torch-mlir/test/npcomp-run-mlir/constant.mlir

// RUN: npcomp-run-mlir %s \
// RUN:   -invoke constant \
// RUN:   -shared-libs=%npcomp_runtime_shlib 2>&1 \
// RUN:   | FileCheck %s

// CHECK: output #0: dense<1.000000e+00> : tensor<f32>
func @constant() -> tensor<f32> {
  %0 = constant dense<1.0> : tensor<f32>
  return %0 : tensor<f32>
}
Make input file to npcomp-run-mlir be positional. This makes command lines more succinct. 2020-07-14 07:00:54 +08:00			`// RUN: npcomp-run-mlir %s \`
npcomprt: add support for constants - create tcp.global + tcp.get_global_memref - create npcomprt.global + npcomprt.get_global - LLVM lowering for new npcomprt ops - Runtime: - GlobalDescriptor struct emitted by LLVM lowering - implement __npcomp_compiler_rt_get_global Also, - cleanly isolate all runtime data structure definitions shared by the compiler and runtime into lib/runtime/CompilerDataStructures.h 2020-07-11 08:31:24 +08:00			`// RUN: -invoke constant \`
			`// RUN: -shared-libs=%npcomp_runtime_shlib 2>&1 \`
			`// RUN: \| FileCheck %s`

			`// CHECK: output #0: dense<1.000000e+00> : tensor<f32>`
			`func @constant() -> tensor<f32> {`
			`%0 = constant dense<1.0> : tensor<f32>`
			`return %0 : tensor<f32>`
			`}`