File: async-parallel-for-num-worker-threads.mlir

package info (click to toggle)
swiftlang 6.1.3-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 2,791,604 kB
  • sloc: cpp: 9,901,740; ansic: 2,201,431; asm: 1,091,827; python: 308,252; objc: 82,166; f90: 80,126; lisp: 38,358; pascal: 25,559; sh: 20,429; ml: 5,058; perl: 4,745; makefile: 4,484; awk: 3,535; javascript: 3,018; xml: 918; fortran: 664; cs: 573; ruby: 396
file content (45 lines) | stat: -rw-r--r-- 2,924 bytes parent folder | download | duplicates (16) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
 
// RUN: mlir-opt %s -split-input-file -async-parallel-for=num-workers=-1  \
// RUN: | FileCheck %s --dump-input=always

// CHECK-LABEL: @num_worker_threads(
// CHECK:       %[[MEMREF:.*]]: memref<?xf32>
func.func @num_worker_threads(%arg0: memref<?xf32>) {

  // CHECK-DAG: %[[scalingCstInit:.*]] = arith.constant 8.000000e+00 : f32
  // CHECK-DAG: %[[bracketLowerBound4:.*]] = arith.constant 4 : index
  // CHECK-DAG: %[[scalingCst4:.*]] = arith.constant 4.000000e+00 : f32
  // CHECK-DAG: %[[bracketLowerBound8:.*]] = arith.constant 8 : index
  // CHECK-DAG: %[[scalingCst8:.*]] = arith.constant 2.000000e+00 : f32
  // CHECK-DAG: %[[bracketLowerBound16:.*]] = arith.constant 16 : index
  // CHECK-DAG: %[[scalingCst16:.*]] = arith.constant 1.000000e+00 : f32
  // CHECK-DAG: %[[bracketLowerBound32:.*]] = arith.constant 32 : index
  // CHECK-DAG: %[[scalingCst32:.*]] = arith.constant 8.000000e-01 : f32
  // CHECK-DAG: %[[bracketLowerBound64:.*]] = arith.constant 64 : index
  // CHECK-DAG: %[[scalingCst64:.*]] = arith.constant 6.000000e-01 : f32
  // CHECK:     %[[workersIndex:.*]] = async.runtime.num_worker_threads : index
  // CHECK:     %[[inBracket4:.*]] = arith.cmpi sgt, %[[workersIndex]], %[[bracketLowerBound4]] : index
  // CHECK:     %[[scalingFactor4:.*]] = arith.select %[[inBracket4]], %[[scalingCst4]], %[[scalingCstInit]] : f32
  // CHECK:     %[[inBracket8:.*]] = arith.cmpi sgt, %[[workersIndex]], %[[bracketLowerBound8]] : index
  // CHECK:     %[[scalingFactor8:.*]] = arith.select %[[inBracket8]], %[[scalingCst8]], %[[scalingFactor4]] : f32
  // CHECK:     %[[inBracket16:.*]] = arith.cmpi sgt, %[[workersIndex]], %[[bracketLowerBound16]] : index
  // CHECK:     %[[scalingFactor16:.*]] = arith.select %[[inBracket16]], %[[scalingCst16]], %[[scalingFactor8]] : f32
  // CHECK:     %[[inBracket32:.*]] = arith.cmpi sgt, %[[workersIndex]], %[[bracketLowerBound32]] : index
  // CHECK:     %[[scalingFactor32:.*]] = arith.select %[[inBracket32]], %[[scalingCst32]], %[[scalingFactor16]] : f32
  // CHECK:     %[[inBracket64:.*]] = arith.cmpi sgt, %[[workersIndex]], %[[bracketLowerBound64]] : index
  // CHECK:     %[[scalingFactor64:.*]] = arith.select %[[inBracket64]], %[[scalingCst64]], %[[scalingFactor32]] : f32
  // CHECK:     %[[workersInt:.*]] = arith.index_cast %[[workersIndex]] : index to i32
  // CHECK:     %[[workersFloat:.*]] = arith.sitofp %[[workersInt]] : i32 to f32
  // CHECK:     %[[scaledFloat:.*]] = arith.mulf %[[scalingFactor64]], %[[workersFloat]] : f32
  // CHECK:     %[[scaledInt:.*]] = arith.fptosi %[[scaledFloat]] : f32 to i32
  // CHECK:     %[[scaledIndex:.*]] = arith.index_cast %[[scaledInt]] : i32 to index

  %lb = arith.constant 0 : index
  %ub = arith.constant 100 : index
  %st = arith.constant 1 : index
  scf.parallel (%i) = (%lb) to (%ub) step (%st) {
    %one = arith.constant 1.0 : f32
    memref.store %one, %arg0[%i] : memref<?xf32>
  }

  return
}