(no commit message)

[libreriscv.git] / openpower / sv / int_fp_mv.mdwn

[[!tag standards]]

# FPR-to-GPR and GPR-to-FPR

**Draft Status** under development, for submission as an RFC

Links:

* <https://bugs.libre-soc.org/show_bug.cgi?id=650>
* <https://bugs.libre-soc.org/show_bug.cgi?id=230#c71>
* <https://bugs.libre-soc.org/show_bug.cgi?id=230#c74>
* <https://bugs.libre-soc.org/show_bug.cgi?id=230#c76>

Introduction:

High-performance CPU/GPU software needs to often convert between integers
and floating-point, therefore fast conversion/data-movement instructions
are needed.  Also given that initialisation of floats tends to take up
considerable space (even to just load 0.0) the inclusion of compact
format float immediate is up for consideration using BF16 as a base.

Libre-SOC will be compliant with the
**Scalar Floating-Point Subset** (SFFS) i.e. is not implementing VMX/VSX,
and with its focus on modern 3D GPU hybrid workloads represents an
important new potential use-case for OpenPOWER.

Prior to the formation of the Compliancy Levels first introduced
in v3.0C and v3.1
the progressive historic development of the Scalar parts of the Power ISA assumed
that VSX would always be there to complement it. However With VMX/VSX 
**not available** in the newly-introduced SFFS Compliancy Level, the
existing non-VSX conversion/data-movement instructions require load/store
instructions (slow and expensive) to transfer data between the FPRs and
the GPRs.  For a 3D GPU this kills any modern competitive edge.
Also, because SimpleV needs efficient scalar instructions in
order to generate efficient vector instructions, adding new instructions
for data-transfer/conversion between FPRs and GPRs multiplies the savings.

In addition, the vast majority of GPR <-> FPR data-transfers are as part
of a FP <-> Integer conversion sequence, therefore reducing the number
of instructions required to the minimum seems necessary.

Therefore, we are proposing adding:

* FPR load-immediate using `BF16` as the constant
* FPR <-> GPR data-transfer instructions that just copy bits without conversion
* FPR <-> GPR combined data-transfer/conversion instructions that do
  Integer <-> FP conversions

If we're adding new Integer <-> FP conversion instructions, we may
as well take this opportunity to modernise the instructions and make them
well suited for common/important conversion sequences:

* standard Integer -> FP IEEE754 conversion (used by most languages and CPUs)
* standard OpenPower FP -> Integer conversion (saturation with NaN
  converted to minimum valid integer)
* Rust FP -> Integer conversion (saturation with NaN converted to 0)
* JavaScript FP -> Integer conversion (modular with Inf/NaN converted to 0)

The assembly listings in the [[int_fp_mv/appendix]] show how costly
some of these language-specific conversions are: Javascript is 35
scalar instructions, including four branches.

## FP -> Integer conversions

Different programming languages turn out to have completely different
semantics for FP to Integer conversion.  This section gives an overview
of the different variants, listing the languages and hardware that
implements each variant.

## standard Integer -> FP conversion

This conversion is outlined in the IEEE754 specification.  It is used
by nearly all programming languages and CPUs.  In the case of OpenPOWER,
the rounding mode is read from FPSCR

### standard OpenPower FP -> Integer conversion

This conversion, instead of exact IEEE754 Compliance, performs
"saturation with NaN converted to minimum valid integer". This
is also exactly the same as the x86 ISA conversion senantics.
OpenPOWER however has instructions for both:

* rounding mode read from FPSCR
* rounding mode always set to truncate

### Rust FP -> Integer conversion

For the sake of simplicity, the FP -> Integer conversion semantics generalized from those used by Rust's `as` operator will be referred to as [Rust conversion semantics](#fp-to-int-rust-conversion-semantics).

Those same semantics are used in some way by all of the following languages (not necessarily for the default conversion method):

* Rust's FP -> Integer conversion using the
  [`as` operator](https://doc.rust-lang.org/reference/expressions/operator-expr.html#semantics)
* Java's
  [FP -> Integer conversion](https://docs.oracle.com/javase/specs/jls/se16/html/jls-5.html#jls-5.1.3)
* LLVM's
  [`llvm.fptosi.sat`](https://llvm.org/docs/LangRef.html#llvm-fptosi-sat-intrinsic) and
  [`llvm.fptoui.sat`](https://llvm.org/docs/LangRef.html#llvm-fptoui-sat-intrinsic) intrinsics
* SPIR-V's OpenCL dialect's
  [`OpConvertFToU`](https://www.khronos.org/registry/spir-v/specs/unified1/SPIRV.html#OpConvertFToU) and
  [`OpConvertFToS`](https://www.khronos.org/registry/spir-v/specs/unified1/SPIRV.html#OpConvertFToS)
  instructions when decorated with
  [the `SaturatedConversion` decorator](https://www.khronos.org/registry/spir-v/specs/unified1/SPIRV.html#_a_id_decoration_a_decoration).

### JavaScript FP -> Integer conversion

For the sake of simplicity, the FP -> Integer conversion semantics generalized from those used by JavaScripts's `ToInt32` abstract operation will be referred to as [JavaScript conversion semantics](#fp-to-int-javascript-conversion-semantics).

This instruction is present in ARM assembler as FJCVTZS
<https://developer.arm.com/documentation/dui0801/g/hko1477562192868>

### Other languages

TODO: review and investigate other language semantics

# Proposed New Scalar Instructions

All of the following instructions use the standard OpenPower conversion to/from 64-bit float format when reading/writing a 32-bit float from/to a FPR.  All integers however are sourced/stored in the *GPR*.

Integer operands and results being in the GPR is the key differentiator between the proposed instructions
(the entire rationale) compated to existing Scalar Power ISA.
In all existing Power ISA Scalar conversion instructions, all
operands are FPRs, even if the format of the source or destination
data is actually a scalar integer.

Note that source and destination widths can be overridden by SimpleV
SVP64, and that SVP64 also has Saturation Modes *in addition*
to those independently described here. SVP64 Overrides and Saturation
work on *both* Fixed *and* Floating Point operands and results.
 The interactions with SVP64
are explained in the  [[int_fp_mv/appendix]]

## FPR to GPR moves

* `fmvtg RT, FRA`
* `fmvtg. RT, FRA`

move a 64-bit float from a FPR to a GPR, just copying bits directly.
As a direct bitcopy, no exceptions occur and no status flags are set.

Rc=1 tests RT and sets CR0, exactly like all other Scalar Fixed-Point
operations.

* `fmvtgs RT, FRA`
* `fmvtgs. RT, FRA`

move a 32-bit float from a FPR to a GPR, just copying bits. Converts the
64-bit float in `FRA` to a 32-bit float, then writes the 32-bit float to
`RT`. Effectively, `fmvtgs` is a macro-fusion of `frsp fmvtg`
and therefore has the exact same exception and flags behaviour of `frsp`

Unlike `frsp` however, with RT being a GPR, Rc=1 follows
standard *integer* behaviour, i.e. tests RT and sets CR0.

## GPR to FPR moves

`fmvfg FRT, RA`

move a 64-bit float from a GPR to a FPR, just copying bits. No exceptions
are raised, no flags are altered of any kind.

Rc=1 tests FRT and sets CR1

`fmvfgs FRT, RA`

move a 32-bit float from a GPR to a FPR, just copying bits. Converts the
32-bit float in `RA` to a 64-bit float, then writes the 64-bit float to
`FRT`. Effectively, `fmvfgs` is a macro-fusion of `fmvfg frsp` and
therefore has the exact same exception and flags behaviour of `frsp`

Rc=1 tests FRT and sets CR1

TODO: clear statement on evaluation as to whether exceptions or flags raised as part of the **FP** conversion (not the int bitcopy part, the conversion part.  the semantics should really be the same as frsp)

v3.0C section 4.6.7.1 states:

FPRF is set to the class and sign of the result, except for Invalid Operation Exceptions when VE=1.

    Special Registers Altered:
      FPRF FR FI
      FX OX UX XX VXSNAN
      CR1 (if Rc=1)

### Float load immediate <a name="fmvis"></a>

This is like a variant of `fmvfg`

`fmvis FRT, FI`

Reinterprets `FI << 16` as a 32-bit float, which is then converted to a
64-bit float and written to `FRT`.  This is equivalent to reinterpreting
`FI` as a `BF16` and converting to 64-bit float.

There is no need for an Rc=1 variant because this is an immediate loading
instruction. This frees up one extra bit in the X-Form format for packing
a full `BF16`.

Example:

```
# clearing a FPR
fmvis f4, 0 # writes +0.0 to f4
# loading handy constants
fmvis f4, 0x8000 # writes -0.0 to f4
fmvis f4, 0x3F80 # writes +1.0 to f4
fmvis f4, 0xBF80 # writes -1.0 to f4
fmvis f4, 0xBFC0 # writes -1.5 to f4
fmvis f4, 0x7FC0 # writes +qNaN to f4
fmvis f4, 0x7F80 # writes +Infinity to f4
fmvis f4, 0xFF80 # writes -Infinity to f4
fmvis f4, 0x3FFF # writes +1.9921875 to f4

# clearing 128 FPRs with 2 SVP64 instructions
# by issuing 32 vec4 (subvector length 4) ops
setvli VL=MVL=32
sv.fmvis/vec4 f0, 0 # writes +0.0 to f0-f127
```
Important: If the float load immediate instruction(s) are left out,
change all [GPR to FPR conversion instructions](#GPR-to-FPR-conversions)
to instead write `+0.0` if `RA` is register `0`, at least
allowing clearing FPRs.

|  0-5   | 6-10 | 11-25 | 26-30 | 31  |
|--------|------|-------|-------|-----|
|  Major | FRT  | FI    | XO    | FI0 |

The above fits reasonably well with Minor 19 and follows the
pattern shown by `addpcis`, which uses an entire column of Minor 19
XO. 15 bits of FI fit into bits 11 to 25,
the top bit FI0 (MSB0 numbered 0) makes 16.

    bf16 = FI0 || FI
    fp32 = bf16 || [0]*16
    FRT = Single_to_Double(fp32)

Also worth noting, `fmvis` fits well with DX-Form:

|  0-5   | 6-10 | 11-15 | 16-25 | 26-30 | 31  |
|--------|------|-------|-------|-------|-----|
|  Major | FRT  | d0    | d1    | XO    | d2  |

    bf16 = d2 || d1 || d0
    fp32 = bf16 || [0]*16
    FRT = Single_to_Double(fp32)

## FPR to GPR conversions

<div id="fpr-to-gpr-conversion-mode"></div>

X-Form:

|  0-5   | 6-10 | 11-15  | 16-25 | 26-30 | 31 |
|--------|------|--------|-------|-------|----|
|  Major | RT   | //Mode | FRA   | XO    | Rc |
|  Major | FRT  | //Mode | RA    | XO    | Rc |

Mode values:

| Mode | `rounding_mode` | Semantics                        |
|------|-----------------|----------------------------------|
| 000  | from `FPSCR`    | [OpenPower semantics]            |
| 001  | Truncate        | [OpenPower semantics]            |
| 010  | from `FPSCR`    | [Rust semantics]                 |
| 011  | Truncate        | [Rust semantics]                 |
| 100  | from `FPSCR`    | [JavaScript semantics]           |
| 101  | Truncate        | [JavaScript semantics]           |
| rest | --              | illegal instruction trap for now |

[OpenPower semantics]: #fp-to-int-openpower-conversion-semantics
[Rust semantics]: #fp-to-int-rust-conversion-semantics
[JavaScript semantics]: #fp-to-int-javascript-conversion-semantics

`fcvttgw RT, FRA, Mode`

Convert from 64-bit float to 32-bit signed integer, writing the result
to the GPR `RT`. Converts using [mode `Mode`]

`fcvttguw RT, FRA, Mode`

Convert from 64-bit float to 32-bit unsigned integer, writing the result
to the GPR `RT`. Converts using [mode `Mode`]

`fcvttgd RT, FRA, Mode`

Convert from 64-bit float to 64-bit signed integer, writing the result
to the GPR `RT`. Converts using [mode `Mode`]

`fcvttgud RT, FRA, Mode`

Convert from 64-bit float to 64-bit unsigned integer, writing the result
to the GPR `RT`. Converts using [mode `Mode`]

`fcvtstgw RT, FRA, Mode`

Convert from 32-bit float to 32-bit signed integer, writing the result
to the GPR `RT`. Converts using [mode `Mode`]

`fcvtstguw RT, FRA, Mode`

Convert from 32-bit float to 32-bit unsigned integer, writing the result
to the GPR `RT`. Converts using [mode `Mode`]

`fcvtstgd RT, FRA, Mode`

Convert from 32-bit float to 64-bit signed integer, writing the result
to the GPR `RT`. Converts using [mode `Mode`]

`fcvtstgud RT, FRA, Mode`

Convert from 32-bit float to 64-bit unsigned integer, writing the result
to the GPR `RT`. Converts using [mode `Mode`]

[mode `Mode`]: #fpr-to-gpr-conversion-mode

## GPR to FPR conversions

All of the following GPR to FPR conversions use the rounding mode from `FPSCR`.

`fcvtfgw FRT, RA`

Convert from 32-bit signed integer in the GPR `RA` to 64-bit float in `FRT`.

`fcvtfgws FRT, RA`

Convert from 32-bit signed integer in the GPR `RA` to 32-bit float in `FRT`.

`fcvtfguw FRT, RA`

Convert from 32-bit unsigned integer in the GPR `RA` to 64-bit float in `FRT`.

`fcvtfguws FRT, RA`

Convert from 32-bit unsigned integer in the GPR `RA` to 32-bit float in `FRT`.

`fcvtfgd FRT, RA`

Convert from 64-bit signed integer in the GPR `RA` to 64-bit float in `FRT`.

`fcvtfgds FRT, RA`

Convert from 64-bit signed integer in the GPR `RA` to 32-bit float in `FRT`.

`fcvtfgud FRT, RA`

Convert from 64-bit unsigned integer in the GPR `RA` to 64-bit float in `FRT`.

`fcvtfguds FRT, RA`

Convert from 64-bit unsigned integer in the GPR `RA` to 32-bit float in `FRT`.

# FP to Integer Conversion Pseudo-code

Key for pseudo-code:

| term                      | result type | definition                                                                                         |
|---------------------------|-------------|----------------------------------------------------------------------------------------------------|
| `fp`                      | --          | `f32` or `f64` (or other types from SimpleV)                                                       |
| `int`                     | --          | `u32`/`u64`/`i32`/`i64` (or other types from SimpleV)                                              |
| `uint`                    | --          | the unsigned integer of the same bit-width as `int`                                                |
| `int::BITS`               | `int`       | the bit-width of `int`                                                                             |
| `int::MIN_VALUE`          | `int`       | the minimum value `int` can store (`0` if unsigned, `-2^(int::BITS-1)` if signed)                  |
| `int::MAX_VALUE`          | `int`       | the maximum value `int` can store (`2^int::BITS - 1` if unsigned, `2^(int::BITS-1) - 1` if signed) |
| `int::VALUE_COUNT`        | Integer     | the number of different values `int` can store (`2^int::BITS`). too big to fit in `int`.           |
| `rint(fp, rounding_mode)` | `fp`        | rounds the floating-point value `fp` to an integer according to rounding mode `rounding_mode`      |

<div id="fp-to-int-openpower-conversion-semantics"></div>
OpenPower conversion semantics (section A.2 page 999 (page 1023) of OpenPower ISA v3.1):

```
def fp_to_int_open_power<fp, int>(v: fp) -> int:
    if v is NaN:
        return int::MIN_VALUE
    if v >= int::MAX_VALUE:
        return int::MAX_VALUE
    if v <= int::MIN_VALUE:
        return int::MIN_VALUE
    return (int)rint(v, rounding_mode)
```

<div id="fp-to-int-rust-conversion-semantics"></div>
Rust [conversion semantics](https://doc.rust-lang.org/reference/expressions/operator-expr.html#semantics) (with adjustment to add non-truncate rounding modes):

```
def fp_to_int_rust<fp, int>(v: fp) -> int:
    if v is NaN:
        return 0
    if v >= int::MAX_VALUE:
        return int::MAX_VALUE
    if v <= int::MIN_VALUE:
        return int::MIN_VALUE
    return (int)rint(v, rounding_mode)
```

<div id="fp-to-int-javascript-conversion-semantics"></div>
Section 7.1 of the ECMAScript / JavaScript
[conversion semantics](https://262.ecma-international.org/11.0/#sec-toint32) (with adjustment to add non-truncate rounding modes):

```
def fp_to_int_java_script<fp, int>(v: fp) -> int:
    if v is NaN or infinite:
        return 0
    v = rint(v, rounding_mode)
    v = v mod int::VALUE_COUNT  # 2^32 for i32, 2^64 for i64, result is non-negative
    bits = (uint)v
    return (int)bits
```

# Equivalent OpenPower ISA v3.0 Assembly Language for FP -> Integer Conversion Modes

Moved to [[int_fp_mv/appendix]]