AMD Radeon R7 350 vs Intel UHD Graphics P750 Comparison

Where Each One Wins

The recorded data shows a single benchmark comparison between the AMD Radeon R7 350 and the Intel UHD Graphics P750, and the AMD part claims the only win. In the Geekbench OpenCL test, the R7 350 scores 7792 against the Intel P750's 6554, a delta of 18.9 percent in favor of AMD. This is a compute-oriented workload, so the result suggests the R7 350 has a meaningful advantage in general-purpose GPU compute tasks as measured by OpenCL.

The Intel UHD Graphics P750 has no benchmark wins in this dataset. It does not appear in the head-to-head results with any victory, and its single recorded score in Geekbench OpenCL is the lower of the two. However, the P750 does have a Vulkan API version of 1.4, while the R7 350 supports Vulkan 1.2.170, and it supports DirectX 12 (12_1) compared to the R7 350's DirectX 12 (11_1). These API differences do not translate into a benchmark win here, but they indicate the Intel part carries a more modern feature set for certain software paths.

The use-case split, based strictly on the data, is narrow. If the workload is OpenCL compute, the AMD Radeon R7 350 is the stronger choice. If the workload relies on newer API feature levels, the Intel UHD Graphics P750 may be the more compatible option, though there is no benchmark evidence in the database to quantify that advantage. The R7 350 also holds a higher percentile ranking among all GPUs: 40th percentile versus the P750's 38th. The average benchmark score for the R7 350 is 7425, while the P750 sits at 6554, which places the AMD part ahead in the database's aggregate scoring.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R7 350 has an average benchmark score of 7425, while the Intel UHD Graphics P750 has an average score of 6554. The R7 350 also ranks in the 40th percentile of all GPUs, compared to the P750's 38th percentile.

Q: How large is the performance gap in the only head-to-head benchmark?

A: In Geekbench OpenCL, the AMD Radeon R7 350 scores 7792 and the Intel UHD Graphics P750 scores 6554. The AMD part wins by 18.9 percent.

Q: Does the Intel UHD Graphics P750 beat the R7 350 in any benchmark?

A: No. The database records one head-to-head benchmark, Geekbench OpenCL, and the Intel UHD Graphics P750 does not win that test. Its wins count is zero, while the R7 350 has one win.

Q: What are the closest rivals to each GPU according to the database?

A: For the AMD Radeon R7 350, the nearest rival is the Intel UHD Graphics 750 with an average score of 7441 and a delta of negative 0.2 percent. For the Intel UHD Graphics P750, the nearest rival is the AMD Radeon HD 7730M with an average score of 6581 and a delta of negative 0.4 percent.

Q: How do the shading unit counts compare between the two?

A: The AMD Radeon R7 350 has 512 shading units, while the Intel UHD Graphics P750 has 256 shading units. The AMD part has twice as many shading units, but the Intel part has 64 texture mapping units and 32 ROPs versus the R7 350's 32 TMUs and 16 ROPs.

Q: What is the power draw difference between them?

A: The AMD Radeon R7 350 has a TDP of 55 W, while the Intel UHD Graphics P750 has a TDP of 15 W. The Intel part is an integrated GPU (IGP), while the AMD part is a single-slot discrete card with no power connectors and a suggested PSU of 250 W.

Head-to-Head Benchmarks

The database contains exactly one head-to-head benchmark between these two GPUs: Geekbench OpenCL. In that test, the AMD Radeon R7 350 produces a score of 7792, and the Intel UHD Graphics P750 produces a score of 6554. The delta of 18.9 percent in favor of the AMD part is substantial. To put that in context, the R7 350's nearest rival, the Intel UHD Graphics 750, averages 7441, which is only 0.2 percent below the R7 350's average. The P750, by contrast, sits 18.9 percent behind the R7 350 in this specific test, a much wider gap than what separates the R7 350 from its closest competitor.

The Intel UHD Graphics P750's own nearest rivals tell a different story. Its closest competitor is the AMD Radeon HD 7730M at 6581, which is 0.4 percent above the P750's 6554. The NVIDIA GeForce GTX 670M sits at 6513, 0.6 percent below the P750. The AMD Radeon R7 M460 is at 6612, 0.9 percent above, and the NVIDIA GeForce GT 555M is at 6493, 0.9 percent below. This means the P750 is clustered with mobile GPUs from previous generations, and its OpenCL performance is competitive within that group, but it is not competitive with the R7 350's level of output.

The AMD R7 350, with a score of 7792, is not just ahead of the P750; it is also positioned near the NVIDIA GeForce GTX 1650, which averages 7472 and trails the R7 350 by 0.6 percent. The Intel Arc A310 averages 7550, 1.7 percent below the R7 350. So the R7 350's OpenCL result places it in a higher performance tier than the P750, whose results align with older mobile parts rather than modern desktop or Arc-class hardware.

Specification Differences

The two GPUs differ sharply in almost every specification category. The AMD Radeon R7 350 uses the Cape Verde chip with GCN 1.0 architecture, built on a 28 nm process at TSMC. The Intel UHD Graphics P750 uses the Rocket Lake chip with Generation 12.1 architecture, built on Intel's 14 nm+++ process. The AMD part has 1,500 million transistors on a 123 mm² die, giving a transistor density of 12.2 million per square millimeter. The Intel part has no transistor count, die size, or density figures recorded in the database.

Memory is another major split. The R7 350 has 2 GB of GDDR5 on a 128 bit bus, with a bandwidth of 72.00 GB/s and a memory clock of 1125 MHz, which translates to 4.5 Gbps effective. The P750 uses system shared memory, with a system dependent bandwidth and no dedicated memory clock. This makes the R7 350 a discrete card with its own VRAM, while the P750 relies on the host system's memory.

Compute resources differ in a counterintuitive way. The R7 350 has 512 shading units, 32 TMUs, and 16 ROPs. The P750 has 256 shading units, 64 TMUs, and 32 ROPs, meaning Intel doubled the texture units and ROP count while halving the shading units. The pixel rate reflects this: the P750 outputs 41.60 GPixel/s versus the R7 350's 12.80 GPixel/s. The texture rate also favors Intel: 83.20 GTexel/s versus 25.60 GTexel/s. However, the FP32 compute rate favors AMD: 819.2 GFLOPS versus 665.6 GFLOPS. The P750 does record FP16 at 1,331.2 GFLOPS with a 2:1 ratio, while the R7 350 has no FP16 figure.

Power and physical design are also divergent. The R7 350 has a TDP of 55 W, occupies a single slot, requires no power connectors, and suggests a 250 W PSU. The P750 has a TDP of 15 W and is an IGP with no slot width, power connectors, or PSU recommendation. The R7 350 uses PCIe 3.0 x16, while the P750 uses a Ring Bus. Display outputs on the R7 350 include 1x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2, while the P750's outputs are motherboard dependent. The R7 350 has physical dimensions of 168 mm or 6.6 inches in length; the P750 has none recorded.

Architecture Differences

The architectural gulf between these two parts is wide. The AMD Radeon R7 350 belongs to the Pirate Islands generation, specifically the R7 300 family, and is a GCN 1.0 design codenamed Cape Verde. Its predecessor is listed as Volcanic Islands, and its successor is Arctic Islands. The Intel UHD Graphics P750 belongs to the HD Graphics-W generation under Rocket Lake, using Intel's Generation 12.1 architecture. It has no predecessor or successor listed.

The process node difference is significant: AMD uses 28 nm at TSMC, while Intel uses 14 nm+++. The AMD chip is discrete, with its own GDDR5 memory and a 128 bit bus. The Intel chip is integrated, sharing system memory with no dedicated VRAM. The R7 350's GCN 1.0 design is an older architecture that emphasizes raw FP32 throughput, and its 512 shading units are organized around that design. The P750's Generation 12.1 architecture is newer and supports a higher DirectX feature level of 12 (12_1), while the R7 350 is limited to DirectX 12 (11_1). Vulkan support on the Intel side is 1.4, while the R7 350 supports 1.2.170. OpenGL is 4.6 on both.

The R7 350's GCN 1.0 lacks RT cores, tensor cores, and FP16, and its FP32 peak of 819.2 GFLOPS is its primary compute metric. The P750 also lacks RT cores and tensor cores, but it does record FP16 at 1,331.2 GFLOPS at a 2:1 ratio, doubling its FP32 number. The R7 350's pixel and texture rates are lower than the Intel part, but the Intel part's 83.10 GTexel/s and 41.60 GPixel/s are anomalous for a 15 W IGP. This suggests Intel's architecture, despite less raw shading power, excels at fill-rate-style work. The R7 350's 1.5 billion transistors and 123 mm² die size are the only transistor-level data in the database, and the Intel part has no such figures, making a direct transistor comparison impossible.

The Verdict

The data points to a clear but narrow conclusion. The AMD Radeon R7 350 wins the only benchmark recorded, Geekbench OpenCL, by 18.9 percent over the Intel UHD Graphics P750. Its average benchmark score is 7425 versus 6554, and its percentile rank is 40 versus 38. Anyone choosing between these two for OpenCL compute should select the R7 350 based on the available measurements.

The Intel UHD Graphics P750 is not without its own strengths. It has a 15 W TDP, making it far more power-efficient than the R7 350's 55 W. It has double the TMUs and ROPs, leading to much higher pixel and texture rates: 41.60 GPixel/s and 83.20 GTexel/s versus 12.80 GPixel/s and 25.60 GTexel/s. It also supports a newer DirectX feature level, 12 (12_1) versus 12 (11_1), and a newer Vulkan version, 1.4 versus 1.2.170. For integrated graphics in a system with shared memory, the P750 is a low-power option that offers superior fill-rate performance and API compatibility in the database's recorded specifications.

The R7 350, however, is a discrete card with dedicated 2 GB GDDR5 memory and a 128 bit bus, which provides 72.00 GB/s of bandwidth. Its FP32 performance of 819.2 GFLOPS is higher than the P750's 665.6 GFLOPS. Its shading unit count is double that of the Intel part. The R7 350 also sits in a higher performance tier among its nearest rivals, close to the NVIDIA GeForce GTX 1650 and Intel Arc A310. The P750's nearest rivals are older mobile parts like the AMD Radeon HD 7730M and NVIDIA GeForce GTX 670M.

The verdict, strictly from the data: the AMD Radeon R7 350 is the pick for compute-heavy OpenCL workloads and for users who need dedicated VRAM. The Intel UHD Graphics P750 is the pick for low-power integrated scenarios where fill-rate performance and modern API support matter more than raw compute scores. The R7 350 wins the only benchmark in the database, and that is the deciding factor for performance comparisons.