AMD Radeon RX 560 vs NVIDIA GeForce 930A Comparison

Head-to-Head Benchmarks

The only directly comparable benchmark in the database is Geekbench OpenCL, and the result is decisive. The AMD Radeon RX 560 scores 16,472, while the NVIDIA GeForce 930A scores 5,317. That puts the AMD part 67.7% ahead, a margin that separates entirely different performance classes. The delta is so large that it does not represent a close contest; it represents a generational and architectural gap.

The GeForce 930A's average benchmark score is 5,317, which places it in the 31st percentile of all GPUs. Its nearest rivals in the database are all within a very tight band: the NVIDIA GeForce 840M scores 5,322 (0.1% ahead), the NVIDIA GeForce GTX 980M scores 5,308 (0.2% behind), the NVIDIA GeForce 940M scores 5,284 (0.6% behind), and the AMD Radeon R7 M445 scores 5,358 (0.8% ahead). The 930A sits in a cluster where a few percent separates all five parts. This is a low-midrange space where no single card dominates its immediate neighbors, and the 930A is essentially interchangeable with its closest competitors in raw OpenCL output.

The Radeon RX 560, by contrast, has an average benchmark score of 4,569 across all recorded tests, which lands it in the 26th percentile of all GPUs. Its nearest rivals are similarly clustered: the AMD Radeon R5 M230 scores 4,577 (0.2% ahead), the Intel HD Graphics P530 scores 4,560 (0.2% behind), the NVIDIA Quadro M3000M scores 4,621 (1.1% ahead), and the NVIDIA GeForce GTX 970M scores 4,628 (1.3% ahead). The RX 560's average is dragged down by its varied benchmark suite, which includes DirectX 9, 10, 11, and 12 tests, plus compute and 2D workloads. Its OpenCL result alone, 16,472, is over three times the 930A's entire average.

The RX 560 also has other recorded results that tell a fuller story. It scores 18,941 in Geekbench Metal, 3,671 in Passmark G3D, 1,437 in Passmark GPU Compute, and 485 in Passmark G2D. Its DirectX results range from 16 in DirectX 10 to 57 in DirectX 9, with 25 in DirectX 11 and 21 in DirectX 12. These are not directly comparable to the 930A, which only has the single OpenCL entry, but they show a broad workload spread. The 930A has no recorded Metal, DirectX, or compute scores, so the database can only confirm its behavior in one API. That asymmetry is itself informative: the RX 560 has been tested across many environments, while the 930A has a much thinner record.

The percentile ranking is worth noting. Despite the 930A's low raw OpenCL score, it sits at the 31st percentile, five points higher than the RX 560's 26th percentile. That is because the two parts are ranked against different pools of recorded GPUs, and the RX 560's average includes several weak DirectX results that pull its mean down. The OpenCL head-to-head is unambiguous, but the overall percentile comparison shows that percentile alone does not capture the RX 560's peak capability. The data implies the RX 560 is a high-variance part: excellent in compute-heavy APIs, modest in legacy DirectX tests.

The Verdict

The data points to a clear hierarchy. In the only shared benchmark, Geekbench OpenCL, the AMD Radeon RX 560 is 67.7% ahead of the NVIDIA GeForce 930A. That is not a marginal win; it is a dominant one. The RX 560 also carries a 4 GB GDDR5 frame buffer on a 128-bit bus with 112.0 GB/s of bandwidth, versus 2 GB of DDR3 on a 64-bit bus with 16.02 GB/s. The compute gap matches the memory gap: the RX 560 delivers 2.611 TFLOPS of FP32, while the 930A manages 722.7 GFLOPS. The texture rate is 81.60 GTexel/s against 22.58 GTexel/s, and the pixel rate is 20.40 GPixel/s against 7.528 GPixel/s. Every measured throughput metric favors the RX 560 by a wide margin.

Who should pick the GeForce 930A? Strictly from the database, only a user constrained by power or form factor. The 930A has a 33 W TDP, an IGP slot width, and no power connectors. The RX 560 has a 75 W TDP, a dual-slot cooler, and a suggested 250 W power supply. The 930A also has a release date of March 2015, over two years before the RX 560's April 2017 launch. For a portable or low-power system where a discrete card cannot fit, the 930A is the only choice between the two. For anyone who can accommodate a dual-slot card and a 250 W PSU, the RX 560 is the stronger part in every recorded benchmark.

The percentile data complicates a simple "RX 560 wins" narrative. The 930A's 31st percentile versus the RX 560's 26th percentile suggests that, across all recorded GPUs, the 930A sits in a slightly higher relative position. But that ranking is an artifact of the test suite. The 930A has one OpenCL score. The RX 560 has nine scores, several of them in legacy DirectX modes where it performs poorly. The OpenCL head-to-head is the only apples-to-apples comparison in the database, and it favors the RX 560 by 67.7%. The verdict follows the head-to-head, not the percentile.

Architecture Differences

The two GPUs come from different manufacturers, different foundries, and different design philosophies. The NVIDIA GeForce 930A uses the GM108 chip on the Maxwell architecture, built on a 28 nm process at TSMC. It packs 1,020 million transistors into a 77 mm² die, giving a transistor density of 13.2 million per square millimeter. The AMD Radeon RX 560 uses the Polaris 21 chip on the GCN 4.0 architecture, built on a 14 nm process at GlobalFoundries. It contains 3,000 million transistors on a 123 mm² die, for a density of 24.4 million per square millimeter.

The transistor counts tell a story. The RX 560 has nearly three times the transistor budget of the 930A, and it uses that budget across 1,024 shading units, 64 texture mapping units, and 16 ROPs. The 930A has 384 shading units, 24 TMUs, and 8 ROPs. That is 2.7 times the shading units, 2.7 times the TMUs, and 2 times the ROPs in favor of the AMD part. The process advantage also matters: 14 nm versus 28 nm allows the RX 560 to fit more transistors per area and run at higher clocks, 1175 MHz base and 1275 MHz boost versus 928 MHz base and 941 MHz boost.

Memory architecture differs as fundamentally as the compute fabric. The 930A uses DDR3 at 1001 MHz (2 Gbps effective) on a 64-bit bus, yielding 16.02 GB/s. The RX 560 uses GDDR5 at 1750 MHz (7 Gbps effective) on a 128-bit bus, yielding 112.0 GB/s. The bandwidth ratio is almost exactly 7:1, which explains why memory-heavy workloads see such a lopsided OpenCL result. The RX 560 also supports FP16 at a 1:1 ratio with 2.611 TFLOPS, a capability the 930A does not record.

API support shows a version split as well. The 930A supports DirectX 12 (11_0) and OpenGL 4.6, while the RX 560 supports DirectX 12 (12_0) and OpenGL 4.6. Vulkan support differs: the 930A lists Vulkan 1.4, the RX 560 lists Vulkan 1.3. Both use PCIe 3.0 x8, and both are marked end-of-life. The RX 560 names its predecessor as Arctic Islands and its successor as Vega; the 930A names its predecessor as GeForce 800A and has no recorded successor.

Specification Differences

The two cards differ in nearly every physical and electrical specification. Process node: 28 nm for the 930A, 14 nm for the RX 560. Foundry: TSMC versus GlobalFoundries. Transistors: 1,020 million versus 3,000 million. Die size: 77 mm² versus 123 mm². Transistor density: 13.2M per mm² versus 24.4M per mm². Base clock: 928 MHz versus 1175 MHz. Boost clock: 941 MHz versus 1275 MHz. Memory clock: 1001 MHz (2 Gbps effective) versus 1750 MHz (7 Gbps effective).

Memory capacity: 2 GB versus 4 GB. Memory type: DDR3 versus GDDR5. Bus width: 64 bit versus 128 bit. Bandwidth: 16.02 GB/s versus 112.0 GB/s. Shading units: 384 versus 1024. TMUs: 24 versus 64. ROPs: 8 versus 16. Pixel rate: 7.528 GPixel/s versus 20.40 GPixel/s. Texture rate: 22.58 GTexel/s versus 81.60 GTexel/s. FP32: 722.7 GFLOPS versus 2.611 TFLOPS. FP16: not recorded versus 2.611 TFLOPS (1:1). TDP: 33 W versus 75 W. Slot width: IGP versus dual-slot. Power connectors: none for both. Suggested PSU: not recorded for the 930A, 250 W for the RX 560.

Display outputs: the 930A lists "Portable Device Dependent," while the RX 560 lists 1x DVI, 1x HDMI 2.0b, and 1x DisplayPort 1.4a. The RX 560 has a recorded length of 170 mm (6.7 inches); the 930A has no recorded dimensions. Release dates: March 2015 for the 930A, April 2017 for the RX 560. The RX 560 has a launch MSRP of 99 USD; the 930A has no recorded launch MSRP.

FAQ

Q: Which GPU wins the only shared benchmark in the database?

A: The AMD Radeon RX 560 wins Geekbench OpenCL with a score of 16,472 against the NVIDIA GeForce 930A's 5,317, a margin of 67.7%.

Q: How does the memory bandwidth compare?

A: The RX 560 delivers 112.0 GB/s over a 128-bit GDDR5 bus, while the 930A delivers 16.02 GB/s over a 64-bit DDR3 bus. The RX 560 has roughly seven times the bandwidth.

Q: What are the TDP and slot requirements for each card?

A: The 930A has a 33 W TDP and an IGP slot width with no power connectors. The RX 560 has a 75 W TDP, a dual-slot width, no power connectors, and a suggested 250 W power supply.

Q: Which card has more shading units and compute throughput?

A: The RX 560 has 1,024 shading units and 2.611 TFLOPS of FP32 compute. The 930A has 384 shading units and 722.7 GFLOPS of FP32 compute, roughly 27% of the AMD part's output.

Q: What is the percentile ranking of each GPU in the database?

A: The 930A is in the 31st percentile of all GPUs, while the RX 560 is in the 26th percentile. The 930A's single OpenCL score of 5,317 places it higher on that scale, despite being far behind the RX 560 in the head-to-head.

Q: Do both cards support the same APIs?

A: Both support OpenGL 4.6 and PCIe 3.0 x8, and both support DirectX 12, but the 930A lists DirectX 12 (11_0) with Vulkan 1.4, while the RX 560 lists DirectX 12 (12_0) with Vulkan 1.3. The RX 560 also records FP16 compute at 1:1 ratio; the 930A does not.

Where Each One Wins

The AMD Radeon RX 560 wins in raw compute performance. The Geekbench OpenCL result shows a 67.7% advantage, and the supporting metrics confirm it: 2.611 TFLOPS of FP32, 81.60 GTexel/s of texture fill, 20.40 GPixel/s of pixel fill, and 112.0 GB/s of memory bandwidth. The RX 560 wins in capacity as well, with 4 GB of GDDR5 versus 2 GB of DDR3. It also wins in clock speed, with a 1175 MHz base and 1275 MHz boost over the 930A's 928 MHz and 941 MHz. The RX 560 has a clear win in every throughput and capacity category where the database has matching data.

The RX 560 also wins in breadth of recorded testing. It has nine benchmark entries spanning Metal, DirectX 9 through 12, 2D, 3D, and compute workloads. The 930A has one entry. Users who care about API coverage and API support will find the RX 560 covers DirectX 12 (12_0), HDMI 2.0b, DisplayPort 1.4a, and Vulkan 1.3. The 930A lists Vulkan 1.4 but only DirectX 12 (11_0) and offers no recorded display outputs beyond "Portable Device Dependent."

The NVIDIA GeForce 930A wins only where physical footprint and power constraints dominate. Its 33 W TDP is less than half the RX 560's 75 W, it requires no dual-slot cooler, and it needs no power supply beyond what a portable device provides. The suggested 250 W PSU for the RX 560 is a real requirement, and the 170 mm length shows it is a physical card that occupies space. For an IGP-class slot, the 930A fits where the RX 560 cannot.

The 930A also holds a higher percentile ranking at 31% versus 26%. That is a narrow statistical win, and one that comes from a single test. The database positions the 930A among peers like the GeForce 840M, GTX 980M, 940M, and Radeon R7 M445, all within a 1% band. The RX 560 sits with the Radeon R5 M230, HD Graphics P530, Quadro M3000M, and GTX 970M, also within a 1.3% band. In relative placement within these clusters, the 930A is marginally better placed, but the head-to-head delta of 67.7% overrides it.

The RX 560 wins for anyone who wants to run modern workloads with high frame rates and ample VRAM headroom. The data says it is the faster card in every measured category that matters for graphics rendering and compute tasks. The 930A wins for anyone locked into a low-power, space-constrained platform where 33 W TDP and an IGP slot, portable device dependent outputs are non-negotiable.