1 | //===--- arm_neon_incl.td - ARM NEON compiler interface ------------------------===// |
2 | // |
3 | // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. |
4 | // See https://llvm.org/LICENSE.txt for license information. |
5 | // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception |
6 | // |
7 | //===----------------------------------------------------------------------===// |
8 | // |
9 | // This file defines data structures shared by arm_neon.td and arm_fp16.td. |
10 | // It constains base operation classes, operations, instructions, instruction |
11 | // modifiers, etc. |
12 | // |
13 | //===----------------------------------------------------------------------===// |
14 | // |
15 | // Each intrinsic is a subclass of the Inst class. An intrinsic can either |
16 | // generate a __builtin_* call or it can expand to a set of generic operations. |
17 | // |
18 | // The operations are subclasses of Operation providing a list of DAGs, the |
19 | // last of which is the return value. The available DAG nodes are documented |
20 | // below. |
21 | // |
22 | //===----------------------------------------------------------------------===// |
23 | |
24 | // The base Operation class. All operations must subclass this. |
25 | class Operation<list<dag> ops=[]> { |
26 | list<dag> Ops = ops; |
27 | bit Unavailable = 0; |
28 | } |
29 | // An operation that only contains a single DAG. |
30 | class Op<dag op> : Operation<[op]>; |
31 | // A shorter version of Operation - takes a list of DAGs. The last of these will |
32 | // be the return value. |
33 | class LOp<list<dag> ops> : Operation<ops>; |
34 | |
35 | // These defs and classes are used internally to implement the SetTheory |
36 | // expansion and should be ignored. |
37 | foreach Index = 0-63 in |
38 | def sv##Index; |
39 | class MaskExpand; |
40 | |
41 | //===----------------------------------------------------------------------===// |
42 | // Available operations |
43 | //===----------------------------------------------------------------------===// |
44 | |
45 | // DAG arguments can either be operations (documented below) or variables. |
46 | // Variables are prefixed with '$'. There are variables for each input argument, |
47 | // with the name $pN, where N starts at zero. So the zero'th argument will be |
48 | // $p0, the first $p1 etc. |
49 | |
50 | // op - Binary or unary operator, depending on the number of arguments. The |
51 | // operator itself is just treated as a raw string and is not checked. |
52 | // example: (op "+", $p0, $p1) -> "__p0 + __p1". |
53 | // (op "-", $p0) -> "-__p0" |
54 | def op; |
55 | // call - Invoke another intrinsic. The input types are type checked and |
56 | // disambiguated. If there is no intrinsic defined that takes |
57 | // the given types (or if there is a type ambiguity) an error is |
58 | // generated at tblgen time. The name of the intrinsic is the raw |
59 | // name as given to the Inst class (not mangled). |
60 | // example: (call "vget_high", $p0) -> "vgetq_high_s16(__p0)" |
61 | // (assuming $p0 has type int16x8_t). |
62 | def call; |
63 | // cast - Perform a cast to a different type. This gets emitted as a static |
64 | // C-style cast. For a pure reinterpret cast (T x = *(T*)&y), use |
65 | // "bitcast". |
66 | // |
67 | // The syntax is (cast MOD* VAL). The last argument is the value to |
68 | // cast, preceded by a sequence of type modifiers. The target type |
69 | // starts off as the type of VAL, and is modified by MOD in sequence. |
70 | // The available modifiers are: |
71 | // - $X - Take the type of parameter/variable X. For example: |
72 | // (cast $p0, $p1) would cast $p1 to the type of $p0. |
73 | // - "R" - The type of the return type. |
74 | // - A typedef string - A NEON or stdint.h type that is then parsed. |
75 | // for example: (cast "uint32x4_t", $p0). |
76 | // - "U" - Make the type unsigned. |
77 | // - "S" - Make the type signed. |
78 | // - "H" - Halve the number of lanes in the type. |
79 | // - "D" - Double the number of lanes in the type. |
80 | // - "8" - Convert type to an equivalent vector of 8-bit signed |
81 | // integers. |
82 | // example: (cast "R", "U", $p0) -> "(uint32x4_t)__p0" (assuming the return |
83 | // value is of type "int32x4_t". |
84 | // (cast $p0, "D", "8", $p1) -> "(int8x16_t)__p1" (assuming __p0 |
85 | // has type float64x1_t or any other vector type of 64 bits). |
86 | // (cast "int32_t", $p2) -> "(int32_t)__p2" |
87 | def cast; |
88 | // bitcast - Same as "cast", except a reinterpret-cast is produced: |
89 | // (bitcast "T", $p0) -> "*(T*)&__p0". |
90 | // The VAL argument is saved to a temporary so it can be used |
91 | // as an l-value. |
92 | def bitcast; |
93 | // dup - Take a scalar argument and create a vector by duplicating it into |
94 | // all lanes. The type of the vector is the base type of the intrinsic. |
95 | // example: (dup $p1) -> "(uint32x2_t) {__p1, __p1}" (assuming the base type |
96 | // is uint32x2_t). |
97 | def dup; |
98 | // dup_typed - Take a vector and a scalar argument, and create a new vector of |
99 | // the same type by duplicating the scalar value into all lanes. |
100 | // example: (dup_typed $p1, $p2) -> "(float16x4_t) {__p2, __p2, __p2, __p2}" |
101 | // (assuming __p1 is float16x4_t, and __p2 is a compatible scalar). |
102 | def dup_typed; |
103 | // splat - Take a vector and a lane index, and return a vector of the same type |
104 | // containing repeated instances of the source vector at the lane index. |
105 | // example: (splat $p0, $p1) -> |
106 | // "__builtin_shufflevector(__p0, __p0, __p1, __p1, __p1, __p1)" |
107 | // (assuming __p0 has four elements). |
108 | def splat; |
109 | // save_temp - Create a temporary (local) variable. The variable takes a name |
110 | // based on the zero'th parameter and can be referenced using |
111 | // using that name in subsequent DAGs in the same |
112 | // operation. The scope of a temp is the operation. If a variable |
113 | // with the given name already exists, an error will be given at |
114 | // tblgen time. |
115 | // example: [(save_temp $var, (call "foo", $p0)), |
116 | // (op "+", $var, $p1)] -> |
117 | // "int32x2_t __var = foo(__p0); return __var + __p1;" |
118 | def save_temp; |
119 | // name_replace - Return the name of the current intrinsic with the first |
120 | // argument replaced by the second argument. Raises an error if |
121 | // the first argument does not exist in the intrinsic name. |
122 | // example: (call (name_replace "_high_", "_"), $p0) (to call the non-high |
123 | // version of this intrinsic). |
124 | def name_replace; |
125 | // literal - Create a literal piece of code. The code is treated as a raw |
126 | // string, and must be given a type. The type is a stdint.h or |
127 | // NEON intrinsic type as given to (cast). |
128 | // example: (literal "int32_t", "0") |
129 | def literal; |
130 | // shuffle - Create a vector shuffle. The syntax is (shuffle ARG0, ARG1, MASK). |
131 | // The MASK argument is a set of elements. The elements are generated |
132 | // from the two special defs "mask0" and "mask1". "mask0" expands to |
133 | // the lane indices in sequence for ARG0, and "mask1" expands to |
134 | // the lane indices in sequence for ARG1. They can be used as-is, e.g. |
135 | // |
136 | // (shuffle $p0, $p1, mask0) -> $p0 |
137 | // (shuffle $p0, $p1, mask1) -> $p1 |
138 | // |
139 | // or, more usefully, they can be manipulated using the SetTheory |
140 | // operators plus some extra operators defined in the NEON emitter. |
141 | // The operators are described below. |
142 | // example: (shuffle $p0, $p1, (add (highhalf mask0), (highhalf mask1))) -> |
143 | // A concatenation of the high halves of the input vectors. |
144 | def shuffle; |
145 | |
146 | // add, interleave, decimate: These set operators are vanilla SetTheory |
147 | // operators and take their normal definition. |
148 | def add; |
149 | def interleave; |
150 | def decimate; |
151 | // rotl - Rotate set left by a number of elements. |
152 | // example: (rotl mask0, 3) -> [3, 4, 5, 6, 0, 1, 2] |
153 | def rotl; |
154 | // rotl - Rotate set right by a number of elements. |
155 | // example: (rotr mask0, 3) -> [4, 5, 6, 0, 1, 2, 3] |
156 | def rotr; |
157 | // highhalf - Take only the high half of the input. |
158 | // example: (highhalf mask0) -> [4, 5, 6, 7] (assuming mask0 had 8 elements) |
159 | def highhalf; |
160 | // highhalf - Take only the low half of the input. |
161 | // example: (lowhalf mask0) -> [0, 1, 2, 3] (assuming mask0 had 8 elements) |
162 | def lowhalf; |
163 | // rev - Perform a variable-width reversal of the elements. The zero'th argument |
164 | // is a width in bits to reverse. The lanes this maps to is determined |
165 | // based on the element width of the underlying type. |
166 | // example: (rev 32, mask0) -> [3, 2, 1, 0, 7, 6, 5, 4] (if 8-bit elements) |
167 | // example: (rev 32, mask0) -> [1, 0, 3, 2] (if 16-bit elements) |
168 | def rev; |
169 | // mask0 - The initial sequence of lanes for shuffle ARG0 |
170 | def mask0 : MaskExpand; |
171 | // mask0 - The initial sequence of lanes for shuffle ARG1 |
172 | def mask1 : MaskExpand; |
173 | |
174 | def OP_NONE : Operation; |
175 | def OP_UNAVAILABLE : Operation { |
176 | let Unavailable = 1; |
177 | } |
178 | |
179 | //===----------------------------------------------------------------------===// |
180 | // Instruction definitions |
181 | //===----------------------------------------------------------------------===// |
182 | |
183 | // Every intrinsic subclasses "Inst". An intrinsic has a name, a prototype and |
184 | // a sequence of typespecs. |
185 | // |
186 | // The name is the base name of the intrinsic, for example "vget_lane". This is |
187 | // then mangled by the tblgen backend to add type information ("vget_lane_s16"). |
188 | // |
189 | // A typespec is a sequence of uppercase characters (modifiers) followed by one |
190 | // lowercase character. A typespec encodes a particular "base type" of the |
191 | // intrinsic. |
192 | // |
193 | // An example typespec is "Qs" - quad-size short - uint16x8_t. The available |
194 | // typespec codes are given below. |
195 | // |
196 | // The string given to an Inst class is a sequence of typespecs. The intrinsic |
197 | // is instantiated for every typespec in the sequence. For example "sdQsQd". |
198 | // |
199 | // The prototype is a string that defines the return type of the intrinsic |
200 | // and the type of each argument. The return type and every argument gets a |
201 | // "modifier" that can change in some way the "base type" of the intrinsic. |
202 | // |
203 | // The modifier 'd' means "default" and does not modify the base type in any |
204 | // way. The available modifiers are given below. |
205 | // |
206 | // Typespecs |
207 | // --------- |
208 | // c: char |
209 | // s: short |
210 | // i: int |
211 | // l: long |
212 | // k: 128-bit long |
213 | // f: float |
214 | // h: half-float |
215 | // d: double |
216 | // |
217 | // Typespec modifiers |
218 | // ------------------ |
219 | // S: scalar, only used for function mangling. |
220 | // U: unsigned |
221 | // Q: 128b |
222 | // H: 128b without mangling 'q' |
223 | // P: polynomial |
224 | // |
225 | // Prototype modifiers |
226 | // ------------------- |
227 | // prototype: return (arg, arg, ...) |
228 | // |
229 | // v: void |
230 | // t: best-fit integer (int/poly args) |
231 | // x: signed integer (int/float args) |
232 | // u: unsigned integer (int/float args) |
233 | // f: float (int args) |
234 | // F: double (int args) |
235 | // H: half (int args) |
236 | // 0: half (int args), ignore 'Q' size modifier. |
237 | // 1: half (int args), force 'Q' size modifier. |
238 | // d: default |
239 | // g: default, ignore 'Q' size modifier. |
240 | // j: default, force 'Q' size modifier. |
241 | // w: double width elements, same num elts |
242 | // n: double width elements, half num elts |
243 | // h: half width elements, double num elts |
244 | // q: half width elements, quad num elts |
245 | // e: half width elements, double num elts, unsigned |
246 | // m: half width elements, same num elts |
247 | // i: constant int |
248 | // l: constant uint64 |
249 | // s: scalar of element type |
250 | // z: scalar of half width element type, signed |
251 | // r: scalar of double width element type, signed |
252 | // a: scalar of element type (splat to vector type) |
253 | // b: scalar of unsigned integer/long type (int/float args) |
254 | // $: scalar of signed integer/long type (int/float args) |
255 | // y: scalar of float |
256 | // o: scalar of double |
257 | // k: default elt width, double num elts |
258 | // 2,3,4: array of default vectors |
259 | // B,C,D: array of default elts, force 'Q' size modifier. |
260 | // p: pointer type |
261 | // c: const pointer type |
262 | // 7: vector of 8-bit elements, ignore 'Q' size modifier |
263 | // 8: vector of 8-bit elements, same width as default type |
264 | // 9: vector of 8-bit elements, force 'Q' size modifier |
265 | |
266 | // Every intrinsic subclasses Inst. |
267 | class Inst <string n, string p, string t, Operation o> { |
268 | string Name = n; |
269 | string Prototype = p; |
270 | string Types = t; |
271 | string ArchGuard = ""; |
272 | |
273 | Operation Operation = o; |
274 | bit CartesianProductOfTypes = 0; |
275 | bit BigEndianSafe = 0; |
276 | bit isShift = 0; |
277 | bit isScalarShift = 0; |
278 | bit isScalarNarrowShift = 0; |
279 | bit isVCVT_N = 0; |
280 | // For immediate checks: the immediate will be assumed to specify the lane of |
281 | // a Q register. Only used for intrinsics which end up calling polymorphic |
282 | // builtins. |
283 | bit isLaneQ = 0; |
284 | |
285 | // Certain intrinsics have different names than their representative |
286 | // instructions. This field allows us to handle this correctly when we |
287 | // are generating tests. |
288 | string InstName = ""; |
289 | |
290 | // Certain intrinsics even though they are not a WOpInst or LOpInst, |
291 | // generate a WOpInst/LOpInst instruction (see below for definition |
292 | // of a WOpInst/LOpInst). For testing purposes we need to know |
293 | // this. Ex: vset_lane which outputs vmov instructions. |
294 | bit isHiddenWInst = 0; |
295 | bit isHiddenLInst = 0; |
296 | } |
297 | |
298 | // The following instruction classes are implemented via builtins. |
299 | // These declarations are used to generate Builtins.def: |
300 | // |
301 | // SInst: Instruction with signed/unsigned suffix (e.g., "s8", "u8", "p8") |
302 | // IInst: Instruction with generic integer suffix (e.g., "i8") |
303 | // WInst: Instruction with only bit size suffix (e.g., "8") |
304 | class SInst<string n, string p, string t> : Inst<n, p, t, OP_NONE> {} |
305 | class IInst<string n, string p, string t> : Inst<n, p, t, OP_NONE> {} |
306 | class WInst<string n, string p, string t> : Inst<n, p, t, OP_NONE> {} |
307 | |
308 | // The following instruction classes are implemented via operators |
309 | // instead of builtins. As such these declarations are only used for |
310 | // the purpose of generating tests. |
311 | // |
312 | // SOpInst: Instruction with signed/unsigned suffix (e.g., "s8", |
313 | // "u8", "p8"). |
314 | // IOpInst: Instruction with generic integer suffix (e.g., "i8"). |
315 | // WOpInst: Instruction with bit size only suffix (e.g., "8"). |
316 | // LOpInst: Logical instruction with no bit size suffix. |
317 | // NoTestOpInst: Intrinsic that has no corresponding instruction. |
318 | class SOpInst<string n, string p, string t, Operation o> : Inst<n, p, t, o> {} |
319 | class IOpInst<string n, string p, string t, Operation o> : Inst<n, p, t, o> {} |
320 | class WOpInst<string n, string p, string t, Operation o> : Inst<n, p, t, o> {} |
321 | class LOpInst<string n, string p, string t, Operation o> : Inst<n, p, t, o> {} |
322 | class NoTestOpInst<string n, string p, string t, Operation o> : Inst<n, p, t, o> {} |
323 | |