[MLIR] Inconsistent output when executing MLIR program with and without -test-expand-math #119836
Description
My git version is ea44647.
Description:
I am experiencing an inconsistent result when executing the same MLIR program with and without the -test-expand-math.
Steps to Reproduce:
1. MLIR Program (test.mlir):
test.mlir:
module {
func.func private @printMemrefF32(tensor<*xf32>)
func.func @main() -> () {
%arg0 = "tosa.const"() {value = dense<9.5> : tensor<10x20xf32>} : () -> tensor<10x20xf32>
%0 = tosa.reduce_prod %arg0 {axis = 1 : i32} : (tensor<10x20xf32>) -> tensor<10x1xf32>
%1 = tosa.floor %0 : (tensor<10x1xf32>) -> tensor<10x1xf32>
%rtn1 = tensor.cast %1 : tensor<10x1xf32> to tensor<*xf32>
call @printMemrefF32(%rtn1) : (tensor<*xf32>) -> ()
return
}
}
2. Command to Run Without -test-expand-math:
/path/llvm-project/build/bin/mlir-opt test.mlir -pass-pipeline='builtin.module(func.func(tosa-to-linalg))' | \
/path/llvm-project/build/bin/mlir-opt -tosa-to-arith -one-shot-bufferize="bufferize-function-boundaries" -convert-linalg-to-loops -convert-scf-to-cf -expand-strided-metadata -convert-cf-to-llvm -convert-arith-to-llvm -convert-math-to-llvm -finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
/path/llvm-project/build/bin/mlir-cpu-runner -e main -entry-point-result=void \
-shared-libs=/path/llvm-project/build/lib/libmlir_runner_utils.so \
-shared-libs=/path/llvm-project/build/lib/libmlir_c_runner_utils.so \
-shared-libs=/path/llvm-project/build/lib/libmlir_async_runtime.so
3. Output Without -test-expand-math:
[[3.58486e+19],
[3.58486e+19],
[3.58486e+19],
[3.58486e+19],
[3.58486e+19],
[3.58486e+19],
[3.58486e+19],
[3.58486e+19],
[3.58486e+19],
[3.58486e+19]]
4. Command to Run With -test-expand-math:
/path/llvm-project/build/bin/mlir-opt test.mlir -pass-pipeline='builtin.module(func.func(tosa-to-linalg))' | \
/path/llvm-project/build/bin/mlir-opt -tosa-to-arith -one-shot-bufferize="bufferize-function-boundaries" -convert-linalg-to-loops -test-expand-math -convert-scf-to-cf -expand-strided-metadata -convert-cf-to-llvm -convert-arith-to-llvm -convert-math-to-llvm -finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
/path/llvm-project/build/bin/mlir-cpu-runner -e main -entry-point-result=void \
-shared-libs=/path/llvm-project/build/lib/libmlir_runner_utils.so \
-shared-libs=/path/llvm-project/build/lib/libmlir_c_runner_utils.so \
-shared-libs=/path/llvm-project/build/lib/libmlir_async_runtime.so
5. Output With -test-expand-math:
[[9.22337e+18],
[9.22337e+18],
[9.22337e+18],
[9.22337e+18],
[9.22337e+18],
[9.22337e+18],
[9.22337e+18],
[9.22337e+18],
[9.22337e+18],
[9.22337e+18]]
I'm not sure if there is any bug in my program or if the wrong usage of the above passes caused this result.