GPU Comparison
Intel HD Graphics 530
GeForce 920MX
PERFORMANCE BENCHMARKS
Analysis: Intel HD Graphics 530 vs NVIDIA GeForce 920MX
The Verdict
The benchmark data paints a clear picture: the NVIDIA GeForce 920MX is the stronger performer in every head-to-head comparison available. It wins both Geekbench tests, with its most dominant showing in Vulkan, where it more than doubles the Intel HD Graphics 530’s score. The GeForce 920MX also holds a higher average benchmark score (3528 vs. 3332) and sits at the 21st percentile of all GPUs, one point above Intel’s 20th percentile. For any user prioritizing raw graphics throughput, the NVIDIA part is the straightforward choice.
However, the Intel HD Graphics 530 is not without its own advantages. It is a generation newer, built on a smaller 14 nm+ process, and it supports DirectX 12 (12_1), a feature level the 920MX cannot match (it only reaches DirectX 11_0). The Intel solution also has a higher peak FP16 rate (729.6 GFLOPS) and a higher Geekbench Metal score (5025 vs. none recorded for NVIDIA). But those strengths do not translate into wins in the shared OpenCL and Vulkan tests. The data indicates the 920MX is for users who need consistent, measurable performance in compute and graphics workloads, while the HD 530 is for those who value platform integration, lower power draw, and a more modern feature set.
Architecture Differences
The two GPUs come from fundamentally different design philosophies. The NVIDIA GeForce 920MX uses the GM108S chip, built on Maxwell architecture, manufactured by TSMC on a 28 nm process. It packs 1,020 million transistors into a 77 mm² die, yielding a transistor density of 13.2M per mm². The Intel HD Graphics 530, in contrast, uses the Skylake GT2 chip, built on Intel’s Generation 9.0 architecture, manufactured on a 14 nm+ process. Its die is larger at 123 mm², but Intel does not disclose transistor count or density for this part.
Clock behavior differs significantly. The 920MX operates at a base clock of 965 MHz with a boost up to 993 MHz, while the HD 530 starts much lower at 350 MHz but can boost to 950 MHz. This means the NVIDIA chip runs at a consistently higher frequency, while Intel relies on a wider boost range. The memory architecture is another major divergence: the 920MX has dedicated 2 GB of DDR3 on a 64-bit bus with 14.40 GB/s bandwidth, whereas the HD 530 uses system shared memory with system-dependent bandwidth.
Compute resources are also distributed differently. The 920MX has 256 shading units, 24 TMUs, and 8 ROPs. The HD 530 has fewer shading units (192) and only 3 ROPs, but it matches the TMU count at 24. This results in a pixel rate of 7.944 GPixel/s for NVIDIA versus 2.850 GPixel/s for Intel. Texture rates are closer, at 23.83 GTexel/s vs. 22.80 GTexel/s. FP32 performance favors NVIDIA at 508.4 GFLOPS vs. 364.8 GFLOPS, but Intel offers FP16 at 729.6 GFLOPS (2:1), a feature the 920MX does not list.
Head-to-Head Benchmarks
The Geekbench OpenCL test shows the 920MX ahead with a score of 4068 versus 3550 for the HD 530, a 14.6% advantage. This is a solid but not overwhelming lead. The delta suggests that in general-purpose compute workloads using OpenCL, the NVIDIA part’s higher clock speeds and dedicated memory provide a meaningful edge, but the gap is not insurmountable.
The Vulkan test tells a far more dramatic story. The 920MX scores 2987, while the HD 530 manages only 1422. That is a 110.1% difference, more than double the performance. This is the single biggest win for either side and indicates that the NVIDIA architecture handles Vulkan’s low-level API overhead far more efficiently. For users running Vulkan-based games or applications, the choice is unambiguous.
Intel’s only bright spot in the benchmark suite is the Geekbench Metal test, where it scores 5025. However, the 920MX has no recorded Metal score, so this cannot be compared directly. It does show that the HD 530 has strong performance in Apple’s graphics API, which may matter for users in macOS environments. The average benchmark score also reflects the overall picture: 3528 for NVIDIA vs. 3332 for Intel.
Specification Differences
The table below highlights only the fields where the two GPUs differ:
| Specification | NVIDIA GeForce 920MX | Intel HD Graphics 530 |
|---|---|---|
| Chip | GM108S | Skylake GT2 |
| Architecture | Maxwell | Generation 9.0 |
| Generation | GeForce 900M | HD Graphics (Skylake) |
| Process Node | 28 nm | 14 nm+ |
| Foundry | TSMC | Intel |
| Transistors | 1,020 million | Not disclosed |
| Die Size | 77 mm² | 123 mm² |
| Transistor Density | 13.2M / mm² | Not disclosed |
| Base Clock | 965 MHz | 350 MHz |
| Boost Clock | 993 MHz | 950 MHz |
| Memory | 2 GB DDR3, 64-bit, 14.40 GB/s | System Shared |
| Shading Units | 256 | 192 |
| ROPs | 8 | 3 |
| Pixel Rate | 7.944 GPixel/s | 2.850 GPixel/s |
| Texture Rate | 23.83 GTexel/s | 22.80 GTexel/s |
| FP32 | 508.4 GFLOPS | 364.8 GFLOPS |
| FP16 | Not listed | 729.6 GFLOPS (2:1) |
| TDP | 16 W | 15 W |
| Slot Width | MXM Module | IGP |
| Power Connectors | None | Not listed |
| Bus Interface | PCIe 3.0 x8 | Ring Bus |
| Display Outputs | Portable Device Dependent | Motherboard Dependent |
| DirectX | 12 (11_0) | 12 (12_1) |
| Vulkan | 1.4 | 1.3 |
| Release Date | 2016-03-24 | 2015-08-31 |
| Predecessor | GeForce 800M | Not listed |
| Successor | GeForce 10 Mobile | Not listed |
FAQ
Q: Which GPU is faster in Vulkan workloads?
A: The NVIDIA GeForce 920MX is significantly faster, scoring 2987 in Geekbench Vulkan versus 1422 for the Intel HD Graphics 530, a 110.1% advantage.
Q: Does the Intel HD Graphics 530 outperform the 920MX in any benchmark?
A: The Intel part has a higher Geekbench Metal score (5025) but no comparable Metal score exists for the 920MX. In the shared OpenCL and Vulkan tests, the 920MX wins both.
Q: What is the average benchmark score difference between the two?
A: The 920MX has an average benchmark score of 3528, while the HD 530 averages 3332. The NVIDIA part also ranks at the 21st percentile of all GPUs, versus the 20th percentile for Intel.
Q: Which GPU has a smaller manufacturing process node?
A: The Intel HD Graphics 530 is built on a 14 nm+ process, while the NVIDIA GeForce 920MX uses a larger 28 nm process. Intel’s node is manufactured in-house, whereas NVIDIA uses TSMC.
Q: How much dedicated memory does each GPU have?
A: The 920MX has 2 GB of dedicated DDR3 memory on a 64-bit bus with 14.40 GB/s bandwidth. The HD 530 uses system shared memory, with bandwidth described as system dependent.
Q: Which GPU supports a higher DirectX feature level?
A: The Intel HD Graphics 530 supports DirectX 12 (12_1), while the NVIDIA GeForce 920MX only reaches DirectX 12 (11_0). This gives Intel an advantage in API feature support despite its lower raw performance.
Where Each One Wins
The NVIDIA GeForce 920MX is the clear winner for compute-heavy and graphics-intensive tasks. Its 14.6% lead in OpenCL and 110.1% lead in Vulkan make it the superior choice for any workload that leverages these APIs. The dedicated 2 GB of DDR3 memory with 14.40 GB/s bandwidth ensures that data transfer does not bottleneck the GPU, which is a common issue with shared-memory solutions. With a pixel rate of 7.944 GPixel/s and FP32 performance of 508.4 GFLOPS, it is better equipped for real-time rendering and general-purpose GPU computing. Its nearest rivals sit close, the GeForce GT 545 is just 1.8% behind its average score, but the 920MX holds its ground.
The Intel HD Graphics 530 wins in scenarios where power efficiency and platform integration matter more than raw throughput. Its 15 W TDP is marginally lower than the 920MX’s 16 W, and as an IGP it requires no additional power connectors or MXM module. The 14 nm+ process node is more advanced, and the support for DirectX 12 (12_1) means it is better positioned for modern API features. Its FP16 capability at 729.6 GFLOPS could be an advantage in workloads that use half-precision arithmetic, and the Metal score of 5025 suggests strong performance in Apple-centric environments. The HD 530’s nearest rival, the GeForce GT 730M, is only 0.5% ahead, showing it is competitive within its peer group.
For users making a choice strictly from the data, the GeForce 920MX is the performance pick, while the HD Graphics 530 is the integration pick. The benchmark results do not show a single shared test where Intel wins, so any decision favoring Intel must rest on feature support, power draw, or platform simplicity rather than measured graphics performance.