1 # FPR-to-GPR and GPR-to-FPR
5 High-performance CPU/GPU software needs to often convert between integers
6 and floating-point, therefore fast conversion/data-movement instructions
7 are needed. Also given that initialisation of floats tends to take up
8 considerable space (even to just load 0.0) the inclusion of float immediate
9 is up for consideration (BF16 as immediates)
11 Libre-SOC will be compliant with the
12 **Scalar Floating-Point Subset** (SFFS) i.e. is not implementing VMX/VSX,
13 and with its focus on modern 3D GPU hybrid workloads represents an
14 important new potential use-case for OpenPOWER.
16 The progressive development of the Scalar parts of the Power ISA assumed
17 that VSX would be there to complement it. However With VMX/VSX
18 **not available** in the newly-introduced SFFS Compliancy Level, the
19 existing non-VSX conversion/data-movement instructions require load/store
20 instructions (slow and expensive) to transfer data between the FPRs and
21 the GPRs. Also, because SimpleV needs efficient scalar instructions in
22 order to generate efficient vector instructions, adding new instructions
23 for data-transfer/conversion between FPRs and GPRs multiplies the savings.
25 In addition, the vast majority of GPR <-> FPR data-transfers are as part
26 of a FP <-> Integer conversion sequence, therefore reducing the number
27 of instructions required to the minimum seems necessary.
29 Therefore, we are proposing adding:
31 * FPR load-immediate using `BF16` as the constant
32 * FPR <-> GPR data-transfer instructions that just copy bits without conversion
33 * FPR <-> GPR combined data-transfer/conversion instructions that do
34 Integer <-> FP conversions
36 If we're adding new Integer <-> FP conversion instructions, we may
37 as well take this opportunity to modernise the instructions and make them
38 well suited for common/important conversion sequences:
40 * standard Integer -> FP IEEE754 conversion (used by most languages and CPUs)
41 * standard OpenPower FP -> Integer conversion (saturation with NaN
42 converted to minimum valid integer)
43 * Rust FP -> Integer conversion (saturation with NaN converted to 0)
44 * JavaScript FP -> Integer conversion (modular with Inf/NaN converted to 0)
46 The assembly listings in the [[int_fp_mv/appendix]] show how costly
47 some of these language-specific conversions are: Javascript is 35
48 scalar instructions, including four branches.
50 # A bit more research into integer - fp conversion
52 here is a paragraph which explains that there are different semantics
53 for conversion, i don't know what the paragraph should say, but it needs
54 to be here, to give some background. it also acts as a lead-in to the
55 sub-sections, introducing them and explaining why they are here, as
56 justifications and background research as to why the ISA should support
57 the feature being proposed.
59 *nothing* can be left to chance or guesswork.
61 ## standard Integer -> FP conversion
63 This conversion is outlined in the IEEE754 specification. It is used
64 by nearly all programming languages and CPUs. In the case of OpenPOWER,
65 the rounding mode is read from FPSCR
67 ## FP -> Integer conversions
69 ### standard OpenPower FP -> Integer conversion
71 TODO, explain this further, make this a complete sentence:
72 "saturation with NaN converted to minimum valid integer"
74 - Matches x86's conversion semantics
75 - Has instructions for both:
76 * rounding mode read from FPSCR
77 * rounding mode is always truncate
79 ### Rust FP -> Integer conversion
81 TODO, explain this further, the following is not a complete sentence,
82 "saturation with NaN converted to 0"
84 Semantics required by all of:
85 (what does this mean, what is "required"?
86 what semantics are being referred to? the sentence needs completing:
87 "For Rust integer conversion, the semantics required are shown by the
88 following, all of which are supported in XYZ" something like that)
90 * Rust's FP -> Integer conversion using the
91 [`as` operator](https://doc.rust-lang.org/reference/expressions/operator-expr.html#semantics)
93 [FP -> Integer conversion](https://docs.oracle.com/javase/specs/jls/se16/html/jls-5.html#jls-5.1.3)
95 [`llvm.fptosi.sat`](https://llvm.org/docs/LangRef.html#llvm-fptosi-sat-intrinsic) and
96 [`llvm.fptoui.sat`](https://llvm.org/docs/LangRef.html#llvm-fptoui-sat-intrinsic) intrinsics
97 * SPIR-V's OpenCL dialect's
98 [`OpConvertFToU`](https://www.khronos.org/registry/spir-v/specs/unified1/SPIRV.html#OpConvertFToU) and
99 [`OpConvertFToS`](https://www.khronos.org/registry/spir-v/specs/unified1/SPIRV.html#OpConvertFToS)
100 instructions when decorated with
101 [the `SaturatedConversion` decorator](https://www.khronos.org/registry/spir-v/specs/unified1/SPIRV.html#_a_id_decoration_a_decoration).
103 ### JavaScript FP -> Integer conversion
105 modular with Inf/NaN converted to 0
107 TODO, explain this further, it is not a sentence:
108 "Semantics required by JavaScript"
112 TODO: review and investigate other language semantics
116 * <https://bugs.libre-soc.org/show_bug.cgi?id=650>
117 * <https://bugs.libre-soc.org/show_bug.cgi?id=230#c71>
118 * <https://bugs.libre-soc.org/show_bug.cgi?id=230#c74>
119 * <https://bugs.libre-soc.org/show_bug.cgi?id=230#c76>
121 # Proposed New Scalar Instructions
123 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.
125 This can be overridden by SimpleV, which sets the following
126 operation "reinterpretation" rules:
128 * any operation whose assembler mnemonic does not end in "s"
129 (being defined in v3.0B as a "double" operation) is
130 instead an operation at the overridden elwidth for the
132 * any operation nominally defined as a "single" FP operation
133 is redefined to be **half the elwidth** rather than
138 * `sv.fmvtg/sw=32 RT.v, FRA.v` is defined as treating FRA
139 as a vector of *FP32* source operands each *32* bits wide
140 which are to be placed into *64* bit integer destination elements.
141 * `sv.fmvfgs/dw=32 FRT.v, RA.v` is defined as taking the bottom
142 32 bits of each RA integer source, then performing a **32 bit**
143 FP32 to **FP16** conversion and storing the result in the
144 **32 bits** of an FRT destination element.
146 "Single" is therefore redefined in SVP64 to be "half elwidth"
147 rather than Double width hardcoded to 64 and Single width
148 hardcoded to 32. This allows a full range of conversions
149 between FP64, FP32, FP16 and BF16.
156 move a 64-bit float from a FPR to a GPR, just copying bits directly.
157 Rc=1 tests RT and sets CR0
162 move a 32-bit float from a FPR to a GPR, just copying bits. Converts the
163 64-bit float in `FRA` to a 32-bit float, then writes the 32-bit float to
165 Rc=1 tests RT and sets CR0
171 move a 64-bit float from a GPR to a FPR, just copying bits. No exceptions
172 are raised, no flags are altered of any kind.
178 move a 32-bit float from a GPR to a FPR, just copying bits. Converts the
179 32-bit float in `RA` to a 64-bit float, then writes the 64-bit float to
180 `FRT`. Effectively, `fmvfgs` is a macro-fusion of `fmvfg frsp`.
184 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)
186 v3.0C section 4.6.7.1 states:
188 FPRF is set to the class and sign of the result, except for Invalid Operation Exceptions when VE=1.
190 Special Registers Altered:
195 ### Float load immediate (kinda a variant of `fmvfg`)
199 Reinterprets `FI << 16` as a 32-bit float, which is then converted to a
200 64-bit float and written to `FRT`. This is equivalent to reinterpreting
201 `FI` as a `BF16` and converting to 64-bit float.
207 fmvis f4, 0 # writes +0.0 to f4
208 # loading handy constants
209 fmvis f4, 0x8000 # writes -0.0 to f4
210 fmvis f4, 0x3F80 # writes +1.0 to f4
211 fmvis f4, 0xBF80 # writes -1.0 to f4
212 fmvis f4, 0xBFC0 # writes -1.5 to f4
213 fmvis f4, 0x7FC0 # writes +qNaN to f4
214 fmvis f4, 0x7F80 # writes +Infinity to f4
215 fmvis f4, 0xFF80 # writes -Infinity to f4
216 fmvis f4, 0x3FFF # writes +1.9921875 to f4
218 # clearing 128 FPRs with 2 SVP64 instructions
219 # by issuing 32 vec4 (subvector length 4) ops
221 sv.fmvis/vec4 f0, 0 # writes +0.0 to f0-f127
223 Important: If the float load immediate instruction(s) are left out,
224 change all [GPR to FPR conversion instructions](#GPR-to-FPR-conversions)
225 to instead write `+0.0` if `RA` is register `0`, at least
226 allowing clearing FPRs.
228 | 0-5 | 6-10 | 11-25 | 26-30 | 31 |
229 |--------|------|-------|-------|-----|
230 | Major | FRT | FI | XO | FI0 |
232 The above fits reasonably well with Minor 19 and follows the
233 pattern shown by `addpcis`, which uses an entire column of Minor 19
234 XO. 15 bits of FI fit into bits 11 to 25,
235 the top bit FI0 (MSB0 numbered 0) makes 16.
238 fp32 = bf16 || [0]*16
239 FRT = Single_to_Double(fp32)
241 ## FPR to GPR conversions
243 <div id="fpr-to-gpr-conversion-mode"></div>
247 | 0-5 | 6-10 | 11-15 | 16-25 | 26-30 | 31 |
248 |--------|------|--------|-------|-------|----|
249 | Major | RT | //Mode | FRA | XO | Rc |
250 | Major | FRT | //Mode | RA | XO | Rc |
254 | Mode | `rounding_mode` | Semantics |
255 |------|-----------------|----------------------------------|
256 | 000 | from `FPSCR` | [OpenPower semantics] |
257 | 001 | Truncate | [OpenPower semantics] |
258 | 010 | from `FPSCR` | [Rust semantics] |
259 | 011 | Truncate | [Rust semantics] |
260 | 100 | from `FPSCR` | [JavaScript semantics] |
261 | 101 | Truncate | [JavaScript semantics] |
262 | rest | -- | illegal instruction trap for now |
264 [OpenPower semantics]: #fp-to-int-openpower-conversion-semantics
265 [Rust semantics]: #fp-to-int-rust-conversion-semantics
266 [JavaScript semantics]: #fp-to-int-javascript-conversion-semantics
268 `fcvttgw RT, FRA, Mode`
270 Convert from 64-bit float to 32-bit signed integer, writing the result
271 to the GPR `RT`. Converts using [mode `Mode`]
273 `fcvttguw RT, FRA, Mode`
275 Convert from 64-bit float to 32-bit unsigned integer, writing the result
276 to the GPR `RT`. Converts using [mode `Mode`]
278 `fcvttgd RT, FRA, Mode`
280 Convert from 64-bit float to 64-bit signed integer, writing the result
281 to the GPR `RT`. Converts using [mode `Mode`]
283 `fcvttgud RT, FRA, Mode`
285 Convert from 64-bit float to 64-bit unsigned integer, writing the result
286 to the GPR `RT`. Converts using [mode `Mode`]
288 `fcvtstgw RT, FRA, Mode`
290 Convert from 32-bit float to 32-bit signed integer, writing the result
291 to the GPR `RT`. Converts using [mode `Mode`]
293 `fcvtstguw RT, FRA, Mode`
295 Convert from 32-bit float to 32-bit unsigned integer, writing the result
296 to the GPR `RT`. Converts using [mode `Mode`]
298 `fcvtstgd RT, FRA, Mode`
300 Convert from 32-bit float to 64-bit signed integer, writing the result
301 to the GPR `RT`. Converts using [mode `Mode`]
303 `fcvtstgud RT, FRA, Mode`
305 Convert from 32-bit float to 64-bit unsigned integer, writing the result
306 to the GPR `RT`. Converts using [mode `Mode`]
308 [mode `Mode`]: #fpr-to-gpr-conversion-mode
310 ## GPR to FPR conversions
312 All of the following GPR to FPR conversions use the rounding mode from `FPSCR`.
316 Convert from 32-bit signed integer in the GPR `RA` to 64-bit float in `FRT`.
320 Convert from 32-bit signed integer in the GPR `RA` to 32-bit float in `FRT`.
324 Convert from 32-bit unsigned integer in the GPR `RA` to 64-bit float in `FRT`.
328 Convert from 32-bit unsigned integer in the GPR `RA` to 32-bit float in `FRT`.
332 Convert from 64-bit signed integer in the GPR `RA` to 64-bit float in `FRT`.
336 Convert from 64-bit signed integer in the GPR `RA` to 32-bit float in `FRT`.
340 Convert from 64-bit unsigned integer in the GPR `RA` to 64-bit float in `FRT`.
344 Convert from 64-bit unsigned integer in the GPR `RA` to 32-bit float in `FRT`.
346 # FP to Integer Conversion Pseudo-code
350 | term | result type | definition |
351 |---------------------------|-------------|----------------------------------------------------------------------------------------------------|
352 | `fp` | -- | `f32` or `f64` (or other types from SimpleV) |
353 | `int` | -- | `u32`/`u64`/`i32`/`i64` (or other types from SimpleV) |
354 | `uint` | -- | the unsigned integer of the same bit-width as `int` |
355 | `int::BITS` | `int` | the bit-width of `int` |
356 | `int::MIN_VALUE` | `int` | the minimum value `int` can store (`0` if unsigned, `-2^(int::BITS-1)` if signed) |
357 | `int::MAX_VALUE` | `int` | the maximum value `int` can store (`2^int::BITS - 1` if unsigned, `2^(int::BITS-1) - 1` if signed) |
358 | `int::VALUE_COUNT` | Integer | the number of different values `int` can store (`2^int::BITS`). too big to fit in `int`. |
359 | `rint(fp, rounding_mode)` | `fp` | rounds the floating-point value `fp` to an integer according to rounding mode `rounding_mode` |
361 <div id="fp-to-int-openpower-conversion-semantics"></div>
362 OpenPower conversion semantics (section A.2 page 999 (page 1023) of OpenPower ISA v3.1):
365 def fp_to_int_open_power<fp, int>(v: fp) -> int:
367 return int::MIN_VALUE
368 if v >= int::MAX_VALUE:
369 return int::MAX_VALUE
370 if v <= int::MIN_VALUE:
371 return int::MIN_VALUE
372 return (int)rint(v, rounding_mode)
375 <div id="fp-to-int-rust-conversion-semantics"></div>
376 Rust [conversion semantics](https://doc.rust-lang.org/reference/expressions/operator-expr.html#semantics) (with adjustment to add non-truncate rounding modes):
379 def fp_to_int_rust<fp, int>(v: fp) -> int:
382 if v >= int::MAX_VALUE:
383 return int::MAX_VALUE
384 if v <= int::MIN_VALUE:
385 return int::MIN_VALUE
386 return (int)rint(v, rounding_mode)
389 <div id="fp-to-int-javascript-conversion-semantics"></div>
390 JavaScript [conversion semantics](https://262.ecma-international.org/11.0/#sec-toint32) (with adjustment to add non-truncate rounding modes):
393 def fp_to_int_java_script<fp, int>(v: fp) -> int:
394 if v is NaN or infinite:
396 v = rint(v, rounding_mode)
397 v = v mod int::VALUE_COUNT # 2^32 for i32, 2^64 for i64, result is non-negative
402 # Equivalent OpenPower ISA v3.0 Assembly Language for FP -> Integer Conversion Modes
404 Moved to [[int_fp_mv/appendix]]