[mlir][rocdl] Add readfirstlane intrinsic (#152551)

Author: Hardcode84

mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td

@@ -189,6 +189,20 @@ def ROCDL_BallotOp :
   let assemblyFormat = "$pred attr-dict `:` type($res)";
 }
 
+def ROCDL_ReadfirstlaneOp : ROCDL_IntrOp<"readfirstlane", [], [0], [AllTypesMatch<["res", "src"]>], 1>,
+  Arguments<(ins LLVM_Type:$src)> {
+  let results = (outs LLVM_Type:$res);
+  let summary = "Get the value in first active lane.";
+
+  let description = [{
+    Returns the value in the lowest active lane of the input operand.
+  }];
+
+  let assemblyFormat = [{
+    $src attr-dict `:` type($res)
+  }];
+}
+
 def ROCDL_ReadlaneOp : ROCDL_IntrOp<"readlane", [], [0], [AllTypesMatch<["res", "src0"]>], 1>,
   Arguments<(ins LLVM_Type:$src0,
                  I32:$src1)> {
@@ -201,7 +215,7 @@ def ROCDL_ReadlaneOp : ROCDL_IntrOp<"readlane", [], [0], [AllTypesMatch<["res",
 
   let assemblyFormat = [{
     $src0 `,` $src1  attr-dict `:` `(` type($src0) `,` type($src1) `)` `->` type($res)
-   }];
+  }];
 }
 
 //===----------------------------------------------------------------------===//

mlir/test/Dialect/LLVMIR/rocdl.mlir

@@ -981,6 +981,13 @@ llvm.func @rocdl.s.wait.expcnt() {
 
 // -----
 
+llvm.func @rocdl.readfirstlane(%src : f32) -> f32 {
+  // CHECK-LABEL: rocdl.readfirstlane
+  // CHECK: rocdl.readfirstlane %{{.*}} : f32
+  %ret = rocdl.readfirstlane %src : f32
+  llvm.return %ret : f32
+}
+
 llvm.func @rocdl.readlane(%src : f32) -> f32 {
   %cst0 = llvm.mlir.constant(0 : i32) : i32
 

mlir/test/Target/LLVMIR/rocdl.mlir

@@ -125,6 +125,23 @@ llvm.func @rocdl.ballot64(%pred : i1) -> i64 {
   llvm.return %0 : i64
 }
 
+llvm.func @rocdl.readfirstlane(%src0 : f32, %src1: f64, %src2: i32, %src3: vector<2 x f32>) -> f32 {
+  // CHECK-LABEL: rocdl.readfirstlane
+  // CHECK: call float @llvm.amdgcn.readfirstlane.f32(float %{{.*}})
+  %0 = rocdl.readfirstlane %src0 : f32
+
+  // CHECK: call double @llvm.amdgcn.readfirstlane.f64(double %{{.*}})
+  %1 = rocdl.readfirstlane %src1 : f64
+
+  // CHECK: call i32 @llvm.amdgcn.readfirstlane.i32(i32 %{{.*}})
+  %2 = rocdl.readfirstlane %src2 : i32
+
+  // CHECK: call <2 x float> @llvm.amdgcn.readfirstlane.v2f32(<2 x float> %{{.*}})
+  %3 = rocdl.readfirstlane %src3 : vector<2 x f32>
+
+  llvm.return %0 : f32
+}
+
 llvm.func @rocdl.readlane(%src0 : f32, %src1: f64, %src2: i32, %src3: vector<2 x f32>) -> f32 {
   %idx = llvm.mlir.constant(0 : i32) : i32