AMD EPYC 7452 vs Intel Xeon Gold 6336Y Comparison

AMD
AMD

AMD EPYC 7452

CORE STATE Rome
CORE SPECS 32 Cores / 64 Threads
CLOCK SPEED 2.2 Base / 3.35 GHz Turbo
CACHE 128 MB (shared)
MAX TDP 155W
ARCHITECTURE Zen 2
nm
PROCESS 7 nm
LAUNCH DATE 2019
VS
Intel
INTEL

Xeon Gold 6336Y

CORE STATE Ice Lake-SP
CORE SPECS 24 Cores / 48 Threads
CLOCK SPEED 2.4 Base / 3.6 GHz Turbo
CACHE 36 MB (shared)
MAX TDP 185W
ARCHITECTURE Ice Lake
nm
PROCESS 10 nm
LAUNCH DATE 2021

PERFORMANCE BENCHMARKS

cinebench_cinebench_r15_multicore
3,930
3,899
cinebench_cinebench_r15_singlecore
554
550
cinebench_cinebench_r20_multicore
16,377
16,249
cinebench_cinebench_r20_singlecore
2,312
2,294
cinebench_cinebench_r23_multicore
38,993
38,689
cinebench_cinebench_r23_singlecore
5,505
5,462

Analysis: AMD EPYC 7452 vs Intel Xeon Gold 6336Y

FAQ

Q: Which CPU has more cores and threads?

A: The AMD EPYC 7452 has 32 cores and 64 threads, while the Intel Xeon Gold 6336Y has 24 cores and 48 threads. That is a 33% core advantage and a 33% thread advantage for the AMD part.

Q: Which CPU has a higher boost clock?

A: The Intel Xeon Gold 6336Y boosts to 3.60 GHz, while the AMD EPYC 7452 boosts to 3.35 GHz. Intel also has a higher base clock at 2.40 GHz versus 2.20 GHz.

Q: How do their average benchmark scores compare?

A: The AMD EPYC 7452 has an average benchmark score of 11279, while the Intel Xeon Gold 6336Y scores 11191. That puts AMD 0.8% ahead, and both CPUs sit at the 66th percentile among all CPUs.

Q: Which CPU has larger L3 cache?

A: The AMD EPYC 7452 has 128 MB of shared L3 cache, while the Intel Xeon Gold 6336Y has only 36 MB of shared L3 cache. That is a 3.5x difference in favor of AMD.

Q: Do both CPUs support the same memory configuration?

A: Yes. Both support DDR4 memory with an eight-channel memory bus and 204.8 GB/s of memory bandwidth. Both also support ECC memory.

Q: Which CPU was released later?

A: The Intel Xeon Gold 6336Y was released on April 5, 2021, while the AMD EPYC 7452 was released on August 6, 2019. Intel's part is roughly 20 months newer.

Architecture Differences

The AMD EPYC 7452 is built on TSMC's 7 nm process node with a transistor count of 3,800 million on a 74 mm² die. It uses the Zen 2 architecture under the codename Rome, belonging to the EPYC 7002 series. The Intel Xeon Gold 6336Y uses Intel's 10 nm process node with the Ice Lake architecture under the codename Ice Lake-SP. Intel's transistor count and die size are not listed in the data, but the process node difference is clear: 7 nm versus 10 nm.

Cache organization differs significantly. AMD allocates 96 KB of L1 cache per core and 512 KB of L2 cache per core, with a massive 128 MB shared L3 cache. Intel allocates 64 KB of L1 per core and 1 MB of L2 per core, but only 36 MB of shared L3. The L3 cache difference is the most striking architectural gap — AMD has 3.5x more shared L3, which is highly relevant for workloads with large working sets or heavy data sharing between cores.

Both CPUs use Socket SP3 (AMD) and Socket 4189 (Intel), respectively. Both support PCIe Gen 4, though Intel lists 64 lanes (CPU only), while AMD does not specify lane count in the data. Both are server/workstation parts with ECC memory support. Neither has integrated graphics, and neither has an unlocked multiplier.

Head-to-Head Benchmarks

The benchmark results are remarkably close across all six Cinebench tests, with AMD winning every single one by a narrow margin. In Cinebench R15 multicore, the AMD EPYC 7452 scores 3930 versus 3899 for the Intel Xeon Gold 6336Y, a 0.8% lead. The single-core R15 test shows AMD at 554 versus 550, a 0.7% lead.

Moving to Cinebench R20, AMD wins multicore with 16377 against 16249, again by 0.8%. Single-core R20 goes to AMD at 2312 versus 2294, another 0.8% margin. In Cinebench R23, the pattern holds: AMD scores 38993 in multicore versus 38689 for Intel (0.8% lead), and 5505 in single-core versus 5462 (0.8% lead).

The data shows AMD wins all six head-to-head benchmarks, but the margins are consistently under 1%. This is not a rout — it is a statistical tie in real-world terms, with AMD holding a razor-thin edge in every test. The largest delta is 0.8%, which appears in four of the six tests. The smallest is 0.7% in R15 single-core. For a 32-core part versus a 24-core part, the multicore results are surprisingly tight, suggesting Intel's higher clocks (3.60 GHz boost versus 3.35 GHz) compensate significantly for its 8-core deficit.

Specification Differences

| Specification | AMD EPYC 7452 | Intel Xeon Gold 6336Y |

|---|---|---|

| Cores | 32 | 24 |

| Threads | 64 | 48 |

| Base Clock | 2.20 GHz | 2.40 GHz |

| Boost Clock | 3.35 GHz | 3.60 GHz |

| TDP | 155 W | 185 W |

| Socket | AMD Socket SP3 | Intel Socket 4189 |

| Architecture | Zen 2 | Ice Lake |

| Codename | Rome | Ice Lake-SP |

| Process Node | 7 nm (TSMC) | 10 nm (Intel) |

| L1 Cache | 96 KB per core | 64 KB per core |

| L2 Cache | 512 KB per core | 1 MB per core |

| L3 Cache | 128 MB shared | 36 MB shared |

| PCIe | Gen 4 | Gen 4, 64 Lanes (CPU only) |

| Release Date | 2019-08-06 | 2021-04-05 |

| Part Number | 100-000000057 | Not listed |

The most consequential differences are cores (32 vs 24), TDP (155 W vs 185 W), and L3 cache (128 MB vs 36 MB). Intel has higher base and boost clocks, but AMD has more cores and a much larger L3 pool. The TDP difference is notable: AMD delivers more cores at a lower power envelope. Intel's newer release date does not translate into a performance advantage in the benchmark data.

The Verdict

The data points to a statistical dead heat with a slight AMD edge. The AMD EPYC 7452 wins all six head-to-head benchmarks, but by margins under 1% in every case. Both CPUs sit at the 66th percentile among all CPUs, and their average benchmark scores differ by only 0.8%.

For multi-core workloads, the AMD part's 32 cores and 128 MB L3 cache provide a structural advantage, yet the benchmark deltas are tiny — 0.8% in R23 multicore. This suggests that Intel's higher clock speeds (3.60 GHz boost versus 3.35 GHz) and newer architecture largely offset the core and cache disadvantage. The Intel part's 24 cores are enough to keep pace in threaded workloads.

For single-core performance, AMD also edges ahead, but again by less than 1%. The R23 single-core score of 5505 versus 5462 is effectively a tie. Neither CPU is a clear winner in raw performance.

The Intel Xeon Gold 6336Y has a higher TDP (185 W versus 155 W), which means it draws more power to achieve similar results. That makes the AMD part more efficient per watt on paper, though the benchmark data does not include power measurements.

The verdict leans toward the AMD EPYC 7452 for anyone who values the larger core count, bigger L3 cache, and lower TDP, especially in dense virtualization or memory-bandwidth-heavy workloads. The Intel part is competitive for those who prefer the newer platform or need its specific socket and PCIe lane configuration. But based purely on the benchmark scores, the AMD EPYC 7452 is the safer pick — it wins every test, even if narrowly.

Where Each One Wins

AMD EPYC 7452 wins on: All six Cinebench benchmarks (R15, R20, R23, both single and multi-core). The largest margin is 0.8% in four tests, with 0.7% in R15 single-core. It also wins on core count (32 vs 24), thread count (64 vs 48), L3 cache size (128 MB vs 36 MB), and lower TDP (155 W vs 185 W). The AMD part has a smaller process node (7 nm vs 10 nm) and more L1 cache per core (96 KB vs 64 KB).

Intel Xeon Gold 6336Y wins on: Higher base clock (2.40 GHz vs 2.20 GHz), higher boost clock (3.60 GHz vs 3.35 GHz), and larger L2 cache per core (1 MB vs 512 KB). It also has a newer release date (2021 vs 2019) and a lower average benchmark score disadvantage (0.8% behind AMD). Intel's socket 4189 and PCIe Gen 4 with 64 lanes (CPU only) are platform-specific advantages, though AMD also supports PCIe Gen 4.

In practical terms, the AMD EPYC 7452 is the better choice for compute-heavy workloads that scale with cores and benefit from a massive L3 cache. The Intel Xeon Gold 6336Y is competitive for workloads that favor higher clocks and faster per-core L2, but the benchmark data does not show a single test where Intel comes out ahead. The Intel part's higher TDP (185 W) means it consumes more power to deliver slightly lower scores across the board. For new server deployments, the AMD EPYC 7452 offers more cores, more cache, and better efficiency at a nearly identical performance level.

DETAILED SPECIFICATIONS

SPECIFICATION
EPYC 7452
Gold 6336Y
Core Specs
Cores
32
24 -25.0%
Threads
64
48 -25.0%
Base Clock (GHz)
2.2
2.4 +9.1%
Boost Clock (GHz)
3.35
3.6 +7.5%
Frequency (GHz)
2.2
2.4 +9.1%
Turbo Clock (GHz)
3.35
3.6 +7.5%
Multiplier
25
24 -4.0%
SMP CPUs
2
2 0.0%
Cache
L1 Cache
96 KB (per core)
64 KB (per core)
L2 Cache
512 KB (per core)
1 MB (per core)
L3 Cache
128 MB (shared)
36 MB (shared)
Power
TDP (W)
155
185 +19.4%
Architecture
Architecture
Zen 2
Ice Lake
Codename
Rome
Ice Lake-SP
Generation
EPYC (Zen 2 (Rome))
Xeon Gold (Ice Lake-SP)
Process Size
7 nm
10 nm
Transistors
3,800 million
—
Die Size
74 mm²
—
Foundry
TSMC
Intel
Memory
Memory Support
DDR4
DDR4
Memory Bus
Eight-channel
Eight-channel
Memory Bandwidth
204.8 GB/s
204.8 GB/s
ECC Memory
Yes
Yes
Platform
Socket
AMD Socket SP3
Intel Socket 4189
PCIe
Gen 4
Gen 4, 64 Lanes(CPU only)
Other
Market
Server/Workstation
Server/Workstation
Production Status
Active
Active
Part Number
100-000000057
—
Package
FCLGA-4094
FC-LGA4189
View EPYC 7452 Details View Xeon Gold 6336Y Details