AMD Ryzen AI Embedded P164 vs Intel Core 5 120UL Comparison

The Verdict

The benchmark data positions the AMD Ryzen AI Embedded P164 and Intel Core 5 120UL in distinctly different performance classes. The AMD part wins all 11 recorded head-to-head comparisons, with an average benchmark score of 52,901 against 13,594 for the Intel processor. The AMD chip sits at the 91st percentile among all CPUs in the database, while the Intel part lands at the 68th percentile. For workloads that stress multi-threaded throughput, the AMD Ryzen AI Embedded P164 is the clear choice. The Intel Core 5 120UL, with its lower power envelope and desktop socket, suits scenarios where a 15 W processor is the priority. The recorded data shows no benchmark category where the Intel part pulls ahead, so the decision rests on platform requirements and power constraints rather than measured performance.

Architecture Differences

The AMD Ryzen AI Embedded P164 uses the Gorgon Point codename and belongs to the Ryzen AI Embedded generation built on Zen 5 / Zen 5c cores. It is manufactured on a 4 nm process at TSMC with a die size of 233 mm². The Intel Core 5 120UL uses the Raptor Lake architecture with the Raptor Lake-PS codename, built on Intel's 10 nm process. The AMD processor integrates 8 cores and 16 threads, while the Intel part provides 10 cores and 12 threads, indicating a hybrid configuration where some cores do not contribute additional threads. The AMD chip clocks at 2.00 GHz base and 5.00 GHz boost, compared to 1.30 GHz base and 4.60 GHz boost for the Intel part.

Cache layouts differ substantially. Both parts use 80 KB of L1 per core. The AMD processor has 1 MB of L2 per core and 8 MB of L3 cache. The Intel processor has 1.25 MB of L2 per core and 12 MB of shared L3 cache. The Intel part therefore holds a larger total L3 allocation, but the AMD processor compensates with higher clock speeds and a newer core design. The AMD chip supports DDR5 and LPDDR5X memory with dual-channel access and 89.6 GB/s of memory bandwidth. The Intel part supports DDR4 and DDR5 with dual-channel access, though its memory bandwidth is not recorded in the database. ECC memory is supported on the AMD processor but not on the Intel part.

The AMD Ryzen AI Embedded P164 uses AMD Socket FP8, a mobile-oriented socket, while the Intel Core 5 120UL uses Intel Socket 1700, a desktop socket. The AMD chip provides PCIe Gen 4 with 16 lanes from the CPU, while the Intel part provides PCIe Gen 4 with 8 lanes from the CPU. Integrated graphics also differ: the AMD part uses the Radeon 880M, and the Intel part uses Iris Xe Graphics 80EU. The Intel processor has a 15 W TDP, while the AMD processor has a 28 W TDP. Neither chip has an unlocked multiplier.

Where Each One Wins

The AMD Ryzen AI Embedded P164 wins every recorded benchmark category, but the margin varies by workload type. The largest advantage appears in extended instruction processing, where the AMD part scores 24,193 against 5,203 for the Intel chip, a 365% delta. This indicates a major gap in workloads that use advanced CPU instruction sets. Data compression also favors the AMD part heavily, with a score of 327,891 versus 109,090, a 200.6% delta. Random string sorting shows a 155.7% advantage for the AMD processor, and multi-threaded performance is 145.2% higher.

The Intel Core 5 120UL does not win any of the 11 head-to-head tests, so there is no measured workload category where it takes the lead. Its recorded strengths are relative to its own class, not against the AMD part. The Intel processor's nearest rivals in the database are the Intel Core i3-12100F, Intel Core 3 N355, Intel Core i5-9500, and Intel Core 3 304, with average scores ranging from 13,452 to 13,745. The AMD part's nearest rivals are the AMD Ryzen 5 9500F, Intel Xeon 634, AMD EPYC 7313P, and AMD Ryzen 9 7900X, with average scores from 52,873 to 53,288. This places the two processors in entirely different performance tiers.

The Intel part's lower TDP of 15 W and desktop socket may appeal to systems where thermal limits are strict. The AMD part's 28 W TDP and mobile socket align it with embedded or mobile platforms that can accommodate higher power draw. For single-threaded tasks, the AMD processor scores 4,029 against 2,080, a 93.7% advantage. Even in physics simulation, where the Intel part's closest result appears, the AMD chip leads 1,210 to 807, a 49.9% delta.

FAQ

Q: Which processor has the higher multi-threaded benchmark score?

A: The AMD Ryzen AI Embedded P164 scores 25,889 in the PassMark multi-thread test, which is 145.2% higher than the Intel Core 5 120UL's 10,558.

Q: What is the difference in single-thread performance?

A: The AMD Ryzen AI Embedded P164 scores 4,029 in the PassMark single-thread test, while the Intel Core 5 120UL scores 2,080. The AMD part leads by 93.7%.

Q: How do the core and thread counts compare?

A: The AMD Ryzen AI Embedded P164 has 8 cores and 16 threads. The Intel Core 5 120UL has 10 cores and 12 threads.

Q: Do both processors support ECC memory?

A: No. The AMD Ryzen AI Embedded P164 supports ECC memory, while the Intel Core 5 120UL does not.

Q: Which processor supports more PCIe lanes?

A: The AMD Ryzen AI Embedded P164 provides PCIe Gen 4 with 16 lanes from the CPU. The Intel Core 5 120UL provides PCIe Gen 4 with 8 lanes from the CPU.

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

A: The AMD Ryzen AI Embedded P164 has an average benchmark score of 52,901. The Intel Core 5 120UL has an average benchmark score of 13,594.

Head-to-Head Benchmarks

The head-to-head data records 11 benchmark comparisons, and the AMD Ryzen AI Embedded P164 wins all of them. The largest margin is in extended instructions, where the AMD part scores 24,193 and the Intel part scores 5,203, a 365% delta. This category measures the throughput of advanced instruction sets, and the Zen 5 / Zen 5c architecture demonstrates a decisive advantage over Raptor Lake in this area.

Data compression shows the second-largest gap. The AMD processor scores 327,891 against 109,090 for the Intel processor, a 200.6% delta. This workload benefits from the AMD part's higher boost clock of 5.00 GHz and its 16 threads. Random string sorting follows with a 155.7% delta, as the AMD part scores 34,801 and the Intel part scores 13,610.

Multi-threaded performance, measured by the PassMark multithread test, gives the AMD processor a 145.2% lead with a score of 25,889 versus 10,558. Integer math shows a 131.1% delta, with the AMD part scoring 87,940 and the Intel part scoring 38,060. Floating-point math also favors the AMD processor, which scores 55,799 against 26,311, a 112.1% delta.

Data encryption shows a 108.9% delta, with the AMD part scoring 16,055 and the Intel part scoring 7,685. Single-thread performance, recorded in both the passmark_single_thread and passmark_singlethread tests, gives the AMD part a 93.7% advantage at 4,029 versus 2,080. Prime number finding shows a 51.1% delta, with the AMD part scoring 71 and the Intel part scoring 47. Physics simulation shows the smallest margin, a 49.9% delta, with the AMD part scoring 1,210 and the Intel part scoring 807.

The AMD processor's average benchmark score of 52,901 places it within 0.1% of the AMD Ryzen 5 9500F and within 0.1% of the Intel Xeon 634. The Intel Core 5 120UL's average score of 13,594 places it within 0.7% of the Intel Core i3-12100F and within 1.1% of the Intel Core i5-9500. These nearest-rival comparisons confirm that the two processors operate in separate performance brackets, with the AMD part competing against high-core-count server and desktop chips and the Intel part competing against entry-level desktop processors.

Specification Differences

The AMD Ryzen AI Embedded P164 and Intel Core 5 120UL differ across nearly every recorded specification. The AMD part uses 8 cores and 16 threads, while the Intel part uses 10 cores and 12 threads. Base clocks are 2.00 GHz for the AMD part and 1.30 GHz for the Intel part. Boost clocks are 5.00 GHz for the AMD part and 4.60 GHz for the Intel part. The AMD processor has a 28 W TDP, while the Intel processor has a 15 W TDP.

Sockets differ completely: the AMD part uses AMD Socket FP8, and the Intel part uses Intel Socket 1700. The AMD processor uses the Gorgon Point codename with a Zen 5 / Zen 5c generation, while the Intel processor uses the Raptor Lake-PS codename with the Raptor Lake architecture. Process nodes are 4 nm at TSMC for the AMD part and 10 nm at Intel for the Intel part. The AMD die size is 233 mm², while the Intel die size is not recorded in the database.

Cache configurations differ in L2 and L3. The AMD part has 1 MB of L2 per core and 8 MB of L3. The Intel part has 1.25 MB of L2 per core and 12 MB of shared L3. Both use 80 KB of L1 per core. Memory support differs: the AMD part supports DDR5 and LPDDR5X with dual-channel access and 89.6 GB/s of bandwidth, while the Intel part supports DDR4 and DDR5 with dual-channel access and no recorded bandwidth figure. ECC memory is supported only on the AMD part. PCIe lane counts differ, with the AMD part offering 16 lanes of Gen 4 and the Intel part offering 8 lanes of Gen 4. Integrated graphics are the Radeon 880M on the AMD part and Iris Xe Graphics 80EU on the Intel part. The AMD processor is classified as mobile, and the Intel processor is classified as desktop. The AMD part has a release date in 2026, while the Intel part has a release date in 2024. Neither processor has an unlocked multiplier.