[mlir] Add Acos, Asin, Atan, Sinh, Cosh, Pow to SPIRVGLSLOps

[mravishankar]

Thanks! Can we also add some tests for the operation here and serialization roundtrip tests here. This is in keeping with the procedure to add new op here

[LiyangLingIntel]

In D86929#2250080, @mravishankar wrote:

Thanks! Can we also add some tests for the operation here and serialization roundtrip tests here. This is in keeping with the procedure to add new op here

Sure, we are working on it.

[LiyangLingIntel]

[mlir][spirv] Add tests for SPIRVGLSLOps

[LiyangLingIntel]

Hi!
It's glad to see this patch is accepted. As a first-time contributor, it seems I do not have the commit access to this project. Can you help me commit this change?

[antiagainst]

Done. Thanks for the contribution! :)

[bondhugula]

mlir/include/mlir/Dialect/SPIRV/SPIRVGLSLOps.td

268–278

A side question: These ops seem to be introducing a whole lot of duplication. Has SPIRV just considered using std dialect operations where they have the same semantics and are on the same operand types? sine, arcsine, tan, pow, exp, .. are all mathematically the same irrespective of which dialect they live in. If there are slight differences in semantics, a new op could be introduced briefly documenting the deviation. What are the benefits on creating <dialect_name>.op aliases? If there are no type conversions needed, why shouldn't/can't we mix std dialect ops?

mlir/include/mlir/Dialect/SPIRV/SPIRVGLSLOps.td

let description = [{
     %2 = spv.GLSL.Tan %0 : f32
     %3 = spv.GLSL.Tan %1 : vector<3xf16>
     ```
   }];
 }
 
 // -----
 
+def SPV_GLSLAsinOp : SPV_GLSLUnaryArithmeticOp<"Asin", 16, SPV_Float16or32> {
+  let summary = "Arc Sine of operand in radians";
+
+  let description = [{
+    The standard trigonometric arc sine of x radians.
+
+    Result is an angle, in radians, whose sine is x. The range of result values
+    is [-π / 2, π / 2]. Result is undefined if abs x > 1.
+
+    The operand x must be a scalar or vector whose component type is 16-bit or
+    32-bit floating-point.
+
+    Result Type and the type of x must be the same type. Results are computed
+    per component.
+    <!-- End of AutoGen section -->
+    ```
+    restricted-float-scalar-type ::=  `f16` | `f32`
+    restricted-float-scalar-vector-type ::=
+      restricted-float-scalar-type |
+      `vector<` integer-literal `x` restricted-float-scalar-type `>`
+    asin-op ::= ssa-id `=` `spv.GLSL.Asin` ssa-use `:`
+                restricted-float-scalar-vector-type
+    ```
+    #### Example:
+
+    ```mlir
+    %2 = spv.GLSL.Asin %0 : f32
+    %3 = spv.GLSL.Asin %1 : vector<3xf16>
+    ```
+  }];
+}
+
+// -----
+
+def SPV_GLSLAcosOp : SPV_GLSLUnaryArithmeticOp<"Acos", 17, SPV_Float16or32> {
+  let summary = "Arc Cosine of operand in radians";
+
+  let description = [{
+    The standard trigonometric arc cosine of x radians.
+
+    Result is an angle, in radians, whose cosine is x. The range of result
+    values is [0, π]. Result is undefined if abs x > 1.
+
+    The operand x must be a scalar or vector whose component type is 16-bit or
+    32-bit floating-point.
+
+    Result Type and the type of x must be the same type. Results are computed
+    per component.
+    <!-- End of AutoGen section -->
+    ```
+    restricted-float-scalar-type ::=  `f16` | `f32`
+    restricted-float-scalar-vector-type ::=
+      restricted-float-scalar-type |
+      `vector<` integer-literal `x` restricted-float-scalar-type `>`
+    acos-op ::= ssa-id `=` `spv.GLSL.Acos` ssa-use `:`
+                restricted-float-scalar-vector-type
+    ```
+    #### Example:
+
+    ```mlir
+    %2 = spv.GLSL.Acos %0 : f32
+    %3 = spv.GLSL.Acos %1 : vector<3xf16>
+    ```
+  }];
+}
+
+// -----
+
+def SPV_GLSLAtanOp : SPV_GLSLUnaryArithmeticOp<"Atan", 18, SPV_Float16or32> {
+  let summary = "Arc Tangent of operand in radians";
+
+  let description = [{
+    The standard trigonometric arc tangent of x radians.
+
+    Result is an angle, in radians, whose tangent is y_over_x. The range of
+    result values is [-π / 2, π / 2].
+
+    The operand x must be a scalar or vector whose component type is 16-bit or
+    32-bit floating-point.
+
+    Result Type and the type of x must be the same type. Results are computed
+    per component.
+    <!-- End of AutoGen section -->
+    ```
+    restricted-float-scalar-type ::=  `f16` | `f32`
+    restricted-float-scalar-vector-type ::=
+      restricted-float-scalar-type |
+      `vector<` integer-literal `x` restricted-float-scalar-type `>`
+    atan-op ::= ssa-id `=` `spv.GLSL.Atan` ssa-use `:`
+                restricted-float-scalar-vector-type
+    ```
+    #### Example:
+
+    ```mlir
+    %2 = spv.GLSL.Atan %0 : f32
+    %3 = spv.GLSL.Atan %1 : vector<3xf16>
+    ```
+  }];
+}
+
+// -----
+
 def SPV_GLSLExpOp : SPV_GLSLUnaryArithmeticOp<"Exp", 27, SPV_Float16or32> {
   let summary = "Exponentiation of Operand 1";
 
   let description = [{
     Result is the natural exponentiation of x; e^x.
 
     The operand x must be a scalar or vector whose component type is
     16-bit or 32-bit floating-point.
let description = [{
     %2 = spv.GLSL.SMin %0, %1 : i32
     %3 = spv.GLSL.SMin %0, %1 : vector<3xi16>
     ```
   }];
 }
 
 // -----
 
+def SPV_GLSLPowOp : SPV_GLSLBinaryArithmeticOp<"Pow", 26, SPV_Float16or32> {
+  let summary = "Return x raised to the y power of two operands";
+
+  let description = [{
+    Result is x raised to the y power; x^y.
+
+    Result is undefined if x = 0 and y ≤ 0.
+
+    The operand x and y must be a scalar or vector whose component type is
+    16-bit or 32-bit floating-point.
+
+    Result Type and the type of all operands must be the same type. Results are
+    computed per component.
+
+    <!-- End of AutoGen section -->
+    ```
+    restricted-float-scalar-type ::=  `f16` | `f32`
+    restricted-float-scalar-vector-type ::=
+      restricted-float-scalar-type |
+      `vector<` integer-literal `x` restricted-float-scalar-type `>`
+    pow-op ::= ssa-id `=` `spv.GLSL.Pow` ssa-use `:`
+               restricted-float-scalar-vector-type
+    ```
+    #### Example:
+
+    ```mlir
+    %2 = spv.GLSL.Pow %0, %1 : f32
+    %3 = spv.GLSL.Pow %0, %1 : vector<3xf16>
+    ```
+  }];
+}
+
+// -----
+
 def SPV_GLSLFSignOp : SPV_GLSLUnaryArithmeticOp<"FSign", 6, SPV_Float> {
   let summary = "Returns the sign of the operand";
 
   let description = [{
     Result is 1.0 if x > 0, 0.0 if x = 0, or -1.0 if x < 0.
 
     The operand x must be a scalar or vector whose component type is
     floating-point.
let description = [{
     %2 = spv.GLSL.Sqrt %0 : f32
     %3 = spv.GLSL.Sqrt %1 : vector<3xf16>
     ```
   }];
 }
 
 // -----
 
+def SPV_GLSLSinhOp : SPV_GLSLUnaryArithmeticOp<"Sinh", 19, SPV_Float16or32> {
+  let summary = "Hyperbolic sine of operand in radians";
+
+  let description = [{
+    Hyperbolic sine of x radians.
+
+    The operand x must be a scalar or vector whose component type is 16-bit or
+    32-bit floating-point.
+
+    Result Type and the type of x must be the same type. Results are computed
+    per component.
+
+    <!-- End of AutoGen section -->
+    ```
+    restricted-float-scalar-type ::=  `f16` | `f32`
+    restricted-float-scalar-vector-type ::=
+      restricted-float-scalar-type |
+      `vector<` integer-literal `x` restricted-float-scalar-type `>`
+    sinh-op ::= ssa-id `=` `spv.GLSL.Sinh` ssa-use `:`
+                restricted-float-scalar-vector-type
+    ```
+    #### Example:
+
+    ```mlir
+    %2 = spv.GLSL.Sinh %0 : f32
+    %3 = spv.GLSL.Sinh %1 : vector<3xf16>
+    ```
+  }];
+}
+
+// -----
+
+def SPV_GLSLCoshOp : SPV_GLSLUnaryArithmeticOp<"Cosh", 20, SPV_Float16or32> {
+  let summary = "Hyperbolic cosine of operand in radians";
+
+  let description = [{
+    Hyperbolic cosine of x radians.
+
+    The operand x must be a scalar or vector whose component type is 16-bit or
+    32-bit floating-point.
+
+    Result Type and the type of x must be the same type. Results are computed
+    per component.
+
+    <!-- End of AutoGen section -->
+    ```
+    restricted-float-scalar-type ::=  `f16` | `f32`
+    restricted-float-scalar-vector-type ::=
+      restricted-float-scalar-type |
+      `vector<` integer-literal `x` restricted-float-scalar-type `>`
+    cosh-op ::= ssa-id `=` `spv.GLSL.Cosh` ssa-use `:`
+                restricted-float-scalar-vector-type
+    ```
+    #### Example:
+
+    ```mlir
+    %2 = spv.GLSL.Cosh %0 : f32
+    %3 = spv.GLSL.Cosh %1 : vector<3xf16>
+    ```
+  }];
+}
+
+// -----
+
 def SPV_GLSLTanhOp : SPV_GLSLUnaryArithmeticOp<"Tanh", 21, SPV_Float16or32> {
   let summary = "Hyperbolic tangent of operand in radians";
 
   let description = [{
     Hyperbolic tangent of x radians.
 
     The operand x must be a scalar or vector whose component type is 16-bit or
     32-bit floating-point.