AMD Radeon R5 M335 vs NVIDIA GeForce 930A Comparison

FAQ

Q: How does the NVIDIA GeForce 930A compare to the AMD Radeon R5 M335 in OpenCL performance?

A: The GeForce 930A scores 5,317 in Geekbench OpenCL, while the Radeon R5 M335 scores 4,745. This gives the NVIDIA part a 12.1% lead in that specific benchmark.

Q: What is the overall benchmark percentile ranking for each GPU?

A: The GeForce 930A sits at the 31st percentile among all GPUs, while the Radeon R5 M335 ranks at the 28th percentile. Both parts are near the lower end of the performance spectrum.

Q: Which GPU has higher compute throughput in raw FP32 performance?

A: The GeForce 930A delivers 722.7 GFLOPS of FP32 compute, compared to 659.2 GFLOPS for the Radeon R5 M335. That is a difference of roughly 10% in theoretical peak compute.

Q: Are both GPUs built on the same manufacturing process?

A: Yes, both are fabricated on a 28 nm process at TSMC. The NVIDIA chip (GM108) contains 1,020 million transistors on a 77 mm² die, while the AMD chip (Exo) packs 690 million transistors on a 56 mm² die.

Q: Which GPU supports a newer version of DirectX?

A: The AMD Radeon R5 M335 supports DirectX 12 (11_1), while the NVIDIA GeForce 930A supports DirectX 12 (11_0). The difference is minor in practice, as both are DirectX 12 compatible.

Q: How does the Radeon R5 M335 perform in Vulkan compared to OpenCL?

A: The Radeon R5 M335 scores 4,758 in Geekbench Vulkan and 4,745 in Geekbench OpenCL. The two results are nearly identical, with a difference of only 0.3%.

Architecture Differences

The two GPUs represent fundamentally different architectural designs from their respective manufacturers. The NVIDIA GeForce 930A is built on the Maxwell architecture with the GM108 chip, while the AMD Radeon R5 M335 uses the GCN 1.0 architecture with the Exo chip.

The transistor counts differ substantially. NVIDIA packs 1,020 million transistors into a 77 mm² die, yielding a transistor density of 13.2M per mm². AMD fits 690 million transistors into a smaller 56 mm² die, resulting in a density of 12.3M per mm². Despite having fewer transistors, the AMD die is smaller in absolute terms, which reflects the simpler GCN 1.0 design compared to Maxwell.

Core configuration differs in every major compute unit. The GeForce 930A has 384 shading units, 24 texture mapping units, and 8 ROPs. The Radeon R5 M335 has 320 shading units, 20 TMUs, and 8 ROPs. This means NVIDIA has 20% more shading units and 20% more TMUs, while both parts share the same 8 ROP count.

Clock behavior is another key distinction. The GeForce 930A has explicit base and boost clocks of 928 MHz and 941 MHz respectively, allowing dynamic frequency scaling under load. The Radeon R5 M335 has no listed base or boost clock in the database, so its operating frequency is effectively unspecified and likely varies by implementation.

Memory configuration is similar on the surface, with both using 2 GB of DDR3 over a 64-bit bus. However, the GeForce 930A runs its memory at 1001 MHz with 2 Gbps effective data rate, producing 16.02 GB/s of bandwidth. The Radeon R5 M335 runs memory at 900 MHz with 1800 Mbps effective, yielding 14.40 GB/s. That is a 11.3% bandwidth advantage for the NVIDIA part.

API support shows generational differences. Both support OpenGL 4.6, but NVIDIA offers Vulkan 1.4 while AMD provides Vulkan 1.2.170. For DirectX, AMD lists 12 (11_1) versus NVIDIA's 12 (11_0). The production status for both is end-of-life, with the NVIDIA part released in March 2015 and the AMD part released in October 2015.

Head-to-Head Benchmarks

The database contains one head-to-head benchmark comparison between these two GPUs: Geekbench OpenCL. In this test, the NVIDIA GeForce 930A scores 5,317 against the AMD Radeon R5 M335's 4,745. The delta is 12.1% in favor of NVIDIA, which is the only recorded head-to-head win for either part.

This OpenCL result aligns with the theoretical specifications. The GeForce 930A has higher FP32 throughput (722.7 GFLOPS versus 659.2 GFLOPS), higher texture fill rate (22.58 GTexel/s versus 20.60 GTexel/s), and higher memory bandwidth (16.02 GB/s versus 14.40 GB/s). The only metric where AMD holds an advantage is pixel rate, at 8.240 GPixel/s versus 7.528 GPixel/s for NVIDIA, a 9.5% difference.

The AMD part also has a Vulkan benchmark score of 4,758, but the GeForce 930A has no recorded Vulkan score in the database, so no direct comparison is possible in that API. The Vulkan score for the Radeon R5 M335 is essentially tied with its OpenCL score, suggesting the GCN 1.0 architecture scales similarly across these two compute APIs.

When placing the OpenCL scores into context, the GeForce 930A's 5,317 places it within 0.1% of the NVIDIA GeForce 840M (5,322) and 0.2% ahead of the NVIDIA GeForce GTX 980M (5,308). The Radeon R5 M335's 4,745 sits 0.5% behind the AMD Radeon R8 M445DX (4,727) and 0.7% behind the AMD Radeon R5 M255 (4,788). These near-identical scores for the NVIDIA part suggest that Maxwell's OpenCL performance is heavily clustered, while the AMD part shows similar clustering within its own family.

Specification Differences

The following specifications differ between the two GPUs:

• Manufacturer: NVIDIA versus AMD
• Chip: GM108 versus Exo
• Architecture: Maxwell versus GCN 1.0
• Generation: GeForce 900A versus Gem System (R5 M300)
• Transistors: 1,020 million versus 690 million
• Die Size: 77 mm² versus 56 mm²
• Transistor Density: 13.2M / mm² versus 12.3M / mm²
• Base Clock: 928 MHz versus not listed
• Boost Clock: 941 MHz versus not listed
• Memory Clock: 1001 MHz (2 Gbps effective) versus 900 MHz (1800 Mbps effective)
• Memory Bandwidth: 16.02 GB/s versus 14.40 GB/s
• Shading Units: 384 versus 320
• TMUs: 24 versus 20
• Pixel Rate: 7.528 GPixel/s versus 8.240 GPixel/s
• Texture Rate: 22.58 GTexel/s versus 20.60 GTexel/s
• FP32: 722.7 GFLOPS versus 659.2 GFLOPS
• TDP: 33 W versus not listed
• Slot Width: IGP versus not listed
• DirectX Support: 12 (11_0) versus 12 (11_1)
• Vulkan Support: 1.4 versus 1.2.170
• Release Date: March 2015 versus October 2015
• Predecessor: GeForce 800A versus Solar System
• Successor: not listed versus Polaris Mobile

Fields that are identical include memory size (2 GB), memory type (DDR3), bus width (64 bit), ROPs (8), power connectors (none), bus interface (PCIe 3.0 x8), display outputs (portable device dependent), OpenGL version (4.6), production status (end-of-life), and the lack of a launch MSRP in the database.

Where Each One Wins

The NVIDIA GeForce 930A wins the only recorded head-to-head benchmark, taking Geekbench OpenCL by 12.1%. This advantage is consistent across nearly every compute metric in the specification sheet. The higher FP32 throughput means better raw compute performance for general-purpose workloads, and the higher texture rate suggests stronger fill-rate-bound scenarios. The memory bandwidth advantage of 16.02 GB/s versus 14.40 GB/s also helps in bandwidth-sensitive tasks.

The GeForce 930A is the better choice for OpenCL compute workloads, where its 384 shading units and Maxwell architecture deliver a clear edge. Its nearest rival comparison shows it clustered with the GeForce 840M and even the high-end GeForce GTX 980M, all within 0.2% of each other, which indicates that Maxwell's OpenCL performance is consistent across its mobile lineup. For users running OpenCL-based applications such as video encoding, image processing, or scientific compute, the data points to the NVIDIA part.

The AMD Radeon R5 M335, while losing the head-to-head OpenCL test, does have one measurable advantage: pixel rate. At 8.240 GPixel/s, it outperforms the GeForce 930A's 7.528 GPixel/s by 9.5%. This suggests that in pure pixel-fill workloads, such as certain rendering paths or compositing tasks, the AMD part may hold a slight edge. However, this advantage does not translate into a win in the OpenCL benchmark, which likely stresses a mix of compute and memory rather than pure ROP throughput.

The Radeon R5 M335 also offers a Vulkan benchmark score, which the GeForce 930A lacks in the database. For Vulkan-specific workloads, the AMD part at least has a recorded capability, though the absence of an NVIDIA Vulkan score prevents any comparison. The AMD part's Vulkan score of 4,758 is nearly identical to its OpenCL score, suggesting that GCN 1.0 handles both APIs with similar efficiency.

For gaming and general mobile GPU use, the GeForce 930A's higher shading unit count, higher clock rates, and greater memory bandwidth make it the more capable part on paper. The AMD part's higher pixel rate could benefit legacy or simple 2D workloads, but the overall compute advantage remains with NVIDIA.

The release timing also matters. The GeForce 930A launched in March 2015, seven months before the Radeon R5 M335's October 2015 debut. Both are now end-of-life products, so the practical choice depends on which used or pre-owned system contains which GPU. The database shows NVIDIA winning the measurable benchmark, and the specification sheet reinforces that result across FP32, texture rate, and bandwidth. The AMD part wins only on pixel rate and offers an extra Vulkan benchmark score, but no head-to-head win in the recorded data.