<table border="1" cellspacing="0" cellpadding="8">
<tr>
<th>Issue</th>
<td>
<a href=https://github.com/llvm/llvm-project/issues/129529>129529</a>
</td>
</tr>
<tr>
<th>Summary</th>
<td>
[MLIR] Inconsistent output when executing MLIR program with and without `-tosa-test-quant-utils`
</td>
</tr>
<tr>
<th>Labels</th>
<td>
mlir
</td>
</tr>
<tr>
<th>Assignees</th>
<td>
</td>
</tr>
<tr>
<th>Reporter</th>
<td>
Lambor24
</td>
</tr>
</table>
<pre>
My git version is [55fdecc](https://github.com/llvm/llvm-project/commit/55fdeccc4567bcd4e3f8df0d177195880a194a6a).
## Description:
I am experiencing an inconsistent result when executing the same MLIR program with and without the `-tosa-test-quant-utils`.
## Steps to Reproduce:
### 1. **MLIR Program (test.mlir)**:
test.mlir:
```
module {
func.func private @printMemrefI32(tensor<*xi32>)
func.func @main() -> () {
%arg0 = "tosa.const"() {value = dense<-4636> : tensor<52x3x2xi64>} : () -> tensor<52x3x2xi64>
%0 = tosa.reduce_sum %arg0 {axis = 0 : i32} : (tensor<52x3x2xi64>) -> tensor<1x3x2xi64>
%1 = tosa.equal %0, %0 : (tensor<1x3x2xi64>, tensor<1x3x2xi64>) -> tensor<1x3x2xi1>
%2 = tosa.cast %1 : (tensor<1x3x2xi1>) -> tensor<1x3x2xi32>
%rtn2 = tensor.cast %2 : tensor<1x3x2xi32> to tensor<*xi32>
call @printMemrefI32(%rtn2) : (tensor<*xi32>) -> ()
return
}
}
```
### 2. **Command to Run Without `-tosa-test-quant-utils`:**
```
/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-tensor -tosa-to-arith -one-shot-bufferize="bufferize-function-boundaries" -convert-linalg-to-affine-loops -lower-affine -convert-scf-to-cf -expand-strided-metadata -convert-cf-to-llvm -convert-arith-to-llvm -finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
/path/llvm-project/build/bin/mlir-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 `-tosa-test-quant-utils`:**
```
[[[1, 1],
[1, 1],
[1, 1]]]
```
### 4. **Command to Run With `-tosa-test-quant-utils`:**
```
/path/llvm-project/build/bin/mlir-opt test.mlir -tosa-test-quant-utils | \
/path/llvm-project/build/bin/mlir-opt -pass-pipeline='builtin.module(func.func(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-affine-loops -lower-affine -convert-scf-to-cf -expand-strided-metadata -convert-cf-to-llvm -convert-arith-to-llvm -finalize-memref-to-llvm -convert-func-to-llvm -reconcile-unrealized-casts | \
/path/llvm-project/build/bin/mlir-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 `-tosa-test-quant-utils`:**
```
[[[-1, -1],
[-1, -1],
[-1, -1]]]
```
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="1" height="1" alt="" src="http://email.email.llvm.org/o/eJzsV0-P4rgT_TTmUjJKbELgwIGGaamlGf1-mj3sceQ4FfAqsTP-Q9P76Vd2AjTTNKOd2dVeRrLSiVN-78Wuek0J59ROI65I8UCK7UQEvzd29VF0lbFsNqlM_bL69AI75eGA1imjQTkgxUNRNDVKSYotYYu9970jfE3YI2GPO-X3oZpK0xH22LaH0x_aW_MHSk_YozRdp-LNCCNnxbysZD1D3izqJqvzssyXxWKRiXw5E3NB2HJKsnUcjBPGYYtOWtV7ZXQkztZPIDrAY49WoZZK70BoUFoa7ZTzqD1YdKH18LxHDXhEGXyM8nsEJzqETx-fPkNvzc6KDp6V34PQdboxwacwMs-oN05Qj87Tr0FoT4NXrSPz7Frdbx57B97AZ-ytqYPEQeQ5IgblUyBsTdg6Mf9_ZCZsEeGnXassYcsh4rz68uqMN8_Gka07U4cWgZQPJFsDNEHLabxAb9VBeAQyy3qrtP-EncXmibPEpp2xhG8IWx8VZ4R_iLzXAGSWdUJpwhaELYES_gHG-xMZAGGFsLsMCN8CYSzu1DRuvyeMXYIPog2YYmrUDgnf0NmczxMiX8NZTcGO_MiOaj6Lgsptevua_53Is5ZBSFJhMR7BFxe6i8jyQRxjKvMtZAk7fvqF5h30N-T5Te78wo1fg2iTHsI2J13XFFcYbPMO-HvU-RUzuzBL4fxJzE3C_B7skAhnXOv1CJ3izuDs-tReL475fyu5Bkwp2vZmPo5kKV2-0X2Voa-zcMS06IPV8YGU21gbw_VVhVwVIDsV4MZ0XSz2WLBBw-9jzd-r9-R2abypQsIee-H3b12vCqqt499YSI-xiqnpPZxrGmgvnKO96rFVGgnfElbGRV7p6VDbhC3ORRl3JqkztFVatLtkF0vCSiDlBkix-QEx9AQ5bPrlWdhoidRopG5vPK1C06BVfw4y2fmRRmnRlmllgq6FVegIY0Cl0Qe0ftSaIJtGaaStMb0D2ppntOPcJdrJJobKBigee6Fr6rxVNda0Qy9q4cUldgiN33mZS7Iv000kjyq7lHFv46P6y6xFabRULdKgLaaVNY2p735wi23QGi1QhGinQFF7-0J7o7Snw_8nwrcHo-oRm7q9sFjTVlUubfR3qFpVDdfI9mVg-5JydurMP4Ip_xVU4V50Qvaqw6kz98qWn8r2f8H3wf90ucafPnHk0XsBIE8_ajaQTOU0f3PyFDyMO5Jnd5zmP7CZm2w_Yxq_fOuXb_3yre_4VnHDt37atOjJiOi3DjW8eWf6vOAd63oirOxAGw8uWATVxAYo3jgQ-gWqsAOloXs5N0zGjkHwbI3eQXBih2CGKVGZA0I0CXQgRXBYg98rN7Zk00m94vWSL8UEV3k5y7OsnGfFZL8SpWRZzau8ZJJjky1ZxStZyGXJZLbMFxO1YhkrMp7xnOecsemC54Wsy6ISAheLpiCzDDuh2mk8zqmxu4lyLuAqZ8uCLSetqLB1qf1lbGi5WGyE7SodfxV2jsyyVjnvLghe-Ta1zLFxI8UWnl63mWY43W_azPvd5b0smATbrv52h52-0hH2OH7oYcX-CgAA__9P3vM0">