AMD Ryzen Embedded 9600X vs Intel Core Ultra 5 235 Comparison

AMD Ryzen Embedded 9600X and Intel Core Ultra 5 235 occupy different positions in the desktop processor landscape. The AMD part is a 6-core, 12-thread Zen 5 design built for embedded systems, while the Intel part is a 14-core, 14-thread Arrow Lake-S processor aimed at mainstream desktops. The recorded data shows a clear split in workload strengths, with the Intel chip dominating multithreaded and math-heavy tasks and the AMD chip holding advantages in specific single-thread and memory-sensitive scenarios. This analysis relies exclusively on the benchmark results and specifications in the database.

Where Each One Wins

The Intel Core Ultra 5 235 wins decisively in multicore rendering workloads. In Cinebench R15 multicore, it scores 1488, while the AMD Ryzen Embedded 9600X has no recorded score in this test. The same pattern appears in Cinebench R20 multicore, where Intel scores 6202, and in Cinebench R23 multicore, where it reaches 14769. These results indicate a substantial lead in heavily threaded tasks, which aligns with the Intel part's 14 cores versus the AMD part's 6 cores.

The Intel processor also dominates PassMark math and encryption tests. It scores 87948 in integer math, 117951 in floating point math, and 32752 in extended instructions. Data encryption shows a score of 29293, and data compression reaches 390711. The multithread score of 37816 further confirms its strength in parallel workloads. Random string sorting yields 48980, and physics simulation scores 2570. These figures place the Intel chip well ahead in compute-heavy applications.

The AMD Ryzen Embedded 9600X, however, has no recorded benchmark scores in the database. Its wins are therefore based on architectural and specification advantages rather than measured performance. The AMD part supports ECC memory, which the Intel part does not. It also offers a higher boost clock of 5.40 GHz compared to the Intel's 5.00 GHz. The AMD chip has a smaller process node at 4 nm versus the Intel's 3 nm, though both are fabricated by TSMC. The AMD part features a larger shared L3 cache of 32 MB, while the Intel part has 24 MB. These differences suggest potential advantages in latency-sensitive workloads and memory reliability, even without direct benchmark confirmation.

Architecture Differences

The two processors use fundamentally different core designs. The AMD Ryzen Embedded 9600X uses the Zen 5 architecture under the Granite Ridge codename, part of the Ryzen Embedded generation. It contains 6 cores and 12 threads, meaning each core supports two threads. The Intel Core Ultra 5 235 uses the Arrow Lake architecture under the Arrow Lake-S codename, part of the Core Ultra Series 2 generation. It contains 14 cores and 14 threads, meaning each core supports a single thread. This difference explains why the Intel part excels in raw multicore throughput despite having no simultaneous multithreading: it simply has more physical cores.

Cache hierarchies differ significantly. The AMD part allocates 80 KB of L1 cache per core, 1 MB of L2 cache per core, and 32 MB of shared L3 cache. The Intel part allocates 192 KB of L1 cache per core, 3 MB of L2 cache per core, and 24 MB of shared L3 cache. Per-core cache capacities favor Intel, but total L3 capacity favors AMD. The larger L3 on the AMD chip could benefit workloads that repeatedly access a moderate-sized working set.

Process technology sets them apart. The AMD chip uses a 4 nm node, while the Intel chip uses a 3 nm node. Both are fabricated by TSMC, but the Intel part integrates 17,800 million transistors on a 243 mm² die, whereas the AMD part integrates 8,315 million transistors on a 70.6 mm² die. The Intel die is more than three times larger in area and holds more than twice the transistor count. This reflects the Intel part's higher core count and larger per-core cache allocation.

Memory support also diverges. Both support DDR5 and dual-channel memory, but the AMD part has a memory bandwidth of 89.6 GB/s, while the Intel part reaches 102.4 GB/s. The Intel chip thus has a theoretical bandwidth advantage of roughly 14 percent. ECC memory support exists only on the AMD part, making it suitable for error-sensitive embedded or server-adjacent workloads. The Intel part does not support ECC.

PCIe connectivity differs as well. The AMD part provides Gen 5 with 24 lanes from the CPU, while the Intel part provides Gen 5 with 20 lanes. The AMD chip offers four additional CPU lanes, which can matter for systems with multiple high-bandwidth devices. Integrated graphics also differ: the AMD part uses Radeon Graphics, while the Intel part uses Arc Xe-LPG Graphics 24EU. No benchmark scores exist for either integrated GPU in the database, so performance comparisons are not possible.

Clock speeds show a mixed picture. The AMD part has a base clock of 3.90 GHz and a boost clock of 5.40 GHz. The Intel part has a base clock of 3.40 GHz and a boost clock of 5.00 GHz. The AMD chip holds a 0.50 GHz advantage in base clock and a 0.40 GHz advantage in boost clock. These higher clocks could translate to a single-thread advantage, although the Intel chip's recorded single-core Cinebench scores do not reflect a deficit because no AMD scores are available for comparison.

The multiplier is unlocked on the AMD part, while the Intel part has a locked multiplier. This means the AMD chip supports manual overclocking, whereas the Intel chip does not. Overclocking headroom could partially offset the Intel part's core-count advantage in multithreaded tasks, though the database contains no overclocking results.

The Verdict

The Intel Core Ultra 5 235 is the clear choice for multicore rendering, math-heavy computation, and data compression or encryption workloads. Its Cinebench R23 multicore score of 14769 and PassMark multithread score of 37816 place it firmly in the upper tier of desktop processors, with a percentile ranking of 89 among all CPUs. The nearest rivals in the database, the AMD Ryzen AI 9 HX 375 and the Intel Core i9-13900HX, show average scores of 46030 and 46098 respectively, with performance deltas of 0.1 percent and negative 0.1 percent. The Intel Core Ultra 5 235 scores essentially neck-and-neck with those parts, confirming its position in the high-performance desktop segment.

The AMD Ryzen Embedded 9600X, despite lacking recorded benchmark scores, offers specific advantages that matter for certain use cases. ECC memory support makes it the only option of the two for systems requiring error-correcting memory. The larger 32 MB L3 cache and higher boost clock of 5.40 GHz could improve performance in cache-sensitive and lightly threaded workloads. The unlocked multiplier adds flexibility for users who intend to overclock. The AMD part also provides more PCIe lanes at 24 versus 20, which benefits multi-device configurations.

For general-purpose desktop use with heavy multitasking, rendering, or scientific computing, the Intel part wins on measured performance. For embedded systems, reliability-focused builds, or workloads that depend on ECC memory and large shared caches, the AMD part holds the architectural edge. The database shows zero benchmark wins for either side in head-to-head testing because no head-to-head benchmark data exists, but the Intel part's substantial recorded scores in every available test make it the performance leader in all measured categories.

FAQ

Q: Which processor has more cores?

A: The Intel Core Ultra 5 235 has 14 cores and 14 threads. The AMD Ryzen Embedded 9600X has 6 cores and 12 threads. The Intel part has more physical cores, while the AMD part supports simultaneous multithreading on each core.

Q: Does either processor support ECC memory?

A: Only the AMD Ryzen Embedded 9600X supports ECC memory. The Intel Core Ultra 5 235 does not list ECC memory support in the database.

Q: What are the boost clock speeds?

A: The AMD Ryzen Embedded 9600X boosts to 5.40 GHz, and the Intel Core Ultra 5 235 boosts to 5.00 GHz. The AMD part has a 0.40 GHz higher peak boost clock.

Q: Which processor has a higher memory bandwidth?

A: The Intel Core Ultra 5 235 has a memory bandwidth of 102.4 GB/s, while the AMD Ryzen Embedded 9600X has 89.6 GB/s. The Intel part holds a roughly 14 percent theoretical bandwidth advantage.

Q: Is the multiplier unlocked on either processor?

A: The AMD Ryzen Embedded 9600X has an unlocked multiplier. The Intel Core Ultra 5 235 has a locked multiplier, so it does not support manual overclocking.

Q: What is the Intel part's percentile ranking?

A: The Intel Core Ultra 5 235 ranks in the 89th percentile among all CPUs in the database, with an average benchmark score of 46062. No percentile data is recorded for the AMD Ryzen Embedded 9600X.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries between these two processors, so direct comparisons rely on the Intel part's recorded scores and the AMD part's specifications. The Intel Core Ultra 5 235 delivers its strongest results in Cinebench R23 multicore, scoring 14769. This score, combined with a Cinebench R20 multicore score of 6202 and a Cinebench R15 multicore score of 1488, shows a processor built for sustained multithreaded output. Single-core Cinebench scores for the Intel part are 2085 in R23, 875 in R20, and 210 in R15, which are competitive for a desktop chip but cannot be directly compared to the AMD part due to missing data.

In PassMark tests, the Intel part shows its widest margins. Floating point math scores 117951, integer math scores 87948, and extended instructions scores 32752. Data compression reaches 390711, data encryption reaches 29293, and random string sorting reaches 48980. The physics test scores 2570, and the find prime numbers test scores 371. The single-thread score is 4516, and the multithread score is 37816. These numbers establish the Intel part as a strong all-around performer, particularly in arithmetic and compression tasks.

The AMD Ryzen Embedded 9600X has no recorded scores in any of these tests. Its case rests on architectural merits: a 5.40 GHz boost clock, 32 MB of shared L3 cache, ECC support, 24 PCIe Gen 5 lanes, and an unlocked multiplier. The Intel part counters with 14 cores, a 102.4 GB/s memory bandwidth, a 3 nm process node, and a 24 MB shared L3 cache. For users who prioritize measured multicore performance, the Intel part is the only option with data to support it. For users who prioritize ECC memory, overclocking flexibility, or a larger shared cache, the AMD part offers features the Intel part lacks.

The Intel part's nearest rivals in the database include the AMD Ryzen AI 9 HX 375 with an average score of 46030 and a performance delta of 0.1 percent, and the Intel Core i9-13900HX with an average score of 46098 and a performance delta of negative 0.1 percent. The Core Ultra 5 235 sits between these two parts in average score at 46062, effectively matching both. The AMD EPYC 4364P and AMD EPYC 7303, with average scores of 45970 and 45960 respectively, sit slightly below at 0.2 percent deltas. This clustering indicates that the Core Ultra 5 235 performs at the level of high-end laptop and server parts from the previous generation.

In the absence of head-to-head results, the database's recorded measurements favor the Intel part in every benchmark category where data exists. The AMD part's specifications suggest it could compete in single-threaded and cache-sensitive workloads, but without recorded scores, no quantitative comparison is possible. The Intel Core Ultra 5 235's 89th percentile ranking and average benchmark score of 46062 place it among the faster desktop processors in the database, while the AMD Ryzen Embedded 9600X remains an unmeasured entry with strong feature-level credentials.