AMD Ryzen Embedded V2546 vs Intel Core 5 120UL Comparison

The AMD Ryzen Embedded V2546 and Intel Core 5 120UL are two very different processors that target the same desktop embedded space. The data shows a clear split: Intel wins the majority of benchmark tests, but AMD secures decisive victories in specific workloads. The Intel Core 5 120UL takes 13 of the 17 head-to-head comparisons, while the AMD Ryzen Embedded V2546 wins four. The average benchmark scores are close, with the AMD part at 14336 and the Intel part at 13594, putting the Ryzen Embedded V2546 in the 69th percentile of all CPUs and the Core 5 120UL in the 68th. Despite the Intel chip winning more tests, the overall performance picture is more nuanced than a simple win count suggests.

Where Each One Wins

The Intel Core 5 120UL dominates in general-purpose computing and heavily threaded rendering workloads. It wins every Cinebench test, including multi-core and single-core variants across R15, R20, and R23. The Intel chip also leads in PassMark's multithread test, floating point math, integer math, physics, and prime number finding. This makes it the stronger choice for video rendering, physics simulations, and number-crunching tasks that scale across cores.

The AMD Ryzen Embedded V2546, by contrast, establishes its wins in data handling and specialized instruction workloads. It wins PassMark's data compression test by a wide margin, along with data encryption, extended instructions, and random string sorting. These results indicate that the AMD processor is better suited for compression workloads, encryption tasks, and workloads that leverage extended CPU instruction sets. The AMD part also holds a slight edge in the average benchmark score, 14336 versus 13594, despite losing the majority of individual tests.

The use-case split is stark: Intel for raw compute throughput and rendering, AMD for data transformation and security-related tasks. For a system that primarily runs Cinebench-style workloads, the Intel chip is the obvious pick. For a system that handles compressed data streams or heavy encryption, the AMD processor is the better fit.

Architecture Differences

The two processors come from different architectural eras and foundries. The AMD Ryzen Embedded V2546 uses the Zen 2 architecture, specifically the Renoir codename, built on a 7 nm process at TSMC. It packs 9,800 million transistors into a 156 mm² die. The Intel Core 5 120UL uses Raptor Lake, specifically the Raptor Lake-PS codename, built on Intel's 10 nm process. The Intel chip has no listed transistor count or die size in the database.

Core configurations differ substantially. The AMD chip has 6 cores and 12 threads, while the Intel chip has 10 cores and 12 threads. Both support 12 threads, but Intel achieves this with more physical cores. The Intel chip has a lower base clock of 1.30 GHz but a much higher boost clock of 4.60 GHz, compared to the AMD chip's 3.00 GHz base and 3.95 GHz boost. The TDP ratings are also very different: the AMD part is rated at 35 watts, while the Intel part is rated at 15 watts.

Cache hierarchies are notably different. The AMD chip has 64 KB of L1 cache per core, 512 KB of L2 per core, and 8 MB of shared L3 cache. The Intel chip has 80 KB of L1 per core, 1.25 MB of L2 per core, and 12 MB of shared L3 cache. The Intel part has a larger cache at every level, which helps explain its single-thread advantage.

Memory support differs as well. The AMD chip supports DDR4 only, with dual-channel memory and a recorded bandwidth of 51.2 GB/s. The Intel chip supports both DDR4 and DDR5, also dual-channel, but no bandwidth figure is recorded. The AMD chip supports ECC memory, while the Intel chip does not. PCIe support also differs: the AMD chip provides PCIe Gen 3 with 20 CPU lanes, while the Intel chip provides PCIe Gen 4 with 8 CPU lanes.

Integrated graphics diverge as well. The AMD chip includes Radeon Graphics with 384 shader processors, while the Intel chip includes Iris Xe Graphics with 80 execution units. The AMD chip uses the AMD Socket FP6, while the Intel chip uses Intel Socket 1700. The AMD part was released on 2020-11-09, while the Intel part launched later on 2024-04-07. Both are currently marked as active production parts.

Head-to-Head Benchmarks

The Cinebench results are consistent across all three versions of the benchmark. In Cinebench R15 multi-core, the Intel chip scores 904 against the AMD chip's 827, a delta of -8.5% for the AMD part. The single-core R15 test shows 127 versus 116, a delta of -8.7%. Cinebench R20 multi-core shows 3769 versus 3446, a delta of -8.6%, and single-core shows 531 versus 486, also -8.5%. Cinebench R23 multi-core shows 8974 versus 8207, and single-core shows 1266 versus 1158, both at -8.5% deltas. The consistency of the ~8.5% gap across all Cinebench workloads indicates a stable performance advantage for the Intel chip in rendering tasks.

PassMark results tell a more varied story. The AMD chip wins data compression decisively: 136097 versus 109090, a 24.8% advantage. Data encryption goes to AMD at 8046 versus 7685, a 4.7% edge. Extended instructions is the largest AMD win: 8799 versus 5203, a 69.1% advantage. Random string sorting is a narrow AMD win at 13926 versus 13610, a 2.3% margin.

The Intel chip's PassMark wins are substantial in several areas. Floating point math goes to Intel at 26311 versus 18534, a 29.6% advantage. Integer math goes to Intel at 38060 versus 30739, a 19.2% edge. Physics is a major Intel win at 807 versus 441, a 45.4% advantage. Find prime numbers shows Intel at 47 versus AMD's 22, a 53.2% gap. The multithread test goes to Intel at 10558 versus 9656, an 8.5% margin. Single-thread performance shows Intel at 2080 versus 1609, a 22.6% advantage.

The PassMark physics result is particularly notable: the Intel chip scores 807 against the AMD chip's 441, a gap of 45.4%. This aligns with the Intel chip's higher boost clock and larger cache. The extended instructions result is the inverse: the AMD chip's 69.1% advantage suggests its Zen 2 architecture handles those specific instruction workloads much more efficiently than Intel's Raptor Lake design.

FAQ

Q: Which processor has the higher single-core performance?

A: The Intel Core 5 120UL wins all single-core tests. In PassMark single-thread it scores 2080 against the AMD chip's 1609, a 22.6% advantage. Cinebench R23 single-core shows 1266 versus 1158, an 8.5% gap.

Q: Does the AMD Ryzen Embedded V2546 win any benchmark categories?

A: Yes. The AMD chip wins four head-to-head tests: data compression (136097 versus 109090, 24.8% ahead), data encryption (8046 versus 7685, 4.7% ahead), extended instructions (8799 versus 5203, 69.1% ahead), and random string sorting (13926 versus 13610, 2.3% ahead).

Q: How do the core counts compare between the two processors?

A: The AMD Ryzen Embedded V2546 has 6 cores and 12 threads. The Intel Core 5 120UL has 10 cores and 12 threads. Both support 12 threads, but the Intel chip uses more physical cores to achieve this.

Q: Which processor supports ECC memory?

A: The AMD Ryzen Embedded V2546 supports ECC memory. The Intel Core 5 120UL does not support ECC memory. This is a key differentiator for systems requiring error-correcting memory.

Q: What are the TDP ratings for each processor?

A: The AMD Ryzen Embedded V2546 is rated at 35 watts, while the Intel Core 5 120UL is rated at 15 watts. The Intel chip offers a lower power envelope despite its higher boost clock.

Q: How do the average benchmark scores compare?

A: The AMD Ryzen Embedded V2546 has an average benchmark score of 14336, placing it in the 69th percentile of all CPUs. The Intel Core 5 120UL has an average score of 13594, placing it in the 68th percentile. The AMD chip holds a slight overall edge despite winning fewer individual tests.

The Verdict

The Intel Core 5 120UL is the better choice for workloads that depend on raw compute throughput. It wins every Cinebench test, the PassMark multithread test, floating point math, integer math, physics, and prime number finding. The consistent ~8.5% advantage across all Cinebench versions indicates a reliable edge in rendering and CPU-bound tasks. Its higher boost clock of 4.60 GHz and larger cache hierarchy, including 12 MB of shared L3 cache, support this performance profile. The 15-watt TDP makes it an efficient option for systems where power draw matters.

The AMD Ryzen Embedded V2546 is the better choice for data-centric workloads. Its 24.8% lead in data compression and 69.1% lead in extended instructions make it the stronger processor for compression, encryption, and specialized instruction workloads. The 4.7% edge in data encryption and 2.3% edge in random string sorting reinforce this pattern. ECC memory support adds value for systems that require error correction. The 35-watt TDP is higher than the Intel chip's 15 watts, but the AMD part compensates with a 51.2 GB/s memory bandwidth figure.

For a general-purpose system running a mix of workloads, the Intel Core 5 120UL wins more tests and offers better single-thread performance, a 22.6% lead in PassMark single-thread. For a system dedicated to compression, encryption, or instruction-heavy data processing, the AMD Ryzen Embedded V2546 is the stronger pick. The data does not support a single universal winner. It supports a workload-dependent choice between two differently optimized processors.