From WikiChip
Difference between revisions of "intel/microarchitectures/tremont"
(One-word typo fix. (Accross to across)) |
|||
(41 intermediate revisions by 13 users not shown) | |||
Line 1: | Line 1: | ||
− | {{intel title|Tremont|l=arch}} | + | {{intel title|Tremont|arch}} |
− | {{ | + | {{microarchitecture |
+ | |atype=CPU | ||
+ | |name=Tremont | ||
+ | |designer=Intel | ||
+ | |manufacturer=Intel | ||
+ | |introduction=2019 | ||
+ | |process=10 nm | ||
+ | |type=Superscalar | ||
+ | |oooe=Yes | ||
+ | |speculative=Yes | ||
+ | |renaming=Yes | ||
+ | |isa=x86-64 | ||
+ | |extension=MOVBE | ||
+ | |extension 2=MMX | ||
+ | |extension 3=SSE | ||
+ | |extension 4=SSE2 | ||
+ | |extension 5=SSE3 | ||
+ | |extension 6=SSSE3 | ||
+ | |extension 7=SSE4.1 | ||
+ | |extension 8=SSE4.2 | ||
+ | |extension 9=POPCNT | ||
+ | |extension 10=AES | ||
+ | |extension 11=PCLMUL | ||
+ | |extension 12=RDRND | ||
+ | |extension 13=XSAVE | ||
+ | |extension 14=XSAVEOPT | ||
+ | |extension 15=FSGSBASE | ||
+ | |extension 16=PTWRITE | ||
+ | |extension 17=RDPID | ||
+ | |extension 18=SGX | ||
+ | |extension 19=UMIP | ||
+ | |extension 20=GFNI-SSE | ||
+ | |extension 21=CLWB | ||
+ | |extension 22=ENCLV | ||
+ | |extension 23=SHA | ||
+ | |core name=Elkhart Lake | ||
+ | |core name 2=Jasper Lake | ||
+ | |core name 3=Skyhawk Lake | ||
+ | |core name 4=Lakefield | ||
+ | |core name 5=Snow Ridge | ||
+ | |predecessor=Goldmont Plus | ||
+ | |predecessor link=intel/microarchitectures/goldmont plus | ||
+ | |successor=Gracemont | ||
+ | |successor link=intel/microarchitectures/gracemont | ||
+ | }} | ||
+ | '''Tremont''' is [[Intel]]'s successor to {{\\|Goldmont Plus}}, a [[10 nm]] microarchitecture for ultra-low power devices and microservers. | ||
+ | |||
+ | == Codenames == | ||
+ | {| class="wikitable" | ||
+ | ! Platform !! Core Name || PCH | ||
+ | |- | ||
+ | | || {{intel|Skyhawk Lake|l=core}} || | ||
+ | |- | ||
+ | | Jacobsville || {{intel|Elkhart Lake|l=core}} || {{intel|Mule Creek Canyon|l=chipset}} | ||
+ | |- | ||
+ | | || {{intel|Jasper Lake|l=core}} || | ||
+ | |- | ||
+ | | || {{intel|Lakefield|l=core}} || | ||
+ | |- | ||
+ | | || {{intel|Snow Ridge |l=core}} || | ||
+ | |} | ||
+ | |||
+ | == Brands == | ||
+ | {{empty section}} | ||
+ | |||
+ | == Release Dates == | ||
+ | Tremont was released in a number of products in late 2019. | ||
+ | |||
+ | == Technology == | ||
+ | Tremont uses Intel's [[10 nm process]]. | ||
+ | |||
+ | == Compiler support == | ||
+ | {| class="wikitable" | ||
+ | |- | ||
+ | ! Compiler !! Arch-Specific || Arch-Favorable | ||
+ | |- | ||
+ | | [[ICC]] || <code>-march=tremont</code> || <code>-mtune=tremont</code> | ||
+ | |- | ||
+ | | [[GCC]] || <code>-march=tremont</code> || <code>-mtune=tremont</code> | ||
+ | |- | ||
+ | | [[LLVM]] || <code>-march=tremont</code> || <code>-mtune=tremont</code> | ||
+ | |- | ||
+ | | [[Visual Studio]] || <code>/arch:?</code> || <code>/tune:?</code> | ||
+ | |} | ||
+ | |||
+ | === CPUID === | ||
+ | {| class="wikitable tc1 tc2 tc3 tc4" | ||
+ | ! Core !! Extended<br>Family !! Family !! Extended<br>Model !! Model | ||
+ | |- | ||
+ | | rowspan="2" | ? || 0 || 0x6 || 0x8 || 0x6 | ||
+ | |- | ||
+ | | colspan="4" | Family 6 Model 134 | ||
+ | |} | ||
+ | |||
+ | == Architecture == | ||
+ | Tremont is designed with significant single-thread performance in mind while focusing on low-power small silicon area cores. | ||
+ | === Key changes from {{\\|Goldmont Plus}} === | ||
+ | * Significant [[IPC]] uplift ([[Intel]] self-reported average 32% IPC across proxy benchmarks such as [[SPEC CPU2006]]/[[SPEC CPU2017]]) | ||
+ | * Front-end | ||
+ | ** Redesigned front-end | ||
+ | *** New dual symmetric decode cluster | ||
+ | **** Out-of-order decode | ||
+ | **** 6-wide decode | ||
+ | ***** 3-way decode per cluster | ||
+ | ** Smarter [[prefetchers]] | ||
+ | ** Improved [[branch predictor]] | ||
+ | *** Big-core level of performance | ||
+ | * Back-end | ||
+ | ** larger ROB | ||
+ | ** wide issue (10-wide) | ||
+ | * Execution Engine | ||
+ | ** 2x store data ports (up from 1) | ||
+ | |||
+ | |||
+ | ====New instructions ==== | ||
+ | Tremont introduced a number of {{x86|extensions|new instructions}}: | ||
+ | |||
+ | * {{x86|CLWB|<code>CLWB</code>}} - Force cache line write-back without flush | ||
+ | * {{x86|ENCLV|<code>ENCLV</code>}} - SGX oversubscription instructions | ||
+ | * {{x86|CLDEMOTE|<code>CLDEMOTE</code>}} - Cache line demote instruction | ||
+ | * {{x86|SSE_GFNI|<code>SSE_GFNI</code>}} - SSE-based Galois Field New Instructions | ||
+ | * Direct store instructions: MOVDIRI, MOVDIR64B | ||
+ | * User wait instructions: TPAUSE, UMONITOR, UMWAIT | ||
+ | * Split Lock Detection - detection and cause an exception for split locks | ||
+ | |||
+ | === Block Diagram === | ||
+ | ==== Individual Core ==== | ||
+ | :[[File:tremont block diagram.svg|850px]] |
Latest revision as of 19:12, 10 December 2020
Edit Values | |
Tremont µarch | |
General Info | |
Arch Type | CPU |
Designer | Intel |
Manufacturer | Intel |
Introduction | 2019 |
Process | 10 nm |
Pipeline | |
Type | Superscalar |
OoOE | Yes |
Speculative | Yes |
Reg Renaming | Yes |
Instructions | |
ISA | x86-64 |
Extensions | MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, POPCNT, AES, PCLMUL, RDRND, XSAVE, XSAVEOPT, FSGSBASE, PTWRITE, RDPID, SGX, UMIP, GFNI-SSE, CLWB, ENCLV, SHA |
Cores | |
Core Names | Elkhart Lake, Jasper Lake, Skyhawk Lake, Lakefield, Snow Ridge |
Succession | |
Tremont is Intel's successor to Goldmont Plus, a 10 nm microarchitecture for ultra-low power devices and microservers.
Contents
Codenames[edit]
Platform | Core Name | PCH |
---|---|---|
Skyhawk Lake | ||
Jacobsville | Elkhart Lake | Mule Creek Canyon |
Jasper Lake | ||
Lakefield | ||
Snow Ridge |
Brands[edit]
![]() |
This section is empty; you can help add the missing info by editing this page. |
Release Dates[edit]
Tremont was released in a number of products in late 2019.
Technology[edit]
Tremont uses Intel's 10 nm process.
Compiler support[edit]
Compiler | Arch-Specific | Arch-Favorable |
---|---|---|
ICC | -march=tremont |
-mtune=tremont
|
GCC | -march=tremont |
-mtune=tremont
|
LLVM | -march=tremont |
-mtune=tremont
|
Visual Studio | /arch:? |
/tune:?
|
CPUID[edit]
Core | Extended Family |
Family | Extended Model |
Model |
---|---|---|---|---|
? | 0 | 0x6 | 0x8 | 0x6 |
Family 6 Model 134 |
Architecture[edit]
Tremont is designed with significant single-thread performance in mind while focusing on low-power small silicon area cores.
Key changes from Goldmont Plus[edit]
- Significant IPC uplift (Intel self-reported average 32% IPC across proxy benchmarks such as SPEC CPU2006/SPEC CPU2017)
- Front-end
- Redesigned front-end
- New dual symmetric decode cluster
- Out-of-order decode
- 6-wide decode
- 3-way decode per cluster
- New dual symmetric decode cluster
- Smarter prefetchers
- Improved branch predictor
- Big-core level of performance
- Redesigned front-end
- Back-end
- larger ROB
- wide issue (10-wide)
- Execution Engine
- 2x store data ports (up from 1)
New instructions[edit]
Tremont introduced a number of new instructions:
-
CLWB
- Force cache line write-back without flush -
ENCLV
- SGX oversubscription instructions -
CLDEMOTE
- Cache line demote instruction -
SSE_GFNI
- SSE-based Galois Field New Instructions - Direct store instructions: MOVDIRI, MOVDIR64B
- User wait instructions: TPAUSE, UMONITOR, UMWAIT
- Split Lock Detection - detection and cause an exception for split locks
Block Diagram[edit]
Individual Core[edit]
Facts about "Tremont - Microarchitectures - Intel"
codename | Tremont + |
designer | Intel + |
first launched | 2019 + |
full page name | intel/microarchitectures/tremont + |
instance of | microarchitecture + |
instruction set architecture | x86-64 + |
manufacturer | Intel + |
microarchitecture type | CPU + |
name | Tremont + |
process | 10 nm (0.01 μm, 1.0e-5 mm) + |