AMD Ryzen AI Embedded P164 vs Intel Core i7-13850HX Comparison

The AMD Ryzen AI Embedded P164 and Intel Core i7-13850HX are both mobile processors, but they target different corners of the performance envelope. The AMD part, built on a 4 nm TSMC process with 8 cores and 16 threads, posts a higher average benchmark score and a higher single-thread result, while the Intel part, a 20-core, 28-thread Raptor Lake-HX chip on Intel's 10 nm process, wins the majority of the head-to-head PassMark tests. The recorded data shows a clear split: AMD for single-thread efficiency, Intel for multi-thread throughput.

FAQ

Q: Which processor has more cores and threads?

A: The Intel Core i7-13850HX has 20 cores and 28 threads, while the AMD Ryzen AI Embedded P164 has 8 cores and 16 threads.

Q: Which processor has the higher single-thread benchmark score?

A: The AMD Ryzen AI Embedded P164 scores 4029 in PassMark single-thread, 6.9% ahead of the Intel Core i7-13850HX's 3769.

Q: Which processor has the higher average benchmark score?

A: The AMD Ryzen AI Embedded P164 has an average benchmark score of 52901, compared to 50761 for the Intel Core i7-13850HX. The AMD part also sits at the 91st percentile of all CPUs, one point above Intel's 90th.

Q: Which processor has the larger L3 cache?

A: The Intel Core i7-13850HX has 30 MB of shared L3 cache, while the AMD Ryzen AI Embedded P164 has 8 MB.

Q: Which processor supports ECC memory?

A: Both support ECC memory. The AMD part supports DDR5 and LPDDR5X, while the Intel part supports DDR4 and DDR5.

Q: Which processor has a higher boost clock?

A: The Intel Core i7-13850HX boosts to 5.30 GHz, while the AMD Ryzen AI Embedded P164 boosts to 5.00 GHz.

Architecture Differences

The two chips come from different foundries and process nodes. The AMD Ryzen AI Embedded P164 is built on TSMC's 4 nm process with a die size of 233 mm², while the Intel Core i7-13850HX uses Intel's 10 nm process with a die size of 257 mm². The AMD part uses the Gorgon Point codename and a Zen 5 / Zen 5c generation, while the Intel part is Raptor Lake-HX.

Core and thread counts differ sharply: 8 cores and 16 threads on the AMD side versus 20 cores and 28 threads on the Intel side. Cache hierarchies also diverge. Both have 80 KB of L1 per core, but the AMD part has 1 MB of L2 per core and 8 MB of L3, while the Intel part has 2 MB of L2 per core and 30 MB of shared L3. The larger L3 on Intel is a significant advantage for workloads that reuse data.

Memory support differs: the AMD part supports DDR5 and LPDDR5X with a recorded memory bandwidth of 89.6 GB/s, while the Intel part supports DDR4 and DDR5 with no recorded bandwidth figure. Both use dual-channel memory buses. PCIe connectivity also differs: the AMD part offers Gen 4 with 16 CPU lanes, while the Intel part offers Gen 5 with 20 CPU lanes.

Integrated graphics differ as well. The AMD part carries a Radeon 880M, while the Intel part has UHD Graphics 770. Both are mobile parts, and both are active in production. The AMD part has a TDP of 28 W, while the Intel part has a TDP of 55 W. The Intel part has an unlocked multiplier, while the AMD part does not. The Intel part has a part number of SRMEA, while the AMD part's part number is unknown. The AMD part was released on 2026-03-08, while the Intel part was released on 2023-01-03.

The Verdict

The data points in two directions. The AMD Ryzen AI Embedded P164 wins the single-thread PassMark test by 6.9% (4029 vs 3769) and has a higher average benchmark score (52901 vs 50761) and a higher percentile rank (91st vs 90th). It also draws less power, with a 28 W TDP versus 55 W for the Intel part. For workloads that are latency-sensitive or lightly threaded, the AMD part is the better choice.

The Intel Core i7-13850HX wins 9 of the 11 head-to-head PassMark tests, including multithread (36870 vs 25889, a 29.8% lead), physics (2483 vs 1210, a 51.3% lead), integer math (126852 vs 87940, a 30.7% lead), and floating-point math (92369 vs 55799, a 39.6% lead). It also has more cores, more threads, a larger L3 cache, and a higher boost clock (5.30 GHz vs 5.00 GHz). For heavily threaded compute, the Intel part is the clear winner.

The Intel part has a launch MSRP of $428. The AMD part has no recorded launch MSRP. The choice comes down to workload: pick the AMD for single-thread performance and lower power, pick the Intel for multi-thread throughput and cache-heavy workloads.

Specification Differences

The two processors differ in the following recorded fields:

• Cores: 8 (AMD) vs 20 (Intel)
• Threads: 16 (AMD) vs 28 (Intel)
• Base clock: 2.00 GHz (AMD) vs 2.10 GHz (Intel)
• Boost clock: 5.00 GHz (AMD) vs 5.30 GHz (Intel)
• TDP: 28 W (AMD) vs 55 W (Intel)
• Socket: AMD Socket FP8 vs Intel BGA 1964
• Architecture: null (AMD) vs Raptor Lake (Intel)
• Codename: Gorgon Point (AMD) vs Raptor Lake-HX (Intel)
• Generation: Ryzen AI Embedded (Zen 5 / Zen 5c) vs Core i7 (Raptor Lake-HX)
• Process node: 4 nm (AMD) vs 10 nm (Intel)
• Foundry: TSMC (AMD) vs Intel (Intel)
• Die size: 233 mm² (AMD) vs 257 mm² (Intel)
• L2 cache: 1 MB per core (AMD) vs 2 MB per core (Intel)
• L3 cache: 8 MB (AMD) vs 30 MB shared (Intel)
• Memory support: DDR5, LPDDR5X (AMD) vs DDR4, DDR5 (Intel)
• Memory bandwidth: 89.6 GB/s (AMD) vs null (Intel)
• PCIe: Gen 4, 16 lanes (AMD) vs Gen 5, 20 lanes (Intel)
• Integrated graphics: Radeon 880M (AMD) vs UHD Graphics 770 (Intel)
• Release date: 2026-03-08 (AMD) vs 2023-01-03 (Intel)
• Launch MSRP: null (AMD) vs $428 (Intel)
• Multiplier unlocked: false (AMD) vs true (Intel)
• Part number: unknown (AMD) vs SRMEA (Intel)

Fields that are identical: L1 cache (80 KB per core), memory bus (dual-channel), ECC support (true), market segment (mobile), production status (active).

Head-to-Head Benchmarks

The head-to-head PassMark results show a dominant Intel performance in most tests. The largest Intel lead is in find prime numbers, where the Intel part scores 184 against the AMD's 71, a 61.4% advantage. Physics follows with 2483 vs 1210, a 51.3% lead. Floating-point math shows 92369 vs 55799, a 39.6% lead, and data encryption shows 26062 vs 16055, a 38.4% lead. Integer math is 126852 vs 87940, a 30.7% lead. Multithread is 36870 vs 25889, a 29.8% lead. Random string sorting is 49198 vs 34801, a 29.3% lead. Data compression is 441525 vs 327891, a 25.7% lead. Extended instructions are 26586 vs 24193, a 9% lead.

The AMD part wins only the single-thread test, scoring 4029 against Intel's 3769, a 6.9% lead. This result appears twice in the recorded data, once as passmark_single_thread and once as passmark_singlethread, with identical scores.

The overall tally is 9 wins for Intel and 2 wins for AMD (the two single-thread entries). The average benchmark scores tell a slightly different story: the AMD part averages 52901, which is 0.1% ahead of the AMD Ryzen 5 9500F (52873) and 0.1% behind the Intel Xeon 634 (52974). The Intel part averages 50761, which is 0.1% ahead of the AMD Ryzen 9 5900XT (50718) and 0.5% behind the Intel Core i9-14900T (51015). The AMD part's nearest rivals also include the AMD EPYC 7313P (53206, 0.6% behind) and the AMD Ryzen 9 7900X (53288, 0.7% behind). The Intel part's nearest rivals also include the AMD Ryzen AI 9 HX PRO 370 (50448, 0.6% ahead) and the Intel Core i9-13980HX (50398, 0.7% ahead).