AMD Ryzen AI Embedded P164 vs Intel Core Ultra 5 235T Comparison

AMD
AMD

AMD Ryzen AI Embedded P164

CORE STATE Gorgon Point
CORE SPECS 8 Cores / 16 Threads
CLOCK SPEED 2 Base / 5 GHz Turbo
CACHE 8 MB
MAX TDP 28W
ARCHITECTURE Gorgon Point
nm
PROCESS 4 nm
LAUNCH DATE 2026
VS
Intel
INTEL

Core Ultra 5 235T

CORE STATE Arrow Lake-S
CORE SPECS 14 Cores / 14 Threads
CLOCK SPEED 2.2 Base / 5 GHz Turbo
CACHE 24 MB (shared)
MAX TDP 65W
ARCHITECTURE Arrow Lake
nm
PROCESS 3 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

passmark_data_compression
327,891
295,100
passmark_data_encryption
16,055
23,457
passmark_extended_instructions
24,193
23,212
passmark_find_prime_numbers
71
318
passmark_floating_point_math
55,799
106,546
passmark_integer_math
87,940
84,244
passmark_multithread
25,889
30,918
passmark_physics
1,210
2,157
passmark_random_string_sorting
34,801
35,377
passmark_single_thread
4,029
4,339
passmark_singlethread
4,029
4,339
cinebench_cinebench_r15_multicore
N/A
2,644
cinebench_cinebench_r15_singlecore
N/A
373
cinebench_cinebench_r20_multicore
N/A
11,017
cinebench_cinebench_r20_singlecore
N/A
1,555
cinebench_cinebench_r23_multicore
N/A
26,232
cinebench_cinebench_r23_singlecore
N/A
3,703

Analysis: AMD Ryzen AI Embedded P164 vs Intel Core Ultra 5 235T

Where Each One Wins

The benchmark split between these two processors is clear: the AMD Ryzen AI Embedded P164 wins in three specific workloads, while the Intel Core Ultra 5 235T takes eight. The AMD part dominates data compression, extended instruction processing, and integer math. Its data compression score of 327891 beats the Intel chip's 295100, an 11.1% advantage. In extended instructions, the AMD processor scores 24193 versus 23212, a 4.2% edge. Integer math also favors AMD, with 87940 against 84244, a 4.4% lead.

The Intel Core Ultra 5 235T wins the remaining categories, often by substantial margins. The largest gap appears in the prime number search test, where Intel scores 318 against AMD's 71, a 77.7% advantage. Floating point math also heavily favors Intel, with 106546 versus 55799, a 47.6% difference. Physics simulation shows Intel ahead by 43.9%, scoring 2157 versus 1210. The multithread benchmark gives Intel 30918 against 25889, a 16.3% lead. Data encryption goes to Intel at 23457 versus 16055, a 31.6% margin. Single-thread performance favors Intel by 7.1%, with scores of 4339 versus 4029. Random string sorting is close, with Intel ahead just 1.6%, 35377 to 34801.

For users who prioritize compression work, encryption-heavy tasks, or integer-heavy code, the AMD part delivers. For everything else, particularly floating point math, physics simulation, and prime number calculations, the Intel processor is the stronger choice. The overall benchmark average tells a similar story: AMD's average score of 52901 places it at the 91st percentile among all CPUs, while Intel's 38561 average sits at the 86th percentile. The AMD chip's nearest rivals include the AMD Ryzen 5 9500F (0.1% behind), Intel Xeon 634 (0.1% ahead), AMD EPYC 7313P (0.6% ahead), and AMD Ryzen 9 7900X (0.7% ahead). The Intel chip's nearest rivals are the Intel Core i5-14500 (0.1% behind), Intel Xeon w3-2525 (0.4% ahead), Intel Core 9 270H (0.6% ahead), and Intel Core Ultra 9 285H (0.7% ahead).

Architecture Differences

The two processors come from different design philosophies. The AMD Ryzen AI Embedded P164 uses the Gorgon Point codename with a Ryzen AI Embedded generation combining Zen 5 and Zen 5c cores. It is built on a 4 nm process at TSMC with a die size of 233 mm². The Intel Core Ultra 5 235T belongs to the Core Ultra Series 2, uses the Arrow Lake-S codename, and is built on a 3 nm process, also at TSMC, with a die size of 243 mm² and 17,800 million transistors.

Core counts differ significantly. The AMD processor has 8 cores and 16 threads, while the Intel chip has 14 cores and 14 threads. This means Intel has more physical cores but no hyperthreading, while AMD relies on simultaneous multithreading to reach 16 threads from 8 cores. The cache hierarchy also diverges. AMD provides 80 KB of L1 per core, 1 MB of L2 per core, and 8 MB of L3. Intel offers 192 KB of L1 per core, 3 MB of L2 per core, and 24 MB of shared L3.

Memory support differs. The AMD chip supports both DDR5 and LPDDR5X over a dual-channel bus with 89.6 GB/s bandwidth. The Intel processor supports DDR5 only, also dual-channel, with 102.4 GB/s bandwidth. ECC memory is supported by AMD but not by Intel. PCIe connectivity favors Intel with Gen 5 and 20 lanes (CPU only), while AMD uses Gen 4 with 16 lanes (CPU only).

The integrated graphics also differ. AMD pairs the CPU with Radeon 880M graphics, while Intel uses Arc Xe-LPG Graphics with 24 execution units. The AMD part targets the mobile market segment and uses AMD Socket FP8. The Intel part targets desktop systems and uses Intel Socket 1851. Both processors are active in production, with AMD released on March 8, 2026, and Intel released on January 6, 2025. Neither has an unlocked multiplier. The Intel part has a listed part number of SRQES, while the AMD part number is unknown.

FAQ

Q: Which processor has more cores?

A: The Intel Core Ultra 5 235T has 14 cores compared to the AMD Ryzen AI Embedded P164's 8 cores. However, the AMD chip has 16 threads versus Intel's 14 threads, due to simultaneous multithreading.

Q: What are the boost clock speeds?

A: Both processors boost to 5.00 GHz. The AMD chip has a base clock of 2.00 GHz, while the Intel chip has a base clock of 2.20 GHz.

Q: Which processor has more L3 cache?

A: The Intel Core Ultra 5 235T has 24 MB of shared L3 cache, while the AMD Ryzen AI Embedded P164 has 8 MB of L3 cache.

Q: Do both processors support ECC memory?

A: No. The AMD Ryzen AI Embedded P164 supports ECC memory. The Intel Core Ultra 5 235T does not support ECC memory.

Q: Which processor has a higher average benchmark score?

A: The AMD Ryzen AI Embedded P164 has an average benchmark score of 52901, placing it at the 91st percentile. The Intel Core Ultra 5 235T has an average score of 38561, at the 86th percentile.

Q: What PCIe generations do the two processors use?

A: The AMD processor uses PCIe Gen 4 with 16 lanes (CPU only). The Intel processor uses PCIe Gen 5 with 20 lanes (CPU only).

Specification Differences

The two processors differ in nearly every major specification. Core count: AMD has 8 cores and 16 threads; Intel has 14 cores and 14 threads. Base clock: AMD runs at 2.00 GHz, Intel at 2.20 GHz. Boost clock is identical at 5.00 GHz. TDP: AMD is rated at 28 watts, Intel at 65 watts. Socket: AMD uses AMD Socket FP8, Intel uses Intel Socket 1851.

Process node: AMD is on 4 nm, Intel is on 3 nm. Die size: AMD measures 233 mm², Intel measures 243 mm². Transistor count is listed only for Intel at 17,800 million. Cache: AMD has 80 KB L1 per core, 1 MB L2 per core, and 8 MB L3. Intel has 192 KB L1 per core, 3 MB L2 per core, and 24 MB shared L3.

Memory support: AMD supports DDR5 and LPDDR5X, Intel supports DDR5 only. Memory bandwidth: AMD delivers 89.6 GB/s, Intel delivers 102.4 GB/s. ECC memory: AMD supports it, Intel does not. PCIe: AMD offers Gen 4 with 16 lanes, Intel offers Gen 5 with 20 lanes. Integrated graphics: AMD uses Radeon 880M, Intel uses Arc Xe-LPG Graphics 24EU.

Market segment: AMD is mobile, Intel is desktop. Release date: AMD launched March 8, 2026; Intel launched January 6, 2025. The Intel part has a launch MSRP of $247. The AMD part has no listed launch MSRP. The Intel part number is SRQES; the AMD part number is unknown.

Head-to-Head Benchmarks

The data compression test is the AMD chip's biggest win. It scores 327891 against Intel's 295100, an 11.1% margin. This is a meaningful lead for workloads that involve archiving, file compression, or database operations that rely on data packing. The extended instructions test also goes to AMD, with 24193 versus 23212, a 4.2% edge. This suggests AMD handles certain SIMD or specialized instruction paths more efficiently. Integer math gives AMD a 4.4% win, 87940 to 84244, indicating an advantage in general arithmetic-heavy code.

The Intel chip's wins are more numerous and often larger. The most dramatic gap is in the find prime numbers test, where Intel scores 318 versus AMD's 71, a 77.7% advantage. This test is highly sensitive to core count and single-thread efficiency, and Intel's 14 cores clearly dominate. Floating point math shows Intel at 106546 against 55799, a 47.6% lead. This is a major margin for scientific, engineering, or graphics-rendering workloads that rely heavily on FPU throughput.

Physics simulation gives Intel 2157 versus 1210, a 43.9% lead. This benchmark typically stresses both integer and floating point performance, and Intel's core advantage shows. Data encryption goes to Intel with 23457 against 16055, a 31.6% margin. Encryption workloads often benefit from dedicated instruction extensions and higher core counts. The multithread benchmark shows Intel ahead by 16.3%, with 30918 versus 25889. This is the broadest overall throughput test, and Intel's 14 physical cores outperform AMD's 8 cores with SMT.

Single-thread performance favors Intel by 7.1%, with scores of 4339 versus 4029 on both single-thread tests. Random string sorting is nearly tied, with Intel ahead 35377 to 34801, a 1.6% difference. The overall win count is 8 for Intel and 3 for AMD. The average benchmark scores reflect this: AMD's 52901 average is higher primarily because its winning categories include data compression, which has a very high raw score. Intel's 38561 average is lower, but its wins are spread across more categories and include several with very large margins.

The Verdict

The recorded data indicates two distinct usage profiles. The AMD Ryzen AI Embedded P164 is a mobile processor with a 28-watt TDP, ECC memory support, and a 91st percentile average benchmark score. Its strengths are data compression, extended instructions, and integer math. The Intel Core Ultra 5 235T is a desktop processor with a 65-watt TDP, no ECC support, and an 86th percentile average score. Its strengths are floating point math, physics simulation, prime number calculations, encryption, and single-thread performance.

For a compact mobile system or embedded application where power draw is critical, the AMD chip's 28-watt TDP and LPDDR5X memory support make it the practical choice. The ECC memory capability adds reliability for data-sensitive workloads. The AMD chip also holds a clear performance advantage in data compression, which matters for storage-heavy tasks.

For a desktop build where power consumption is less constrained, the Intel chip's 65-watt TDP and 14 physical cores deliver more raw throughput across a wider range of tests. Its 102.4 GB/s memory bandwidth exceeds the AMD chip's 89.6 GB/s. The PCIe Gen 5 interface with 20 lanes provides more modern connectivity options. The 24 MB of L3 cache is triple the AMD chip's allocation, which helps in cache-sensitive workloads.

The benchmark data shows that the Intel chip wins the majority of tests, but the AMD chip wins the tests where its architecture is strongest. The AMD chip's average score of 52901 is higher than Intel's 38561, yet the Intel chip has a higher multithread score (30918 versus 25889) and a much higher physics score (2157 versus 1210). These are not interchangeable processors. The AMD part is a specialized embedded chip with a specific feature set. The Intel part is a general-purpose desktop processor with broader core scaling.

Buyers should match the processor to the workload. Data compression and integer-heavy code favor AMD. Floating point, encryption, physics, and single-thread responsiveness favor Intel. The Intel chip's launch MSRP is $247, while the AMD chip has no listed launch MSRP. The choice comes down to whether the workload resembles AMD's three winning categories or Intel's eight.

DETAILED SPECIFICATIONS

SPECIFICATION
AI Embedded P164
Ultra 5 235T
Core Specs
Cores
8
14 +75.0%
Threads
16
14 -12.5%
Base Clock (GHz)
2
2.2 +10.0%
Boost Clock (GHz)
5
5 0.0%
Frequency (GHz)
2
2.2 +10.0%
Turbo Clock (GHz)
5
5 0.0%
Multiplier
20
22 +10.0%
SMP CPUs
1
1 0.0%
Cache
L1 Cache
80 KB (per core)
192 KB (per core)
L2 Cache
1 MB (per core)
3 MB (per core)
L3 Cache
8 MB
24 MB (shared)
Power
TDP (W)
28
65 +132.1%
PL1
—
35 W
PL2
—
114 W
Configurable TDP
15-54 W
—
Architecture
Architecture
—
Arrow Lake
Codename
Gorgon Point
Arrow Lake-S
Generation
Ryzen AI Embedded (Zen 5 / Zen 5c)
Ultra 5 (Arrow Lake)
Process Size
4 nm
3 nm
Transistors
—
17,800 million
Die Size
233 mm²
243 mm²
Foundry
TSMC
TSMC
Memory
Memory Support
DDR5, LPDDR5X
DDR5
Memory Bus
Dual-channel
Dual-channel
Memory Bandwidth
89.6 GB/s
102.4 GB/s
ECC Memory
Yes
No
Platform
Socket
AMD Socket FP8
Intel Socket 1851
Chipsets
—
Z890, B860, W880, Q870, H810
PCIe
Gen 4, 16 Lanes(CPU only)
Gen 5, 20 Lanes(CPU only)
Intel Hybrid
Hybrid Cores
3 + 5
P-Cores: 6 E-Cores: 8
E-Core Frequency
2000 MHz up to 3.3 GHz
1600 MHz up to 4.4 GHz
P-Core Turbo
—
4.8 GHz
AI/NPU
NPU
Yes / 50 TOPS
—
Graphics
Integrated Graphics
Radeon 880M
Arc Xe-LPG Graphics 24EU
Other
Market
Mobile
Desktop
Production Status
Active
Active
Launch Price
—
$247
Part Number
unknown
SRQES
Package
FP8
FC-LGA18W
Tj Max
105°C
105°C
View Ryzen AI Embedded P164 Details View Core Ultra 5 235T Details