File: no_blocks_no_threads.mlir

package info (click to toggle)
swiftlang 6.0.3-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 2,519,992 kB
  • sloc: cpp: 9,107,863; ansic: 2,040,022; asm: 1,135,751; python: 296,500; objc: 82,456; f90: 60,502; lisp: 34,951; pascal: 19,946; sh: 18,133; perl: 7,482; ml: 4,937; javascript: 4,117; makefile: 3,840; awk: 3,535; xml: 914; fortran: 619; cs: 573; ruby: 573
file content (34 lines) | stat: -rw-r--r-- 2,127 bytes parent folder | download | duplicates (4)
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
// RUN: mlir-opt -pass-pipeline="builtin.module(func.func(convert-affine-for-to-gpu{gpu-block-dims=0 gpu-thread-dims=1}))" %s | FileCheck --check-prefix=CHECK-THREADS %s
// RUN: mlir-opt -pass-pipeline="builtin.module(func.func(convert-affine-for-to-gpu{gpu-block-dims=1 gpu-thread-dims=0}))" %s | FileCheck --check-prefix=CHECK-BLOCKS %s

// CHECK-THREADS-LABEL: @one_d_loop
// CHECK-BLOCKS-LABEL: @one_d_loop
func.func @one_d_loop(%A : memref<?xf32>, %B : memref<?xf32>) {
  // Bounds of the loop, its range and step.
  // CHECK-THREADS-NEXT: %{{.*}} = arith.constant 0 : index
  // CHECK-THREADS-NEXT: %{{.*}} = arith.constant 42 : index
  // CHECK-THREADS-NEXT: %[[BOUND:.*]] = arith.subi %{{.*}}, %{{.*}} : index
  // CHECK-THREADS-NEXT: %{{.*}} = arith.constant 1 : index
  // CHECK-THREADS-NEXT: %[[ONE:.*]] = arith.constant 1 : index
  //
  // CHECK-BLOCKS-NEXT: %{{.*}} = arith.constant 0 : index
  // CHECK-BLOCKS-NEXT: %{{.*}} = arith.constant 42 : index
  // CHECK-BLOCKS-NEXT: %[[BOUND:.*]] = arith.subi %{{.*}}, %{{.*}} : index
  // CHECK-BLOCKS-NEXT: %{{.*}} = arith.constant 1 : index
  // CHECK-BLOCKS-NEXT: %[[ONE:.*]] = arith.constant 1 : index

  // CHECK-THREADS-NEXT: gpu.launch blocks(%[[B0:.*]], %[[B1:.*]], %[[B2:.*]]) in (%{{.*}} = %[[ONE]], %{{.*}} = %[[ONE]], %{{.*}}0 = %[[ONE]]) threads(%[[T0:.*]], %[[T1:.*]], %[[T2:.*]]) in (%{{.*}} = %[[BOUND]], %{{.*}} = %[[ONE]], %{{.*}} = %[[ONE]])
  // CHECK-BLOCKS-NEXT: gpu.launch blocks(%[[B0:.*]], %[[B1:.*]], %[[B2:.*]]) in (%{{.*}} = %[[BOUND]], %{{.*}} = %[[ONE]], %{{.*}}0 = %[[ONE]]) threads(%[[T0:.*]], %[[T1:.*]], %[[T2:.*]]) in (%{{.*}} = %[[ONE]], %{{.*}} = %[[ONE]], %{{.*}} = %[[ONE]])
  affine.for %i = 0 to 42 {
  // CHECK-THREADS-NEXT: %[[INDEX:.*]] = arith.addi %{{.*}}, %[[T0]]
  // CHECK-THREADS-NEXT: memref.load %{{.*}}[%[[INDEX]]]
  // CHECK-BLOCKS-NEXT: %[[INDEX:.*]] = arith.addi %{{.*}}, %[[B0]]
  // CHECK-BLOCKS-NEXT: memref.load %{{.*}}[%[[INDEX]]]
    %0 = memref.load %A[%i] : memref<?xf32>
    memref.store %0, %B[%i] : memref<?xf32>
    // CHECK-THREADS: gpu.terminator
    // CHECK-BLOCKS: gpu.terminator
  }
  return
}