[Mlir-commits] [mlir] [MLIR]NVVM] Add `inline_ptx` op (PR #139923)

[llvmlistbot at llvm.org]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-mlir-llvm

Author: Guray Ozen (grypp)

<details>
<summary>Changes</summary>

This op allows using PTX directly within the NVVM dialect, while greatly simplifying llvm.inline_asm generation.

**Example 1: Read-only Parameters**

Sets `"l,r"` automatically. 
```
nvvm.inline_ptx "mbarrier.init.b64 [$0], $1;" (%barrier_gen, %count) : !llvm.ptr, i32

// Lowers to:
llvm.inline_asm has_side_effects asm_dialect = att
      "mbarrier.init.b64 [$0], $1;", "l,r" %arg0, %arg2 : (!llvm.ptr, i32) -> ()
```

**Example 2: Read-only and Write-only Parameters**

Sets `=f,f"` automatically. `=` is set because there is store. 
```
%0 = nvvm.inline_ptx "ex2.approx.ftz.f32 $0, $1;" (%input) : f32 -> f32

// Lowers to:
%0 = llvm.inline_asm has_side_effects asm_dialect = att "ex2.approx.ftz.f32 $0, $1;", "=f,f" %arg0 : (f32) -> f32
```

**Example 3: Predicate Usage**

Now `@$2` is set automatically for predication. 
```
nvvm.inline_ptx "mbarrier.init.b64 [$0], $1;" (%barrier_gen, %count), predicate = %pred : !llvm.ptr, i32, i1

// Lowers to:
llvm.inline_asm has_side_effects asm_dialect = att "@$2 mbarrier.init.b64 [$0], $1;", "l,r,b" %arg0, %arg2, %arg3 : (!llvm.ptr, i32, i1) -> ()
```

---
Full diff: https://github.com/llvm/llvm-project/pull/139923.diff


2 Files Affected:

- (modified) mlir/include/mlir/Dialect/LLVMIR/NVVMOps.td (+70) 
- (modified) mlir/test/Conversion/NVVMToLLVM/nvvm-to-llvm.mlir (+25) 


``````````diff
diff --git a/mlir/include/mlir/Dialect/LLVMIR/NVVMOps.td b/mlir/include/mlir/Dialect/LLVMIR/NVVMOps.td
index 654aff71f25be..4ba54fa3c1ca7 100644
--- a/mlir/include/mlir/Dialect/LLVMIR/NVVMOps.td
+++ b/mlir/include/mlir/Dialect/LLVMIR/NVVMOps.td
@@ -236,6 +236,76 @@ foreach index = !range(0, 32) in {
   def NVVM_EnvReg # index # Op : NVVM_SpecialRegisterOp<"read.ptx.sreg.envreg" # index>;
 }
 
+//===----------------------------------------------------------------------===//
+// Inline PTX op definition
+//===----------------------------------------------------------------------===//
+
+def NVVM_InlinePtxOP : NVVM_Op<"inline_ptx", 
+  [DeclareOpInterfaceMethods<BasicPtxBuilderOpInterface>, 
+    AttrSizedOperandSegments]>
+{
+  let summary = "Inline PTX Op";
+  let description = [{This op allows using PTX directly within the NVVM 
+    dialect, while greatly simplifying llvm.inline_asm generation. It 
+    automatically handles register size selection and sets the correct 
+    read/write access for each operand. The operation leverages the 
+    `BasicPtxBuilderInterface` to abstract away low-level details of 
+    PTX assembly formatting.
+
+    The `predicate` attribute is used to specify a predicate for the 
+    PTX instruction.
+
+    Example 1: Read-only Parameters
+    ```mlir
+    nvvm.inline_ptx "mbarrier.init.b64 [$0], $1;" (%barrier_gen, %count) : !llvm.ptr, i32
+
+    // Lowers to:
+    llvm.inline_asm has_side_effects asm_dialect = att 
+      "mbarrier.init.b64 [$0], $1;", "l,r" %arg0, %arg2 : (!llvm.ptr, i32) -> ()
+    ```
+
+    Example 2: Read-only and Write-only Parameters
+    ```mlir
+    %0 = nvvm.inline_ptx "ex2.approx.ftz.f32 $0, $1;" (%input) : f32 -> f32
+
+    // Lowers to:
+    %0 = llvm.inline_asm has_side_effects asm_dialect = att 
+      "ex2.approx.ftz.f32 $0, $1;", "=f,f" %arg0 : (f32) -> f32
+    ```
+
+    Example 3: Predicate Usage
+    ```mlir
+    nvvm.inline_ptx "mbarrier.init.b64 [$0], $1;" (%barrier_gen, %count), 
+      predicate = %pred : !llvm.ptr, i32, i1
+
+    // Lowers to:
+    llvm.inline_asm has_side_effects asm_dialect = att 
+      "@$2 mbarrier.init.b64 [$0], $1;", "l,r,b" %arg0, %arg2, %arg3 
+      : (!llvm.ptr, i32, i1) -> ()
+    ```
+  }];
+
+  let arguments = (ins Variadic<AnyType>:$readOnlyArgs, 
+                       StrAttr:$ptxCode,
+                       PtxPredicate:$predicate);
+                      
+  let results = (outs Variadic<AnyType>:$writeOnlyArgs);
+
+  let assemblyFormat = [{ 
+    $ptxCode `(` $readOnlyArgs `)` 
+    (`,` `predicate` `=` $predicate^)? attr-dict 
+    `:` type(operands) 
+    (`->` type($writeOnlyArgs)^)?
+  }];
+  
+  let extraClassDefinition = [{
+    std::string $cppClass::getPtx() {
+      StringRef eventName = getPtxCode();
+      return std::string(eventName.data());
+    }
+  }];
+}
+
 //===----------------------------------------------------------------------===//
 // NVVM approximate op definitions
 //===----------------------------------------------------------------------===//
diff --git a/mlir/test/Conversion/NVVMToLLVM/nvvm-to-llvm.mlir b/mlir/test/Conversion/NVVMToLLVM/nvvm-to-llvm.mlir
index c7a6eca158276..1d9164ac94d76 100644
--- a/mlir/test/Conversion/NVVMToLLVM/nvvm-to-llvm.mlir
+++ b/mlir/test/Conversion/NVVMToLLVM/nvvm-to-llvm.mlir
@@ -680,3 +680,28 @@ llvm.func @llvm_nvvm_barrier_arrive(%barID : i32, %numberOfThreads : i32) {
   nvvm.barrier.arrive id = %barID number_of_threads = %numberOfThreads
   llvm.return
 }
+
+
+// -----
+
+llvm.func @init_mbarrier(
+    %barrier_gen : !llvm.ptr, 
+    %barrier : !llvm.ptr<3>, 
+    %count : i32, 
+    %pred : i1) {
+  // CHECK: llvm.inline_asm has_side_effects asm_dialect = att "mbarrier.init.b64 [$0], $1;", "l,r" 
+  nvvm.inline_ptx "mbarrier.init.b64 [$0], $1;" (%barrier_gen, %count)  : !llvm.ptr, i32 
+  // CHECK: llvm.inline_asm has_side_effects asm_dialect = att "@$2 mbarrier.init.b64 [$0], $1;", "l,r,b"
+  nvvm.inline_ptx "mbarrier.init.b64 [$0], $1;" (%barrier_gen, %count), predicate = %pred : !llvm.ptr, i32, i1
+  llvm.return
+}
+// -----
+
+llvm.func @ex2(%input : f32, %pred : i1) {
+  // CHECK: %{{.*}} = llvm.inline_asm has_side_effects asm_dialect = att "ex2.approx.ftz.f32 $0, $1;", "=f,f" %{{.*}} : (f32) -> f32
+  %0 = nvvm.inline_ptx "ex2.approx.ftz.f32 $0, $1;" (%input) : f32 -> f32
+  
+  // CHECK: %{{.*}} =  llvm.inline_asm has_side_effects asm_dialect = att "@$1 ex2.approx.ftz.f32 $0, $1;", "=f,f,b" %{{.*}}, %{{.*}} : (f32, i1) -> f32
+  %1 = nvvm.inline_ptx "ex2.approx.ftz.f32 $0, $1;" (%input), predicate = %pred  : f32, i1 -> f32
+  llvm.return
+}
\ No newline at end of file

``````````

</details>


https://github.com/llvm/llvm-project/pull/139923