AMD Radeon HD 8730M vs Intel UHD Graphics 730 Comparison

FAQ

Q: Which GPU wins in Geekbench OpenCL performance?

A: The Intel UHD Graphics 730 scores 5988 in Geekbench OpenCL, while the AMD Radeon HD 8730M scores 5955. The Intel part wins by 0.6%, a margin within run-to-run variance but still a measurable lead.

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

A: The AMD Radeon HD 8730M sits directly between the NVIDIA Quadro K620M (5957, 0% delta) and the AMD Radeon HD 8750M (5970, -0.3% delta), with the Intel UHD Graphics 730 (5929, 0.4% delta) close behind. For Intel, the closest rival is the AMD Radeon HD 8730M itself at -0.4% delta, followed by the Quadro K620M at -0.5%.

Q: What is the average benchmark score for each GPU?

A: The AMD Radeon HD 8730M has an average benchmark score of 5955, while the Intel UHD Graphics 730 averages 5929. Interestingly, the Intel part’s single OpenCL score (5988) is higher than its average because it also has a Vulkan score of 5870.

Q: Which GPU has a higher boost clock?

A: The Intel UHD Graphics 730 boosts to 1300 MHz, compared to the AMD Radeon HD 8730M’s 700 MHz boost. The AMD part’s base clock is 650 MHz, while Intel’s base is 300 MHz.

Q: What are the direct API level differences?

A: The Intel UHD Graphics 730 supports DirectX 12 (12_1) and Vulkan 1.4, while the AMD Radeon HD 8730M supports DirectX 12 (11_1) and Vulkan 1.2.170. Both support OpenGL 4.6.

Q: Which GPU has a higher pixel fill rate?

A: The Intel UHD Graphics 730 achieves 10.40 GPixel/s, nearly double the AMD Radeon HD 8730M’s 5.600 GPixel/s. This stems from Intel’s higher clock speeds despite having the same 8 ROPs.

The Verdict

The data presents a close contest, with the Intel UHD Graphics 730 taking the single head-to-head benchmark win. The Intel part’s OpenCL score of 5988 edges out AMD’s 5955 by 0.6%, and its Vulkan score of 5870 provides an additional data point that AMD lacks entirely. However, the AMD Radeon HD 8730M’s average benchmark score of 5955 is actually higher than Intel’s 5929 average, because Intel’s Vulkan result drags its mean down.

For users prioritizing raw pixel throughput, the Intel UHD Graphics 730 is the clear choice — its 10.40 GPixel/s versus AMD’s 5.600 GPixel/s is a substantial gap. The Intel part also offers a significant boost clock advantage (1300 MHz vs 700 MHz) and a newer API feature set, including DirectX 12 (12_1) and Vulkan 1.4. The AMD part, however, counters with a 384 shading units versus Intel’s 192, and a higher texture rate (16.80 GTexel/s vs 15.60 GTexel/s) despite having more TMUs (24 vs 12). Its dedicated 2 GB DDR3 memory on a 128-bit bus with 28.80 GB/s bandwidth stands in contrast to Intel’s system-shared memory with system-dependent bandwidth.

Given the 0.6% OpenCL delta and the additional Vulkan benchmark, the Intel UHD Graphics 730 is the better pick for balanced compute workloads. The AMD Radeon HD 8730M remains viable for scenarios where dedicated memory and higher shader count matter more than clock speed and fill rate, but the head-to-head result favors Intel.

Head-to-Head Benchmarks

The only direct comparison available is Geekbench OpenCL, where the Intel UHD Graphics 730 scores 5988 against the AMD Radeon HD 8730M’s 5955. This yields a deltaPct of -0.6% from AMD’s perspective, meaning Intel leads by six-tenths of a percent. In absolute terms, that is a 33-point difference — well within typical noise for OpenCL workloads.

Looking at the broader rival landscape, both GPUs occupy a tight performance cluster. The AMD Radeon HD 8730M’s nearest rival, the NVIDIA Quadro K620M, scores 5957 with a 0% delta, effectively a tie. The AMD Radeon HD 8750M sits at 5970 (-0.3% from the 8730M), and the NVIDIA Quadro K4000 leads at 5982 (-0.5%). The Intel UHD Graphics 730, by contrast, trails all of these in its own rival list: the 8730M at -0.4%, the Quadro K620M at -0.5%, the HD 8750M at -0.7%, and the Quadro K4000 at -0.9%.

Yet the direct head-to-head contradicts the rival-list ordering. Intel’s OpenCL score of 5988 is higher than all four rivals listed for AMD, including the Quadro K4000’s 5982. This suggests the Intel part’s performance is slightly front-loaded in OpenCL, while its Vulkan score of 5870 pulls its average down to 5929. For users relying solely on OpenCL, Intel’s part is marginally faster; for Vulkan-centric workloads, the AMD part has no published result to compare.

The pixel rate comparison is more decisive. Intel’s 10.40 GPixel/s is 85.7% higher than AMD’s 5.600 GPixel/s. This advantage comes from Intel’s 1300 MHz boost clock, which more than compensates for its lower base clock of 300 MHz. In texture rate, AMD edges ahead at 16.80 GTexel/s versus Intel’s 15.60 GTexel/s, a 7.7% lead driven by AMD’s 24 TMUs against Intel’s 12.

Specification Differences

The two GPUs diverge sharply on memory architecture. The AMD Radeon HD 8730M uses 2 GB of dedicated DDR3 memory on a 128-bit bus, delivering 28.80 GB/s of bandwidth at 900 MHz (1800 Mbps effective). The Intel UHD Graphics 730 relies on system-shared memory, with bus width and bandwidth listed as “System Shared” and “System Dependent” respectively. This means Intel’s memory performance is entirely dependent on the host platform’s RAM configuration.

Clock speeds show a similar split. AMD runs at a 650 MHz base and 700 MHz boost, while Intel operates at 300 MHz base and 1300 MHz boost. The boost clock delta is 600 MHz in Intel’s favor, though AMD’s base clock is 350 MHz higher. Pixel rate favors Intel at 10.40 GPixel/s versus AMD’s 5.600 GPixel/s, but texture rate favors AMD at 16.80 GTexel/s versus Intel’s 15.60 GTexel/s.

Compute unit counts differ significantly. AMD fields 384 shading units, 24 TMUs, and 8 ROPs, while Intel has 192 shading units, 12 TMUs, and 8 ROPs. The FP32 throughput reflects this: AMD reaches 537.6 GFLOPS, while Intel hits 499.2 GFLOPS. Intel also lists FP16 at 998.4 GFLOPS (2:1 rate), a figure AMD does not provide. The TDP is listed only for Intel at 15 W; AMD’s TDP is absent from the data. Intel’s slot width is “IGP”, while AMD’s is unspecified. The bus interface differs: AMD uses PCIe 3.0 x8, Intel uses Ring Bus. Display outputs are “Motherboard Dependent” for Intel, with no listing for AMD.

Architecture Differences

The AMD Radeon HD 8730M is built on GCN 1.0 architecture, using a 28 nm process at TSMC with 950 million transistors on a 77 mm² die, yielding a transistor density of 12.3M per mm². Its chip is codenamed Mars, and it belongs to the Solar System generation (HD 8700M). The Intel UHD Graphics 730 uses Generation 12.1 architecture, fabricated on Intel’s 14 nm+++ process with the Rocket Lake chip. Intel does not list transistor count, die size, or density.

The manufacturing contrast is stark: AMD’s 28 nm node versus Intel’s 14 nm+++ process. The AMD part’s predecessor is listed as “London” and its successor as “Gem System,” while Intel lists no predecessor or successor. Both are marked as end-of-life, with AMD releasing in March 2013 and Intel in March 2021 — an eight-year gap that shows in the API support. AMD’s DirectX 12 (11_1) and Vulkan 1.2.170 lag Intel’s DirectX 12 (12_1) and Vulkan 1.4.

The memory controller is another architectural differentiator. AMD integrates a dedicated DDR3 interface with a fixed 128-bit bus and 28.80 GB/s peak bandwidth. Intel’s design shares system memory through the Ring Bus, making bandwidth and capacity platform-dependent. Similarly, display outputs for Intel are motherboard-dependent since the GPU is integrated, whereas AMD’s mobile discrete design does not list outputs.

Both support OpenGL 4.6. The shading architecture favors AMD numerically — 384 unified shaders versus 192 — but Intel’s higher clocks and newer architecture close the compute gap. The FP16 capability on Intel (998.4 GFLOPS at 2:1) hints at more modern execution units, though AMD does not report an FP16 figure. The pixel rate advantage for Intel (10.40 vs 5.600 GPixel/s) combined with its lower ROP count (8 vs 8) suggests Intel’s ROPs are clocked nearly twice as fast.