From WikiChip
Ice Lake (server) - Microarchitectures - Intel
| Edit Values | |
| Ice Lake (server) µarch | |
| General Info | |
| Arch Type | CPU |
| Designer | Intel |
| Manufacturer | Intel |
| Introduction | 2020 |
| Process | 10 nm |
| Instructions | |
| ISA | x86-64 |
| Cores | |
| Core Names | Ice Lake SP, Ice Lake X |
| Succession | |
| Contemporary | |
| Ice Lake (client) | |
Ice Lake (ICL) Server Configuration is Intel's successor to Cascade Lake, a 10 nm microarchitecture for enthusiasts and servers.
Contents
Codenames
| Core | Abbrev | Target |
|---|---|---|
| Ice Lake X | ICL-X | High-end desktops & enthusiasts market |
| Ice Lake W | ICL-W | Enterprise/Business workstations |
| Ice Lake SP | ICL-SP | Server Scalable Processors |
Process Technology
- See also: Ice Lake (client) § Process Technology
Ice Lake will use a second-generation enhanced 10 nm process called "10 nm+". Versus the first generation 10nm which was used for Cannon Lake, 10nm+ will feature higher performance through higher drive current for the same power envelope.
Compiler support
Support for Ice Lake was added in LLVM Clang 6.0 and GCC 8.0.
| Compiler | Arch-Specific | Arch-Favorable |
|---|---|---|
| ICC | -march=icelake |
-mtune=icelake
|
| GCC | -march=icelake |
-mtune=icelake
|
| LLVM | -march=icelake |
-mtune=icelake
|
| Visual Studio | /? |
/tune:?
|
CPUID
| Core | Extended Family |
Family | Extended Model |
Model |
|---|---|---|---|---|
| ? | 0 | 0x6 | 0x? | ? |
| Family 6 Model ? | ||||
| ? | 0 | 0x6 | ? | ? |
| Family 6 Model ? | ||||
Architecture
Key changes from Cascade Lake
- Enhanced "10nm+" (from 14 nm)
- Sunny Cove core
- See Sunny Cove for microarchitectural details and changes
- I/O
- PCIe 4.0 (from PCIe 3.0)
- Memory
- Higher bandwidth (190.7 GiB/s, up from 143.1 GiB/s)
- Octa-channel (up from hexa-channel)
- 3200 MT/s (up from 2933 MT/s)
- Platform
- Packaging
- 4189-contact flip-chip LGA (up from 3647 contacts)
This list is incomplete; you can help by expanding it.
New instructions
Ice Lake introduced a number of new instructions:
-
CLWB- Force cache line write-back without flush -
RDPID- Read Processor ID - Additional AVX-512 extensions:
-
AVX512VPOPCNTDQ- AVX-512 Vector Population Count Doubleword and Quadword -
AVX512VNNI- AVX-512 Vector Neural Network Instructions -
AVX512GFNI- AVX-512 Galois Field New Instructions -
AVX512VAES- AVX-512 Vector AES -
AVX512VBMI2- AVX-512 Vector Bit Manipulation, Version 2 -
AVX512BITALG- AVX-512 Bit Algorithms -
AVX512VPCLMULQDQ- AVX-512 Vector Vector Carry-less Multiply
-
-
TME- Total Memory Encryption -
ENCLV- SGX oversubscription instructions - Fast Short REP MOV
- Split Lock Detection
All Ice Lake Chips
| List of Ice Lake Processors | |||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Main processor | Frequency/Turbo | Mem | Major Feature Diff | ||||||||||||||||||||||
| Model | Launched | Price | Family | Core Name | Cores | Threads | L2$ | L3$ | TDP | Frequency | Max Turbo | Max Mem | Turbo | SMT | |||||||||||
| Uniprocessors | |||||||||||||||||||||||||
| Multiprocessors (2-way) | |||||||||||||||||||||||||
| Multiprocessors (4-way) | |||||||||||||||||||||||||
| Multiprocessors (8-way) | |||||||||||||||||||||||||
| Count: 0 | |||||||||||||||||||||||||
Facts about "Ice Lake (server) - Microarchitectures - Intel"
| codename | Ice Lake (server) + |
| designer | Intel + |
| first launched | 2020 + |
| full page name | intel/microarchitectures/ice lake (server) + |
| instance of | microarchitecture + |
| instruction set architecture | x86-64 + |
| manufacturer | Intel + |
| microarchitecture type | CPU + |
| name | Ice Lake (server) + |
| process | 10 nm (0.01 μm, 1.0e-5 mm) + |