[libreriscv.git] / openpower / sv / rfc / ls008.mdwn

# RFC ls008 SVP64 Management instructions

[[!tag opf_rfc]]

**URLs**:

* <https://libre-soc.org/openpower/sv/>
* <https://libre-soc.org/openpower/sv/rfc/ls008/>
* <https://bugs.libre-soc.org/show_bug.cgi?id=1040>
* <https://git.openpower.foundation/isa/PowerISA/issues/87>

**Severity**: Major

**Status**: New

**Date**: 24 Mar 2023

**Target**: v3.2B

**Source**: v3.0B

**Books and Section affected**:

```
    Book I, new Scalar Chapter.  (Or, new Book on "Zero-Overhead Loop Subsystem")
    Appendix E Power ISA sorted by opcode
    Appendix F Power ISA sorted by version
    Appendix G Power ISA sorted by Compliancy Subset
    Appendix H Power ISA sorted by mnemonic
```

**Summary**

```
    Instructions added
    setvl    - Cray-style "Set Vector Length" instruction
    svstep   - Vertical-First Mode explicit Step and Status
    svremap  - Re-Mapping of Register Element Offsets
    svindex  - General-purpose setting of SHAPEs to be re-mapped
    svshape  - Hardware-level setting of SHAPEs for element re-mapping
    svshape2 - Hardware-level setting of SHAPEs for element re-mapping (v2)
```

**Submitter**: Luke Leighton (Libre-SOC)

**Requester**: Libre-SOC

**Impact on processor**:

```
    Addition of six new "Zero-Overhead-Loop-Control" DSP-style Vector-style
    Management Instructions which can be implemented extremely efficiently
    and effectively by inserting an additional phase between Decode and Issue.
    More complex designs are NOT adversely impacted and in fact greatly benefit
    whilst still retaining an obvious linear sequential execution programming model.
```

**Impact on software**:

```
    Requires support for new instructions in assembler, debuggers,
    and related tools.
```

**Keywords**:

```
    Cray Supercomputing, Vectorisation, Zero-Overhead-Loop-Control,
    Scalable Vectors, Multi-Issue Out-of-Order, Sequential Programming Model
```

**Motivation**

TODO

**Notes and Observations**:

1. TODO

**Changes**

Add the following entries to:

* Section 1.3.2 Notation
* the Appendices of Book I
* Instructions of Book I as a new Section
* SVL-Form of Book I Section 1.6.1.6 and 1.6.2

----------------

\newpage{}

# Notation, Section 1.3.2

When register operands (RA, RT, BF) are prefixed by a single underscore
(_RT, _RA, _BF) the variable contains the contents of the instruction field
not the contents of the Register File referenced *by* that field. Example:
`_RT` contains the contents of bits 5 thru 10. The relationship
`RT = GPR(_RT)` is thus always true. Uses include making alternative
decisions within an instruction based on whether the operand field
is zero or non-zero.

----------------

\newpage{}

# svstep: Vertical-First Stepping and status reporting

SVL-Form

* svstep RT,SVi,vf (Rc=0)
* svstep. RT,SVi,vf (Rc=1)

| 0-5|6-10|11.15|16..22| 23-25    | 26-30 |31|   Form   |
|----|----|-----|------|----------|-------|--|--------- |
|PO  | RT | /   | SVi  |  / / vf  | XO    |Rc| SVL-Form |

Pseudo-code:

```
    if SVi[3:4] = 0b11 then
        # store pack and unpack in SVSTATE
        SVSTATE[53] <- SVi[5]
        SVSTATE[54] <- SVi[6]
        RT <- [0]*62 || SVSTATE[53:54]
    else
        # Vertical-First explicit stepping.
        step <- SVSTATE_NEXT(SVi, vf)
        RT <- [0]*57 || step
```

Special Registers Altered:

    CR0                     (if Rc=1)

-------------

\newpage{}


# setvl

SVL-Form

| 0-5|6-10|11-15|16-22 | 23 24 25 | 26-30 |31|   FORM   |
| -- | -- | --- | ---- |----------| ----- |--|----------|
|PO  | RT | RA  | SVi  | ms vs vf | XO    |Rc| SVL-Form |

* setvl RT,RA,SVi,vf,vs,ms (Rc=0)
* setvl. RT,RA,SVi,vf,vs,ms (Rc=1)

Pseudo-code:

```
    overflow <- 0b0    # sets CR.SO if set and if Rc=1
    VLimm <- SVi + 1
    # set or get MVL
    if ms = 1 then MVL <- VLimm[0:6]
    else           MVL <- SVSTATE[0:6]
    # set or get VL
    if vs = 0                then VL <- SVSTATE[7:13]
    else if _RA != 0         then
        if (RA) >u 0b1111111 then
            VL <- 0b1111111
            overflow <- 0b1
        else                      VL <- (RA)[57:63]
    else if _RT = 0          then VL <- VLimm[0:6]
    else if CTR >u 0b1111111 then
        VL <- 0b1111111
        overflow <- 0b1
    else                          VL <- CTR[57:63]
    # limit VL to within MVL
    if VL >u MVL then
        overflow <- 0b1
        VL <- MVL
    SVSTATE[0:6] <- MVL
    SVSTATE[7:13] <- VL
    if _RT != 0 then
       GPR(_RT) <- [0]*57 || VL
    # MAXVL is a static "state-reset" opportunity so VF is only set then.
    if ms = 1 then
         SVSTATE[63] <- vf   # set Vertical-First mode
         SVSTATE[62] <- 0b0  # clear persist bit
```

Special Registers Altered:

```
    CR0                     (if Rc=1)
```

* `SVi` - bits 16-22 - an immediate operand for setting MVL and/or VL
* `ms` - bit 23 - allows for setting of MVL
* `vs` - bit 24 - allows for setting of VL
* `vf` - bit 25 - sets "Vertical First Mode".

Note that in immediate setting mode VL and MVL start from **one**
but that this is compensated for in the assembly notation.
i.e. that an immediate value of 1 in assembler notation
actually places the value 0b0000000 in the `SVi` field bits:
on execution the `setvl` instruction adds one to the decoded
`SVi` field bits, resulting in
VL/MVL being set to 1. This allows VL to be set to values
ranging from 1 to 128 with only 7 bits instead of 8.
Setting VL/MVL
to 0 would result in all Vector operations becoming `nop`.  If this is
truly desired (nop behaviour) then setting VL and MVL to zero is to be
done via the [[SVSTATE SPR|sv/sprs]].

Note that setmvli is a pseudo-op, based on RA/RT=0, and setvli likewise

    setvli   VL=8   : setvl  r0, r0, VL=8, vf=0, vs=1, ms=0
    setvli.  VL=8   : setvl. r0, r0, VL=8, vf=0, vs=1, ms=0
    setmvli  MVL=8  : setvl  r0, r0, MVL=8, vf=0, vs=0, ms=1
    setmvli. MVL=8  : setvl. r0, r0, MVL=8, vf=0, vs=0, ms=1

Additional pseudo-op for obtaining VL without modifying it (or any state):

    getvl  r5      : setvl  r5, r0, vf=0, vs=0, ms=0
    getvl. r5      : setvl. r5, r0, vf=0, vs=0, ms=0

Note that whilst it is possible to set both MVL and VL from the same
immediate, it is not possible to set them to different immediates in
the same instruction.  Doing so would require two instructions.

**Selecting sources for VL**

There is considerable opcode pressure, consequently to set MVL and VL
from different sources is as follows:

| condition           | effect         |
| - | - |
| `vs=1, RA=0, RT!=0` | VL,RT set to MIN(MVL, CTR)  |
| `vs=1, RA=0, RT=0`  | VL set to MIN(MVL, SVi+1)  |
| `vs=1, RA!=0, RT=0` | VL set to MIN(MVL, RA)  |
| `vs=1, RA!=0, RT!=0` | VL,RT set to MIN(MVL, RA)  |

The reasoning here is that the opportunity to set RT equal to the
immediate `SVi+1` is sacrificed in favour of setting from CTR.

# Unusual Rc=1 behaviour

Normally, the return result from an instruction is in `RT`. With
it being possible for `RT=0` to mean that `CTR` mode is to be read,
some different semantics are needed.

CR Field 0, when `Rc=1`, may be set even if `RT=0`. The reason is that
overflow may occur: `VL`, if set either from an immediate or from `CTR`,
may not exceed `MAXVL`, and if it is, `CR0.SO` must be set.

Additionally, in reality it is **`VL`** being set. Therefore, rather
than `CR0` testing `RT` when `Rc=1`, CR0.EQ is set if `VL=0`, CR0.GE
is set if `VL` is non-zero.

# Vertical First Mode

Vertical First is effectively like an implicit single bit predicate
applied to every SVP64 instruction.  **ONLY** one element in each
SVP64 Vector instruction is executed; srcstep and dststep do **not**
increment, and the Program Counter progresses **immediately** to
the next instruction just as it would for any standard scalar v3.0B
instruction.

An explicit mode of setvl is called which can move srcstep and
dststep on to the next element, still respecting predicate
masks.  

In other words, where normal SVP64 Vectorisation acts "horizontally"
by looping first through 0 to VL-1 and only then moving the PC
to the next instruction, Vertical-First moves the PC onwards
(vertically) through multiple instructions **with the same
srcstep and dststep**, then an explict instruction used to
advance srcstep/dststep. An outer loop is expected to be
used (branch instruction) which completes a series of
Vector operations.

```svfstep``` mode is enabled when vf=1, vs=0 and ms=0. 
When Rc=1 it is possible to determine when any level of
loops reach an end condition, or if VL has been reached. The immediate can
be reinterpreted as indicating which SVSTATE (0-3)
should be tested and placed into CR0 (when Rc=1)

When RT is not zero, an internal stepping index may also be returned,
either the REMAP index or srcstep or dststep. This table is identical
to that of [[sv/svstep]]:

* `SVi=1`: also include inner middle and outer
  loop end conditions from SVSTATE0 into CR.EQ CR.LE CR.GT
* `SVi=2`: test SVSTATE1 (and return conditions)
* `SVi=3`: test SVSTATE2 (and return conditions)
* `SVi=4`: test SVSTATE3 (and return conditions)
* `SVi=5`: `SVSTATE.srcstep` is returned.
* `SVi=6`: `SVSTATE.dststep` is returned.

Testing any end condition of any loop of any REMAP state allows branches to be used to create loops.

*Programmers should be aware that VL, srcstep and dststep are global in nature.
Nested looping with different schedules is perfectly possible, as is
calling of functions, however SVSTATE (and any associated SVSTATE) should be stored on the stack.*

**SUBVL**

Sub-vector elements are not be considered "Vertical". The vec2/3/4
is to be considered as if the "single element".  Caveats exist for
[[sv/mv.swizzle]] and [[sv/mv.vec]] when Pack/Unpack is enabled,
due to the order in which VL and SUBVL loops are applied being
swapped (outer-inner becomes inner-outer)

# Examples

## Core concept loop

```
loop:
    setvl a3, a0, MVL=8    #  update a3 with vl
                           # (# of elements this iteration)
                           # set MVL to 8
    # do vector operations at up to 8 length (MVL=8)
    # ...
    sub a0, a0, a3   # Decrement count by vl
    bnez a0, loop    # Any more?
```

## Loop using Rc=1

    my_fn:
      li r3, 1000
      b test
    loop:
      sub r3, r3, r4
      ...
    test:
      setvli. r4, r3, MVL=64
      bne cr0, loop
    end:
      blr

## Load/Store-Multi (selective)

Up to 64 FPRs will be loaded, here.  `r3` is set one per bit
for each FP register required to be loaded.  The block of memory
from which the registers are loaded is contiguous (no gaps):
any FP register which has a corresponding zero bit in `r3`
is *unaltered*.  In essence this is a selective LD-multi with
"Scatter" capability.

    setvli r0, MVL=64, VL=64
    sv.fld/dm=r3 *r0, 0(r30) # selective load 64 FP registers

Up to 64 FPRs will be saved, here.  Again, `r3` 

    setvli r0, MVL=64, VL=64
    sv.stfd/sm=r3 *fp0, 0(r30) # selective store 64 FP registers

-------------

\newpage{}

# SVSTATE SPR

The format of the SVSTATE SPR is as follows:

| Field | Name     | Description           |
| ----- | -------- | --------------------- |
| 0:6   | maxvl    | Max Vector Length     |
| 7:13  |    vl    | Vector Length         |
| 14:20 | srcstep  | for srcstep = 0..VL-1 |
| 21:27 | dststep  | for dststep = 0..VL-1 |
| 28:29 | dsubstep | for substep = 0..SUBVL-1  |
| 30:31 | ssubstep | for substep = 0..SUBVL-1  |
| 32:33 | mi0      | REMAP RA/FRA/BFA SVSHAPE0-3    |
| 34:35 | mi1      | REMAP RB/FRB/BFB SVSHAPE0-3    |
| 36:37 | mi2      | REMAP RC/FRT SVSHAPE0-3    |
| 38:39 | mo0      | REMAP RT/FRT/BF SVSHAPE0-3    |
| 40:41 | mo1      | REMAP EA/RS/FRS SVSHAPE0-3    |
| 42:46 | SVme     | REMAP enable (RA-RT)  |
| 47:52 | rsvd     | reserved              |
| 53    | pack     | PACK (srcstrp reorder)  |
| 54    | unpack   | UNPACK (dststep order)  |
| 55:61 | hphint   | Horizontal Hint       |
| 62    | RMpst    | REMAP persistence     |
| 63    | vfirst   | Vertical First mode   |

Notes:

* The entries are truncated to be within range.  Attempts to set VL to
  greater than MAXVL will truncate VL.
* Setting srcstep, dststep to 64 or greater, or VL or MVL to greater
  than 64 is reserved and will cause an illegal instruction trap.

**SVSTATE Fields**

SVSTATE is a standard SPR that (if REMAP is not activated) contains sufficient
self-contaned information for a full context save/restore.
SVSTATE contains (and permits setting of):

* MVL (the Maximum Vector Length) - declares (statically) how
  much of a regfile is to be reserved for Vector elements
* VL - Vector Length
* dststep - the destination element offset of the current parallel
  instruction being executed
* srcstep - for twin-predication, the source element offset as well.
* ssubstep - the source subvector element offset of the current
  parallel instruction being executed
* dsubstep - the destination subvector element offset of the current
  parallel instruction being executed
* vfirst - Vertical First mode.  srcstep, dststep and substep
    **do not advance** unless explicitly requested to do so with
    pseudo-op svstep (a mode of setvl)
* RMpst - REMAP persistence.  REMAP will apply only to the following
  instruction unless this bit is set, in which case REMAP "persists".
  Reset (cleared) on use of the `setvl` instruction if used to
  alter VL or MVL.
* Pack - if set then srcstep/substep VL/SUBVL loop-ordering is inverted.
* UnPack - if set then dststep/substep VL/SUBVL loop-ordering is inverted.
* hphint - Horizontal Parallelism Hint. Indicates that
  no Hazards exist between groups of elements in sequential multiples of this number
   (before REMAP).  By definition: elements for which `FLOOR(srcstep/hphint)` is
   equal *before REMAP* are in the same parallelism "group". In Vertical First Mode
   hardware **MUST ONLY** process elements in the same group, and must stop
   Horizontal Issue at the last element of a given group. Set to zero to indicate "no hint".
* SVme - REMAP enable bits, indicating which register is to be
   REMAPed: RA, RB, RC, RT and EA are the canonical (typical) register names
   associated with each bit, with RA being the LSB and EA being the MSB.
   See table below for ordering. When `SVme` is zero (0b00000) REMAP
   is **fully disabled and inactive** regardless of the contents of
  `SVSTATE`, `mi0-mi2/mo0-mo1`, or the four `SVSHAPEn` SPRs
* mi0-mi2/mo0-mo1 - when the corresponding SVme bit is enabled, these
  indicate the SVSHAPE (0-3) that the corresponding register (RA etc)
  should use, as long as the register's corresponding SVme bit is set 

Programmer's Note: the fact that REMAP is entirely dormant when `SVme` is zero
allows establishment of REMAP context well in advance, followed by utilising `svremap`
at a precise (or the very last) moment.  Some implementations may exploit this
to cache (or take some time to prepare caches) in the background whilst other
(unrelated) instructions are being executed. This is particularly important to
bear in mind when using `svindex` which will require hardware to perform (and
cache) additional GPR reads.

Programmer's Note: when REMAP is activated it becomes necessary on any
context-switch (Interrupt or Function call) to detect (or know in advance)
that REMAP is enabled and to additionally save/restore the four SVSHAPE
SPRs, SVHAPE0-3.  Given that this is expected to be a rare occurrence it was
deemed unreasonable to burden every context-switch or function call with
mandatory save/restore of SVSHAPEs, and consequently it is a *callee*
(and Trap Handler) responsibility.  Callees (and Trap Handlers) **MUST**
avoid using all and any SVP64 instructions during the period where state
could be adversely affected.  SVP64 purely relies on Scalar instructions,
so Scalar instructions (except the SVP64 Management ones and mtspr and
mfspr) are 100% guaranteed to have zero impact on SVP64 state.

**Max Vector Length (maxvl)** <a name="mvl" />

MAXVECTORLENGTH is the same concept as MVL in RISC-V RVV, except that it
is variable length and may be dynamically set (normally from an immediate
field only).  MVL is limited to 7 bits
(in the first version of SVP64) and consequently the maximum number of
elements is limited to between 0 and 127.

Programmer's Note: Except by directly using `mtspr` on SVSTATE, which may
result in performance penalties on some hardware implementations, SVSTATE's `maxvl`
field may only be set **statically** as an immediate, by the `setvl` instruction.
It may **NOT** be set dynamically from a register.  Compiler writers and assembly
programmers are expected to perform static register file analysis, subdivision,
and allocation and only utilise `setvl`. Direct writing to SVSTATE in order to
"bypass" this Note could, in less-advanced implementations, potentially cause stalling,
particularly if SVP64 instructions are issued directly after the `mtspr` to SVSTATE.

**Vector Length (vl)** <a name="vl" />

The actual Vector length, the number of elements in a "Vector", `SVSTATE.vl` may be set
entirely dynamically at runtime from a number of sources. `setvl` is the primary
instruction for setting Vector Length.
`setvl` is conceptually similar but different from the Cray, SX Aurora, and RISC-V RVV
equivalent. Similar to RVV, VL is set to be within
the range 0 <= VL <= MVL. Unlike RVV, VL is set **exactly** according to the following:

    VL = (RT|0) = MIN(vlen, MVL)

where 0 <= MVL <= 127 and vlen may come from an immediate, `RA`, or from the `CTR` SPR,
depending on options selected with the `setvl` instruction.

Programmer's Note: conceptual understanding of Cray-style Vectors is far beyond the scope
of the Power ISA Technical Reference.  Guidance on the 50-year-old Cray Vector paradigm is
best sought elsewhere: good studies include Academic Courses given on the 1970s
Cray Supercomputers over at least the past three decades.

**SUBVL - Sub Vector Length**

This is a "group by quantity" that effectively asks each iteration
of the hardware loop to load SUBVL elements of width elwidth at a
time. Effectively, SUBVL is like a SIMD multiplier: instead of just 1
operation issued, SUBVL operations are issued.

The main effect of SUBVL is that predication bits are applied per
**group**, rather than by individual element.  Legal values are 0 to 3,
representing 1 operation (1 element) thru 4 operations (4 elements) respectively.
Elements are best though of in the context of 3D, Audio and Video: two Left and Right
Channel "elements" or four ARGB "elements", or three XYZ coordinate "elements".

`subvl` is again primarily set by the `setvl` instruction. Not to be confused
with `hphint`.

Directly related to `subvl` is the `pack` and `unpack` Mode bits of `SVSTATE`.
See `svstep` instruction for how to set Pack and Unpack Modes.


**Horizontal Parallelism**

A problem exists for hardware where it may not be able to detect
that a programmer (or compiler) knows of opportunities for parallelism
and lack of overlap between loops.

For hphint, the number chosen must be consistently
executed **every time**. Hardware is not permitted to execute five
computations for one instruction then three on the next.
hphint is a hint from the compiler to hardware that exactly this
many elements may be safely executed in parallel, without hazards
(including Memory accesses).
Interestingly, when hphint is set equal to VL, it is in effect
as if Vertical First mode were not set, because the hardware is
given the option to run through all elements in an instruction.
This is exactly what Horizontal-First is: a for-loop from 0 to VL-1
except that the hardware may *choose* the number of elements.

*Note to programmers: changing VL during the middle of such modes
should be done only with due care and respect for the fact that SVSTATE
has exactly the same peer-level status as a Program Counter.*

-------------

\newpage{}

# SVL-Form

Add the following to Book I, 1.6.1, SVL-Form

```
    |0     |6    |11    |16   |23 |24 |25 |26    |31 |
    | PO   |  RT |   RA | SVi |ms |vs |vf |   XO |Rc |
    | PO   |  RT | /    | SVi |/  |/  |vf |   XO |Rc |
```

* Add `SVL` to `RA (11:15)` Field in Book I, 1.6.2
* Add `SVL` to `RT (6:10)` Field in Book I, 1.6.2
* Add `SVL` to `Rc (31)` Field in Book I, 1.6.2
* Add `SVL` to `XO (26:31)` Field in Book I, 1.6.2

Add the following to Book I, 1.6.2

```
    ms (23)
        Field used in Simple-V to specify whether MVL (maxvl in the SVSTATE SPR)
        is to be set
        Formats: SVL
    vf (25)
        Field used in Simple-V to specify whether "Vertical" Mode is set
        (vfirst in the SVSTATE SPR)
        Formats: SVL
    vs (24)
        Field used in Simple-V to specify whether VL (vl in the SVSTATE SPR) is to be set
        Formats: SVL
    SVi (16:22)
         Simple-V immediate field used by setvl for setting VL or MVL
         (vl, maxvl in the SVSTATE SPR)
         and used as a "Mode of Operation" selector in svstep
         Formats: SVL
```

# Appendices

    Appendix E Power ISA sorted by opcode
    Appendix F Power ISA sorted by version
    Appendix G Power ISA sorted by Compliancy Subset
    Appendix H Power ISA sorted by mnemonic

| Form | Book | Page | Version | mnemonic | Description |
|------|------|------|---------|----------|-------------|
| SVL  | I    | #    | 3.0B    | svstep   | Vertical-First Stepping and status reporting |
| SVL  | I    | #    | 3.0B    | setvl    | Cray-like establishment of Looping (Vector) context |