1 # DRAFT Scalar Transcendentals
5 *This proposal extends Power ISA scalar floating point operations to
6 add IEEE754 transcendental functions (pow, log etc) and trigonometric
7 functions (sin, cos etc). These functions are also 98% shared with the
8 Khronos Group OpenCL Extended Instruction Set.*
12 * Luke Kenneth Casson Leighton
18 * Luis Vitorio Cargnini
24 * <http://bugs.libre-soc.org/show_bug.cgi?id=127>
25 * <https://bugs.libre-soc.org/show_bug.cgi?id=923> under review
26 * <https://www.khronos.org/registry/spir-v/specs/unified1/OpenCL.ExtendedInstructionSet.100.html>
27 * [[power_trans_ops]] for opcode listing.
31 TODO: rename extension subsets -- we're not on RISC-V anymore.
33 * **Zftrans**: standard transcendentals (best suited to 3D)
34 * **ZftransExt**: extra functions (useful, not generally needed for 3D,
35 can be synthesised using Ztrans)
36 * **Ztrigpi**: trig. xxx-pi sinpi cospi tanpi
37 * **Ztrignpi**: trig non-xxx-pi sin cos tan
38 * **Zarctrigpi**: arc-trig. a-xxx-pi: atan2pi asinpi acospi
39 * **Zarctrignpi**: arc-trig. non-a-xxx-pi: atan2, asin, acos
40 * **Zfhyp**: hyperbolic/inverse-hyperbolic. sinh, cosh, tanh, asinh,
41 acosh, atanh (can be synthesised - see below)
42 * **ZftransAdv**: much more complex to implement in hardware
43 * **Zfrsqrt**: Reciprocal square-root.
45 Minimum recommended requirements for 3D: Zftrans, Ztrignpi,
46 Zarctrignpi, with Ztrigpi and Zarctrigpi as augmentations.
48 Minimum recommended requirements for Mobile-Embedded 3D:
49 Ztrignpi, Zftrans, with Ztrigpi as an augmentation.
51 The Platform Requirements for 3D are driven by cost competitive
52 factors and it is the Trademarked Vulkan Specification that provides
53 clear direction for 3D GPU markets, but nothing else (IEEE754).
54 Implementors must note that minimum
55 Compliance with the Third Party Vulkan Specification (for power-area competitive
56 reasons with other 3D GPU manufacturers) will not qualify for strict IEEE754 accuracy Compliance or vice-versa.
58 Implementors **must** make it clear which accuracy level is implemented and provide a switching mechanism and throw Illegal Instruction traps if fully compliant accuracy cannot be achieved.
59 It is also the Implementor's responsibility to comply with all Third Party Certification Marks and Trademarks (Vulkan, OpenCL). Nothing in this specification in any way implies that any Third Party Certification Mark Compliance is granted, nullified, altered or overridden by this document.
64 * Decision on accuracy, moved to [[zfpacc_proposal]]
65 <http://lists.libre-riscv.org/pipermail/libre-riscv-dev/2019-August/002355.html>
66 * Errors **MUST** be repeatable.
67 * How about four Platform Specifications? 3DUNIX, UNIX, 3DEmbedded and Embedded?
68 <http://lists.libre-riscv.org/pipermail/libre-riscv-dev/2019-August/002361.html>
69 Accuracy requirements for dual (triple) purpose implementations must
70 meet the higher standard.
71 * Reciprocal Square-root is in its own separate extension (Zfrsqrt) as
72 it is desirable on its own by other implementors. This to be evaluated.
74 # Requirements <a name="requirements"></a>
76 This proposal is designed to meet a wide range of extremely diverse
77 needs, allowing implementors from all of them to benefit from the tools
78 and hardware cost reductions associated with common standards adoption
79 in Power ISA (primarily IEEE754 and Vulkan).
81 **The use-cases are**:
84 * Numerical Computation
85 * (Potentially) A.I. / Machine-learning (1)
87 (1) although approximations suffice in this field, making it more likely
88 to use a custom extension. High-end ML would inherently definitely
91 **The power and die-area requirements vary from**:
93 * Ultra-low-power (smartwatches where GPU power budgets are in milliwatts)
94 * Mobile-Embedded (good performance with high efficiency for battery life)
96 * Server / HPC / Supercomputing
98 **The software requirements are**:
100 * Full public integration into GNU math libraries (libm)
101 * Full public integration into well-known Numerical Computation systems (numpy)
102 * Full public integration into upstream GNU and LLVM Compiler toolchains
103 * Full public integration into Khronos OpenCL SPIR-V compatible Compilers
104 seeking public Certification and Endorsement from the Khronos Group
105 under their Trademarked Certification Programme.
107 # Proposed Opcodes vs Khronos OpenCL vs IEEE754-2019<a name="khronos_equiv"></a>
109 This list shows the (direct) equivalence between proposed opcodes,
110 their Khronos OpenCL equivalents, and their IEEE754-2019 equivalents.
111 98% of the opcodes in this proposal that are in the IEEE754-2019 standard
112 are present in the Khronos Extended Instruction Set.
115 <https://www.khronos.org/registry/spir-v/specs/unified1/OpenCL.ExtendedInstructionSet.100.html>
116 and <https://ieeexplore.ieee.org/document/8766229>
118 * Special FP16 opcodes are *not* being proposed, except by indirect / inherent
119 use of elwidth overrides that is already present in the SVP64 Specification.
120 * "Native" opcodes are *not* being proposed: implementors will be expected
121 to use the (equivalent) proposed opcode covering the same function.
122 * "Fast" opcodes are *not* being proposed, because the Khronos Specification
123 fast\_length, fast\_normalise and fast\_distance OpenCL opcodes require
124 vectors (or can be done as scalar operations using other Power ISA
127 The OpenCL FP32 opcodes are **direct** equivalents to the proposed opcodes.
128 Deviation from conformance with the Khronos Specification - including the
129 Khronos Specification accuracy requirements - is not an option, as it
130 results in non-compliance, and the vendor may not use the Trademarked words
131 "Vulkan" etc. in conjunction with their product.
133 IEEE754-2019 Table 9.1 lists "additional mathematical operations".
134 Interestingly the only functions missing when compared to OpenCL are
135 compound, exp2m1, exp10m1, log2p1, log10p1, pown (integer power) and powr.
137 |opcode |OpenCL FP32|OpenCL FP16|OpenCL native|IEEE754 |Power ISA |
138 |------------|-----------|-----------|-------------|-------------- |------------------------|
139 |fsin |sin |half\_sin |native\_sin |sin |NONE |
140 |fcos |cos |half\_cos |native\_cos |cos |NONE |
141 |ftan |tan |half\_tan |native\_tan |tan |NONE |
142 |NONE (1) |sincos |NONE |NONE |NONE |NONE |
143 |fasin |asin |NONE |NONE |asin |NONE |
144 |facos |acos |NONE |NONE |acos |NONE |
145 |fatan |atan |NONE |NONE |atan |NONE |
146 |fsinpi |sinpi |NONE |NONE |sinPi |NONE |
147 |fcospi |cospi |NONE |NONE |cosPi |NONE |
148 |ftanpi |tanpi |NONE |NONE |tanPi |NONE |
149 |fasinpi |asinpi |NONE |NONE |asinPi |NONE |
150 |facospi |acospi |NONE |NONE |acosPi |NONE |
151 |fatanpi |atanpi |NONE |NONE |atanPi |NONE |
152 |fsinh |sinh |NONE |NONE |sinh |NONE |
153 |fcosh |cosh |NONE |NONE |cosh |NONE |
154 |ftanh |tanh |NONE |NONE |tanh |NONE |
155 |fasinh |asinh |NONE |NONE |asinh |NONE |
156 |facosh |acosh |NONE |NONE |acosh |NONE |
157 |fatanh |atanh |NONE |NONE |atanh |NONE |
158 |fatan2 |atan2 |NONE |NONE |atan2 |NONE |
159 |fatan2pi |atan2pi |NONE |NONE |atan2pi |NONE |
160 |frsqrt |rsqrt |half\_rsqrt|native\_rsqrt|rSqrt |fsqrte, fsqrtes (4) |
161 |fcbrt |cbrt |NONE |NONE |NONE (2) |NONE |
162 |fexp2 |exp2 |half\_exp2 |native\_exp2 |exp2 |NONE |
163 |flog2 |log2 |half\_log2 |native\_log2 |log2 |NONE |
164 |fexpm1 |expm1 |NONE |NONE |expm1 |NONE |
165 |flog1p |log1p |NONE |NONE |logp1 |NONE |
166 |fexp |exp |half\_exp |native\_exp |exp |NONE |
167 |flog |log |half\_log |native\_log |log |NONE |
168 |fexp10 |exp10 |half\_exp10|native\_exp10|exp10 |NONE |
169 |flog10 |log10 |half\_log10|native\_log10|log10 |NONE |
170 |fpow |pow |NONE |NONE |pow |NONE |
171 |fpown |pown |NONE |NONE |pown |NONE |
172 |fpowr |powr |half\_powr |native\_powr |powr |NONE |
173 |frootn |rootn |NONE |NONE |rootn |NONE |
174 |fhypot |hypot |NONE |NONE |hypot |NONE |
175 |frecip |NONE |half\_recip|native\_recip|NONE (3) |fre, fres (4) |
176 |NONE |NONE |NONE |NONE |compound |NONE |
177 |fexp2m1 |NONE |NONE |NONE |exp2m1 |NONE |
178 |fexp10m1 |NONE |NONE |NONE |exp10m1 |NONE |
179 |flog2p1 |NONE |NONE |NONE |log2p1 |NONE |
180 |flog10p1 |NONE |NONE |NONE |log10p1 |NONE |
182 Note (1) fsincos is macro-op fused (see below).
184 Note (2) synthesised in IEEE754-2019 as "rootn(x, 3)"
186 Note (3) synthesised in IEEE754-2019 using "1.0 / x"
188 Note (4) these are estimate opcodes that help accelerate
191 ## List of 2-arg opcodes
193 | opcode | Description | pseudocode | Extension |
194 | ------ | ---------------- | ---------------- | ----------- |
195 | fatan2 | atan2 arc tangent | FRT = atan2(FRB, FRA) | Zarctrignpi |
196 | fatan2pi | atan2 arc tangent / pi | FRT = atan2(FRB, FRA) / pi | Zarctrigpi |
197 | fpow | x power of y | FRT = pow(FRA, FRB) | ZftransAdv |
198 | fpown | x power of n (n int) | FRT = pow(FRA, RB) | ZftransAdv |
199 | fpowr | x power of y (x +ve) | FRT = exp(FRA log(FRB)) | ZftransAdv |
200 | frootn | x power 1/n (n integer) | FRT = pow(FRA, 1/RB) | ZftransAdv |
201 | fhypot | hypotenuse | FRT = sqrt(FRA^2 + FRB^2) | ZftransAdv |
203 ## List of 1-arg transcendental opcodes
205 | opcode | Description | pseudocode | Extension |
206 | ------ | ---------------- | ---------------- | ---------- |
207 | frsqrt | Reciprocal Square-root | FRT = sqrt(FRA) | Zfrsqrt |
208 | fcbrt | Cube Root | FRT = pow(FRA, 1.0 / 3) | ZftransAdv |
209 | frecip | Reciprocal | FRT = 1.0 / FRA | Zftrans |
210 | fexp2m1 | power-2 minus 1 | FRT = pow(2, FRA) - 1.0 | ZftransExt |
211 | flog2p1 | log2 plus 1 | FRT = log(2, 1 + FRA) | ZftransExt |
212 | fexp2 | power-of-2 | FRT = pow(2, FRA) | Zftrans |
213 | flog2 | log2 | FRT = log(2. FRA) | Zftrans |
214 | fexpm1 | exponential minus 1 | FRT = pow(e, FRA) - 1.0 | ZftransExt |
215 | flog1p | log plus 1 | FRT = log(e, 1 + FRA) | ZftransExt |
216 | fexp | exponential | FRT = pow(e, FRA) | ZftransExt |
217 | flog | natural log (base e) | FRT = log(e, FRA) | ZftransExt |
218 | fexp10m1 | power-10 minus 1 | FRT = pow(10, FRA) - 1.0 | ZftransExt |
219 | flog10p1 | log10 plus 1 | FRT = log(10, 1 + FRA) | ZftransExt |
220 | fexp10 | power-of-10 | FRT = pow(10, FRA) | ZftransExt |
221 | flog10 | log base 10 | FRT = log(10, FRA) | ZftransExt |
223 ## List of 1-arg trigonometric opcodes
225 | opcode | Description | pseudocode | Extension |
226 | -------- | ------------------------ | ------------------------ | ----------- |
227 | fsin | sin (radians) | FRT = sin(FRA) | Ztrignpi |
228 | fcos | cos (radians) | FRT = cos(FRA) | Ztrignpi |
229 | ftan | tan (radians) | FRT = tan(FRA) | Ztrignpi |
230 | fasin | arcsin (radians) | FRT = asin(FRA) | Zarctrignpi |
231 | facos | arccos (radians) | FRT = acos(FRA) | Zarctrignpi |
232 | fatan | arctan (radians) | FRT = atan(FRA) | Zarctrignpi |
233 | fsinpi | sin times pi | FRT = sin(pi * FRA) | Ztrigpi |
234 | fcospi | cos times pi | FRT = cos(pi * FRA) | Ztrigpi |
235 | ftanpi | tan times pi | FRT = tan(pi * FRA) | Ztrigpi |
236 | fasinpi | arcsin / pi | FRT = asin(FRA) / pi | Zarctrigpi |
237 | facospi | arccos / pi | FRT = acos(FRA) / pi | Zarctrigpi |
238 | fatanpi | arctan / pi | FRT = atan(FRA) / pi | Zarctrigpi |
239 | fsinh | hyperbolic sin (radians) | FRT = sinh(FRA) | Zfhyp |
240 | fcosh | hyperbolic cos (radians) | FRT = cosh(FRA) | Zfhyp |
241 | ftanh | hyperbolic tan (radians) | FRT = tanh(FRA) | Zfhyp |
242 | fasinh | inverse hyperbolic sin | FRT = asinh(FRA) | Zfhyp |
243 | facosh | inverse hyperbolic cos | FRT = acosh(FRA) | Zfhyp |
244 | fatanh | inverse hyperbolic tan | FRT = atanh(FRA) | Zfhyp |
246 [[!inline pages="openpower/power_trans_ops" raw=yes ]]
250 The full set is based on the Khronos OpenCL opcodes. If implemented
251 entirely it would be too much for both Embedded and also 3D.
253 The subsets are organised by hardware complexity, need (3D, HPC), however
254 due to synthesis producing inaccurate results at the range limits,
255 the less common subsets are still required for IEEE754 HPC.
257 MALI Midgard, an embedded / mobile 3D GPU, for example only has the
261 F0 - frcp (reciprocal)
262 F2 - frsqrt (inverse square root, 1/sqrt(x))
263 F3 - fsqrt (square root)
270 These in FP32 and FP16 only: no FP64 hardware, at all.
272 Vivante Embedded/Mobile 3D (etnaviv
273 <https://github.com/laanwj/etna_viv/blob/master/rnndb/isa.xml>)
274 only has the following:
282 It also has fast variants of some of these, as a CSR Mode.
284 AMD's R600 GPU (R600\_Instruction\_Set\_Architecture.pdf) and the
285 RDNA ISA (RDNA\_Shader\_ISA\_5August2019.pdf, Table 22, Section 6.3) have:
295 AMD RDNA has F16 and F32 variants of all the above, and also has F64
296 variants of SQRT, RSQRT and RECIP. It is interesting that even the
297 modern high-end AMD GPU does not have TAN or ATAN, where MALI Midgard
300 Also a general point, that customised optimised hardware targetting
301 FP32 3D with less accuracy simply can neither be used for IEEE754 nor
302 for FP64 (except as a starting point for hardware or software driven
303 Newton Raphson or other iterative method).
305 Also in cost/area sensitive applications even the extra ROM lookup tables
306 for certain algorithms may be too costly.
308 These wildly differing and incompatible driving factors lead to the
309 subset subdivisions, below.
311 ## Transcendental Subsets
315 LOG2 EXP2 RECIP RSQRT
317 Zftrans contains the minimum standard transcendentals best suited to
318 3D. They are also the minimum subset for synthesising log10, exp10,
319 exp1m, log1p, the hyperbolic trigonometric functions sinh and so on.
321 They are therefore considered "base" (essential) transcendentals.
325 LOG, EXP, EXP10, LOG10, LOGP1, EXP1M
327 These are extra transcendental functions that are useful, not generally
328 needed for 3D, however for Numerical Computation they may be useful.
330 Although they can be synthesised using Ztrans (LOG2 multiplied
331 by a constant), there is both a performance penalty as well as an
332 accuracy penalty towards the limits, which for IEEE754 compliance is
333 unacceptable. In particular, LOG(1+FRA) in hardware may give much better
334 accuracy at the lower end (very small FRA) than LOG(FRA).
336 Their forced inclusion would be inappropriate as it would penalise
337 embedded systems with tight power and area budgets. However if they
338 were completely excluded the HPC applications would be penalised on
339 performance and accuracy.
341 Therefore they are their own subset extension.
345 SINH, COSH, TANH, ASINH, ACOSH, ATANH
347 These are the hyperbolic/inverse-hyperbolic functions. Their use in 3D
350 They can all be synthesised using LOG, SQRT and so on, so depend
351 on Zftrans. However, once again, at the limits of the range, IEEE754
352 compliance becomes impossible, and thus a hardware implementation may
355 HPC and high-end GPUs are likely markets for these.
359 CBRT, POW, POWN, POWR, ROOTN
361 These are simply much more complex to implement in hardware, and typically
362 will only be put into HPC applications.
364 * **Zfrsqrt**: Reciprocal square-root.
366 ## Trigonometric subsets
368 ### Ztrigpi vs Ztrignpi
370 * **Ztrigpi**: SINPI COSPI TANPI
371 * **Ztrignpi**: SIN COS TAN
373 Ztrignpi are the basic trigonometric functions through which all others
374 could be synthesised, and they are typically the base trigonometrics
375 provided by GPUs for 3D, warranting their own subset.
377 (programmerjake: actually, all other GPU ISAs mentioned in this document have sinpi/cospi or equivalent, and often not sin/cos, because sinpi/cospi are actually *waay* easier to implement because range reduction is simply a bitwise mask, whereas for sin/cos range reduction is a full division by pi)
379 In the case of the Ztrigpi subset, these are commonly used in for loops
380 with a power of two number of subdivisions, and the cost of multiplying
381 by PI inside each loop (or cumulative addition, resulting in cumulative
382 errors) is not acceptable.
384 In for example CORDIC the multiplication by PI may be moved outside of
385 the hardware algorithm as a loop invariant, with no power or area penalty.
387 Again, therefore, if SINPI (etc.) were excluded, programmers would be
388 penalised by being forced to divide by PI in some circumstances. Likewise
389 if SIN were excluded, programmers would be penaslised by being forced
390 to *multiply* by PI in some circumstances.
392 Thus again, a slightly different application of the same general argument
393 applies to give Ztrignpi and Ztrigpi as subsets. 3D GPUs will almost
394 certainly provide both.
396 ### Zarctrigpi and Zarctrignpi
398 * **Zarctrigpi**: ATAN2PI ASINPI ACOSPI
399 * **Zarctrignpi**: ATAN2 ACOS ASIN
401 These are extra trigonometric functions that are useful in some
402 applications, but even for 3D GPUs, particularly embedded and mobile class
403 GPUs, they are not so common and so are typically synthesised, there.
405 Although they can be synthesised using Ztrigpi and Ztrignpi, there is,
406 once again, both a performance penalty as well as an accuracy penalty
407 towards the limits, which for IEEE754 compliance is unacceptable, yet
408 is acceptable for 3D.
410 Therefore they are their own subset extensions.
412 # Synthesis, Pseudo-code ops and macro-ops
414 The pseudo-ops are best left up to the compiler rather than being actual
415 pseudo-ops, by allocating one scalar FP register for use as a constant
416 (loop invariant) set to "1.0" at the beginning of a function or other
419 * fsincos - fused macro-op between fsin and fcos (issued in that order).
420 * fsincospi - fused macro-op between fsinpi and fcospi (issued in that order).
422 fatanpi example pseudo-code:
424 fmvis ft0, 0x3F800 // upper bits of f32 1.0 (BF16)
425 fatan2pis FRT, FRA, ft0
427 Hyperbolic function example (obviates need for Zfhyp except for
428 high-performance or correctly-rounding):
430 ASINH( x ) = ln( x + SQRT(x**2+1))
432 # Evaluation and commentary
434 Moved to [[discussion]]