<table border="1" cellspacing="0" cellpadding="8">
<tr>
<th>Issue</th>
<td>
<a href=https://github.com/llvm/llvm-project/issues/118945>118945</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>
[MLIR] Inconsistent output when executing MLIR program with and without `-test-expand-math`
</td>
</tr>
<tr>
<th>Labels</th>
<td>
mlir
</td>
</tr>
<tr>
<th>Assignees</th>
<td>
</td>
</tr>
<tr>
<th>Reporter</th>
<td>
jzc-1122
</td>
</tr>
</table>
<pre>
My git version is [35619c7](https://github.com/llvm/llvm-project/commit/35619c791d1f5128d16c7a8e099e8856e12ab39c).
## 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<2.88> : tensor<51x5x89xf32>} : () -> tensor<51x5x89xf32>
%0 = tosa.ceil %arg0 : (tensor<51x5x89xf32>) -> tensor<51x5x89xf32>
%1 = tosa.reduce_sum %0 {axis = 2 : i32} : (tensor<51x5x89xf32>) -> tensor<51x5x1xf32>
%2 = tosa.exp %1 : (tensor<51x5x1xf32>) -> tensor<51x5x1xf32>
%3 = tosa.exp %2 : (tensor<51x5x1xf32>) -> tensor<51x5x1xf32>
%4 = tosa.reciprocal %3 : (tensor<51x5x1xf32>) -> tensor<51x5x1xf32>
%5 = tosa.reshape %4 {new_shape = array<i64: 5, 51>} : (tensor<51x5x1xf32>) -> tensor<5x51xf32>
%6 = tosa.reduce_min %5 {axis = 0 : i32} : (tensor<5x51xf32>) -> tensor<1x51xf32>
%7 = tosa.pow %6, %6 : (tensor<1x51xf32>, tensor<1x51xf32>) -> tensor<1x51xf32>
%rtn1 = tensor.cast %7 : tensor<1x51xf32> 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-named,tosa-to-linalg))' | \
/path/llvm-project/build/bin/mlir-opt -tosa-to-tensor -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`:**
```
[[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]
```
### 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-named,tosa-to-linalg))' | \
/path/llvm-project/build/bin/mlir-opt -tosa-to-tensor -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`:**
```
[[-nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan, -nan]]
```
I'm not sure if there is any bug in my program or if the wrong usage of the above passes caused this result.
</pre>
<img width="1px" height="1px" alt="" src="http://email.email.llvm.org/o/eJzsWF9vo7gX_TTOy5UR2CHAQx7SZCJVmur30-zDPlYGLolHYCPbpMl8-pWB_Gvazky3q9WsRkLYmOtzjo3vcWJhrdwoxDmJ70i8mojObbWZf_1W0ChibJLr8jB_OMBGOtihsVIrkBZIfMfjWZQVCYlXhKVb51pL-IKwNWHrjXTbLg8K3RC2ruvdsaCt0V-xcIStC9000ldGmCwqoyqOWFpGsyIRKYZZhmkazzBiIudZQVgWkHDhL8YJ47BCWxjZOqmVJw4X9yAawH2LRqIqpNqAUCBVoZWV1qFyYNB2tYOnLSrAPRad81Fui2BFg_Dw-f4LtEZvjGjgSbotCFX2Fd25PozMQurQOor7VqiSNsJtySy8FvaHw9aC0_AFW6PLrsBB3ynCB0UBELYgbNGT_n8kJSz18EFTS0NYNkScep9fnfBm4XiFi0aXXY1AkjsSLgCqThWBv0Fr5E44BDINWyOVe8DGYLXmrGdTVhvCl4Qt9hVnhH_yvNcAZBo2QirCUsIyoIR_grF-JAMgLBZmEwLhKyCMOW1F4GfeEcbOwTtRd9jHlKgsEr5kQZr2gHwBJzFxtI_3aXYUlKz615f8r4WexAxKBhko6wt9C7gc97P-P4wfnfEN-m_8aLtmJE7uxN7nCF8B6wklZxeD-Dnu6Iaanalx3x7FvAAd_Swyv0FmH4Q8vZyuQrZGF6I-Un4EQXxJYLeixZE2uVP49Di28BUIY8SB8KWcTT1zTNgS4uh6mf2wln18qYSweHazLBqpRn0XyyJ8c1lcoN5QRteUw-CTM2urn3odflijnmv0SwC2fBn4x1iNU2MW9GFBIaw7qlm82Neb4kuOM0AWoq5fNKmRq_eQZ6O5sq1LaxoxDbrOqP6BJCvvmMP9wjevbJkdbXmpm8a7v7fxTsGf4ybwygbQ73z9dWPLhK1bH3SzA-adrEtfemdde1ununVwMnmgrbCWtrLFWiokfEVY4js5qYLB7AlLTy7tZ0VbQZ2mtVSi3lAlGiwJW14399tKRlgCJFkCiZfv0EiPkMN3OD8L43dNqhVSu9WO5l1VoZHfBvXs9Ei9Yr9z01x3qhRGoiWMAS202qFxxyF41Vq39vzCFpVvLSo4fgLrjCyxpA06UQonzrFDqB_Sua1XeNvsv-O5tfLsXmbTr8LbcC__3Gqw0KqQNdJOGex7ltRng33nHBdtR02nFBqgCH7vBYrKmQNttVSODr9jCF_ttCxHfGq3wmBJa5nbfra_Q1fLfLh7xseB7bFzsraB1R-CWfwjqMIeVI_sZIOB1W9lMz9m8_8613bu72Sx_3V8F3nHBHi9-G7Ahxb_EZrI_4WI37Tl6Ru2_NuT_y1Pfj7pv136t0u_w6XjF1z63RZNlVCDt9zW3nr3MbVfDffXVd6Xr-wb94QlDSjtwHYGQVbgtugrFoQ6QN5tQCpoDqezHm3GIHgyWm2gs2KDoIcmkesdgvd9tFCIzmIJbivteJoUTMo5LzOeiQnOo4TzaZIk2WyynVd8WrFsijFOqwjTPA4jkbKEhzkXeVzyiZyzkE0jFs7CjM_4LKhKzOMqL0sWVmVccDINsRGyDnzOBdpsJtLaDudRlGbTeFKLHGvbn9wxNhwZMRKvJmbe52jebSyZhrW0zp4RnHR1f9r38Pn-C4lXcH95QqaHFHx2Qvb2wdgrqTrpTD3_6XPBfoCWsPU4xt2c_RUAAP__EykYaA">