From WikiChip
Difference between revisions of "ibm/microarchitectures/power9"
< ibm

(Die Shot)
Line 52: Line 52:
  
 
| succession      = Yes
 
| succession      = Yes
| predecessor      = POWER8
+
| predecessor      = POWER8+
| predecessor link = ibm/microarchitectures/power8
+
| predecessor link = ibm/microarchitectures/power8+
 
| successor        = POWER10
 
| successor        = POWER10
 
| successor link  = ibm/microarchitectures/power10
 
| successor link  = ibm/microarchitectures/power10
Line 126: Line 126:
  
 
== Architecture ==
 
== Architecture ==
=== Key changes from {{\\|POWER8}} ===
+
=== Key changes from {{\\|POWER8}}/{{\\|POWER8+|+}} ===
 
* [[14 nm process]] (from [[22 nm]])
 
* [[14 nm process]] (from [[22 nm]])
 
** 17-layer metal stack
 
** 17-layer metal stack

Revision as of 10:49, 18 May 2017

Edit Values
POWER9 µarch
General Info
Arch TypeCPU
DesignerIBM
ManufacturerGlobalFoundries
IntroductionAugust, 2017
Phase-outAugust, 2018
Process14 nm
Core Configs24
Pipeline
TypeSuperscalar
SpeculativeYes
Reg RenamingYes
Stages12-16
Instructions
ISAPower ISA v3.0
Cache
L1I Cache32 KiB/core
L1D Cache32 KiB/core
L2 Cache512 KiB/core
L3 Cache120 MiB/chip
Succession

POWER9 is IBM's successor to POWER8, a 14 nm microarchitecture for Power-based server microprocessors that is set to be introduced in the 2nd half of 2017. POWER9-based processors are branded under the POWER9 family.

Process Technology

POWER9 is set to be fabricated on GlobalFoundries' 14 nm FinFET process, the same process that's used by AMD for their Zen microarchitecture.

Compatibility

Initial support for POWER9 started with Linux Kernel 4.8.

Vendor OS Version Notes
IBM AIX 7.? Support
IBM i  ? Support
Linux Linux Kernel 4.8 Initial Support
Wind River VxWorks VxWorks 7.? Support

Compiler support

Compiler CPU Arch-Favorable
GCC -mcpu=pwr9 -mtune=pwr9
LLVM -mcpu=pwr9 -mtune=pwr9
XL C/C++ -mcpu=pwr9 -mtune=pwr9

Variations

IBM offers POWER9 in two flavors: Scale-Out (SO) and Scale-Up (SU). The Scale-Out variations are design for traditional datacenter clusters utilizing single- and -dual sockets setups. The Scale-Up variations are designed for NUMA servers with four sockets and up, supporting large memory and throughput.

For the Scale-Out there are two variations, a 12-core SMT8 model and a 24-core SMT4 model. The SMT4 is optimized for Linux Ecosystem whereas the SMT8 is said to be optimized for the PowerVM Ecosystem community (AIX / IBM i customers). Those models support up to 8 channels of DDR4 memory for up to 4 TiB of DDR4-2667 memory (per socket). Those models offer up to 120 GiB/s of sustained bandwidth.

Linux Ecosystem PowerVM Ecosystem
24-core / 96 Threads 12-core / 96 Threads
Scale-Out (SO) p9sosmt4.png p9sosmt8.png
p9somem.png

For the Scale-Up there are two variations, a 12-core SMT8 model and a 24-core SMT4 model. The SMT4 is optimized for Linux Ecosystem whereas the SMT8 is said to be optimized for the PowerVM Ecosystem community (AIX / IBM i customers). Those models continue to support IBM's agnostic memory interface powered by IBM's POWER memory buffer products enabling up to 8 TiB per socket and up to 230 GiB/s of sustained bandwidth.

Linux Ecosystem PowerVM Ecosystem
24-core / 96 Threads 12-core / 96 Threads
Scale-Up (SU) p9susmt4.png p9susmt8.png
p9sumem.png

Performance Claims

IBM claims a range of performance improvements for a wide array of workloads. The graph below (provided by IBM) compares POWER9 performance using POWER8 as a baseline. The graph represents a scale-out model of similar specs at a constant frequency.

p9performance.png

Architecture

Key changes from POWER8/+

  • 14 nm process (from 22 nm)
    • 17-layer metal stack
    • 8,000,000,000 transistors
  • Support for Power ISA v3.0
  • Higher single-thread performance
  • New highly modular architecture
  • Pipeline
    • Shorter pipeline
      • 5 stages eliminated from fetch to compute vs POWER8
      • Roughly 5 stages were also eliminated for fixed-point operations
      • Up to 8 cycles were eliminated for floating-point operations
    • Instruction grouping at dispatch has been removed
    • Improved hazard avoidance / reduced hazard disruption
  • Improved branch prediction
  • Cache
    • 120 MiB NUCA L3
      • eDRAM
      • 7 TB/s on-chip bandwidth
  • Hardware Acceleration
  • I/O Subsystem
    • PCIe Gen4
    • Local SMP - 16 GT/s per lane interface
    • Remote SMP - 25 GT/s per lane interface
      • 48-96 lanes capability
      • IBM's SMP connect for their scale-up systems
      • Also available for the accelerators
  • Virtualization
    • QoS assistance
    • New Interrupt architecture
    • Workload-optimized frequency
    • Hardware enforced trusted execution

Block Diagram

New text document.svg This section is empty; you can help add the missing info by editing this page.

Memory Hierarchy

  • Cache
    • L1I Cache
      • 32 KiB, 8-way set associative
      • Per SMT4 Core
    • LID Cache
      • 32 KiB, 8-way set associative
      • Per SMT4 Core
    • L2 Cache
      • 258 KiB per SMT4 core
    • L3 Cache
      • 120 MiB eDRAM
      • 12 chunks (regions) of 10 MiB 20-way set associative
      • 7 TB/s on-chip bandwidth

Execution Slice Microarchitecture

Execution Slice Microarchitecture is POWER9's entirely new refactored core modular design. The same modules were used to build both the SMT4 and SMT8 cores (and in theory scale further to higher thread count although that's not going to happen in this iteration). These modules allow IBM to address the various processor models with support for the different configurations such as bandwidth/lines (from 128 to 64 byte sectors).

A Slice is the basic 64-bit computing block incorporating a single Vector and Scalar Unit (VSU) coupled with Load/Store Unit (LSU). VSU has a heterogeneous mix of computing capabilities including integer and floating point supporting scalar and vector operations. IBM claims this setup allows for higher utilization of resources while providing efficient exchanges of data between the individual slices. Two slices coupled together make up the Super-Slice, a 128-bit POWER9 physical design building block. Two super-slices together along with an Instruction Fetch Unit (IFU) and an Instruction Sequencing Unit (ISU) form a single POWER9 SMT4 core. The SMT8 variant is effectively two SMT4 units.

POWER8 P9 SMT8 (4x Super-Slice) P9 SMT4 (2x Super-Slice) Super-Slice Slice
p8smt8comp.png p94xsuper-slice.png p92xsuper-slice.png p9super-slice.png p9slice.png

Acceleration Platform (POWERAccel)

p9links.png

POWERAccel is the term collective name for all the interfaces and acceleration protocols provided by the POWER microarchitecture. POWER9 offers two sets of acceleration attachments: PCIe Gen4 which offers 48 lanes at 192 GiB/s duplex bandwidth and a new 25G link which offers an additional 48 lanes delivering up to 300 GiB/s of duplex bandwidth. On top of the two physical interfaces are a set of open standard protocols that integrated onto those signaling interfaces. The four prominent standards are:

  • CAPI 2.0 - POWER9 introduces CAPI 2.0 over PCIe which quadruples the bandwidth offered by the original CAPI protocol offered in POWER8.
  • New CAPI - A new interface that runs on top of the POWER9 25G link (300 GiB/s) interface, designed for CPU-Accelerators applications
  • NVLink 2.0 - High bandwidth and integration between the GPU and CPU.
  • On-Chip Acceleration - An array of accelerators offered by the POWER9 architecture itself

Pipeline

POWER9 modular design allowed IBM to reduce fetch-to-compute latency by 5 cycles. Similar number of cycles were also cut from fixed-point operations from fetch to retire. Additional 8 cycles were cut from fetch-to-retire for floating point instructions. POWER9 furthered increased fusion and reduced the number of instructions cracked (POWER handles complex instructions by 'cracking' them into two or three simple µOPs). Instruction grouping at dispatch that was done in POWER8 has also been entirely removed from POWER9.

B0 B1 RES
IF IC D1 D2 Crack/Fuse PD0 PD1 XFER MAP VS0 VS1 F2 F3 F4 F5
LS0 LS1 AGEN BRD CA FMT CA

SMT4 core

p9smt4core.png


Fetch/Branch Slices issue VSU & AGEN VSU Pipe LSU Slices
  • 32 KiB L1I$
  • 8 fetch, 6 decode
  • 1x branch execution
  • 4x scalar-64b / 2x vector-128b
  • 4x load/store AGEN
  • 4x ALU
  • 4x FP + FX-MUL + Complex (64b)
  • 2x Permute (128b)
  • 2x Quad Fixed (128b)
  • 2x Fixed Divide (64b)
  • 1x Quad FP & Decimal FP
  • 1x Cryptography
  • 32 KiB L1D$
  • Up to 4 DW Load or Store

Die

Tetracosa-Core

800px


800px

References

  • Brian Thompto, IBM, Senior Technical Staff Member for IBM POWER Systems, Hot Chips 28

See also

codenamePOWER9 +
core count24 +
designerIBM +
first launchedAugust 2017 +
full page nameibm/microarchitectures/power9 +
instance ofmicroarchitecture +
instruction set architecturePower ISA v3.0 +
manufacturerGlobalFoundries +
microarchitecture typeCPU +
namePOWER9 +
phase-outAugust 2018 +
pipeline stages (max)16 +
pipeline stages (min)12 +
process14 nm (0.014 μm, 1.4e-5 mm) +