilize half-precision. API support also differs: Intel supports DirectX 12 (12_1) and Vulkan 1.4, while AMD offers DirectX 12 (11_1) and Vulkan 1.2.170. Both support OpenGL 4.6.

Specification Differences

The two GPUs differ across nearly every specification category. Intel operates with a 300 MHz base and 1300 MHz boost clock, while AMD runs at 875 MHz base and 960 MHz boost. Memory configurations are fundamentally different: Intel uses system-shared memory with bandwidth described as "system dependent," while AMD has 2 GB of dedicated GDDR5 on a 128-bit bus with 57.60 GB/s bandwidth. Intel's memory clock is tied to the system, whereas AMD runs at 900 MHz with 3.6 Gbps effective speed.

Shading units count favors AMD at 384 versus Intel's 256, and TMUs favor AMD at 24 versus 16. Both have 8 ROPs. Bus interface differs: Intel uses a Ring Bus, AMD uses PCIe 3.0 x8. The TDP is listed as 15 W for Intel, while AMD's TDP is not specified in the data. Intel's process node is 14 nm+++ from Intel's foundry; AMD uses 28 nm from TSMC. AMD lists 950 million transistors and a 77 mm² die size; Intel lists neither. AMD supports FP16? No — Intel does; AMD does not list any FP16 capability.

FAQ

Q: Which GPU wins in OpenCL performance?

A: The AMD Radeon R7 M370 wins the Geekbench OpenCL test with a score of 7063 versus Intel's 6743, a 4.5% margin in AMD's favor.

Q: How large is Intel's Vulkan advantage?

A: Intel UHD Graphics 750 scores 8138 in Geekbench Vulkan versus AMD's 6465, giving Intel a 25.9% lead — a decisive margin that dwarfs AMD's OpenCL win.

Q: Which GPU has more shading units?

A: The AMD Radeon R7 M370 has 384 shading units, while Intel UHD Graphics 750 has 256. Despite this, Intel's average benchmark score of 7441 is higher than AMD's 6764.

Q: What is the memory configuration difference?

A: AMD uses 2 GB of dedicated GDDR5 on a 128-bit bus with 57.60 GB/s bandwidth. Intel uses system-shared memory with bandwidth that is system dependent.

Q: Which GPU supports a newer Vulkan version?

A: Intel supports Vulkan 1.4, while AMD supports Vulkan 1.2.170. Intel also supports DirectX 12 (12_1) compared to AMD's DirectX 12 (11_1).

Q: How do these GPUs compare to their nearest rivals?

A: Intel's nearest rival is the NVIDIA GeForce GTX 1650 at 7472 (-0.4% delta). AMD's nearest rival is the AMD FirePro M5100 at 6830 (-1% delta). Intel sits at the 40th percentile among all GPUs, AMD at the 38th.

The Verdict

The data makes a clear recommendation for most users: Intel UHD Graphics 750 is the stronger GPU. Its average benchmark score of 7441 versus 6764 represents a solid overall advantage, and the 25.9% Vulkan victory is the single largest performance gap in this comparison. For anyone running modern Vulkan-based games, emulators, or compute workloads, the Intel part is the obvious choice. It also offers a current API stack with Vulkan 1.4 and DirectX 12 (12_1), plus FP16 support that the AMD part lacks entirely.

The AMD Radeon R7 M370 has one genuine strength: OpenCL compute. Its 384 shading units and 24 TMUs deliver 737.3 GFLOPS FP32, which beats Intel's 665.6 GFLOPS and translates to a 4.5% OpenCL win. Its dedicated 2 GB GDDR5 with 57.60 GB/s bandwidth also avoids the system-memory contention that Intel's shared-memory design must handle. If a workload is strictly OpenCL-based and benefits from dedicated video memory, the AMD part has a case.

However, the overall picture favors Intel. The average score difference of nearly 700 points places Intel at the 40th percentile versus AMD's 38th, and Intel's nearest rivals include the NVIDIA GeForce GTX 1650, a far more modern discrete GPU. The R7 M370's closest competition includes the GeForce GT 1010, a low-end part. The architectural advantages — 14 nm+++ process, higher clocks, newer architecture — outweigh AMD's shading unit count. For a modern system, pick Intel UHD Graphics 750. For legacy OpenCL compute tasks in an older laptop where the R7 M370 is already installed, the AMD part remains serviceable.