Arm backend: Update ethos-u-vela to 4.5.0 (pytorch#16075)

Remove new passing xfails due to new Vela version is fixing some old
problems.

cc @freddan80 @per @zingo @oscarandersson8218 @digantdesai

Signed-off-by: Erik Lundell <erik.lundell@arm.com>
Co-authored-by: Digant Desai <digantdesai@meta.com>

Author: Erik-Lundell

backends/arm/requirements-arm-ethos-u.txt

@@ -3,5 +3,5 @@
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
-ethos-u-vela == 4.4.1
+ethos-u-vela == 4.5.0
 pte-adapter-model-explorer == 0.0.2

backends/arm/test/misc/test_conv_relu_residual_add.py

@@ -76,13 +76,6 @@ def test_conv_relu_residual_add_tosa_INT(per_channel_quantization):
     pipeline.run()
 
 
-# TODO: Xfail until the Ethos-U Vela compiler ships commit
-# 642f7517d3a6bd053032e1942822f6e38ccd546f. That patch fixes the bug that
-# causes this test to fail.
-@pytest.mark.xfail(
-    reason=("Blocked by Vela commit 642f7517d3a6bd053032e1942822f6e38ccd546f"),
-    strict=True,
-)
 @pytest.mark.slow
 @common.XfailIfNoCorstone300
 @common.parametrize("per_channel_quantization", quant_test_data)

backends/arm/test/ops/test_linear.py

@@ -299,25 +299,7 @@ def test_linear_16a8w_tosa_INT(test_data: torch.Tensor):
     pipeline.run()
 
 
-x_fails = {}
-x_skips = {}
-
-for test_name in [
-    "model_linear_rank4_zeros",
-    "model_linear_rank4_negative_ones",
-    "model_linear_rank4_negative_large_rand",
-]:
-    for set_per_chan in ["True", "False"]:
-        key = test_name + ",per_channel_quant={}".format(set_per_chan)
-        reason = (
-            "MLETORCH-1452: AssertionError: Output 0 does not match reference output."
-        )
-        x_fails[key] = reason
-        # TODO: Check why xfail doesn't work for this buck target. In the interim rely on skip
-        x_skips[key] = reason
-
-
-@common.parametrize("test_data", test_data_all_16a8w, xfails=x_fails, skips=x_skips)
+@common.parametrize("test_data", test_data_all_16a8w)
 @common.XfailIfNoCorstone300
 def test_linear_16a8w_u55_INT(test_data: torch.Tensor):
     """Test linear operation with 16A8W quantization on U55 (16-bit activations, 8-bit weights)"""

backends/arm/test/ops/test_matmul.py

@@ -137,9 +137,6 @@ def test_matmul_u55_INT(test_data: input_t1):
 @common.parametrize(
     "test_data",
     MatMulSingleInput.test_data_generators,
-    xfails={
-        "rand_4d": "MLBEDSW-11228: Matmul output diff between 1 input vs 2 identical inputs"
-    },
 )
 @common.XfailIfNoCorstone300
 def test_matmul_u55_INT_single_input(test_data: input_t1):
@@ -156,9 +153,6 @@ def test_matmul_u55_INT_single_input(test_data: input_t1):
 @common.parametrize(
     "test_data",
     MatMulCombo.test_data_generators,
-    xfails={
-        "rand_rand_rand_4d": "MLBEDSW-11228: Matmul output diff between 1 input vs 2 identical inputs"
-    },
 )
 @common.XfailIfNoCorstone300
 def test_matmul_u55_INT_combo(test_data: input_t1):
@@ -188,9 +182,6 @@ def test_matmul_u85_INT(test_data: input_t1):
 @common.parametrize(
     "test_data",
     MatMulSingleInput.test_data_generators,
-    xfails={
-        "rand_4d": "MLBEDSW-11228: Matmul output diff between 1 input vs 2 identical inputs"
-    },
 )
 @common.XfailIfNoCorstone320
 def test_matmul_u85_INT_single_input(test_data: input_t1):
@@ -207,9 +198,6 @@ def test_matmul_u85_INT_single_input(test_data: input_t1):
 @common.parametrize(
     "test_data",
     MatMulCombo.test_data_generators,
-    xfails={
-        "rand_rand_rand_4d": "MLBEDSW-11228: Matmul output diff between 1 input vs 2 identical inputs"
-    },
 )
 @common.XfailIfNoCorstone320
 def test_matmul_u85_INT_combo(test_data: input_t1):

backends/arm/test/ops/test_rsqrt.py

@@ -8,7 +8,6 @@
 
 from typing import Tuple
 
-import pytest
 import torch
 
 from executorch.backends.arm.test import common
@@ -124,10 +123,7 @@ def test_rsqrt_tosa_INT_a16w8(test_tensor: torch.Tensor):
 
 @common.parametrize("test_tensor", Rsqrt.test_parameters)
 @common.XfailIfNoCorstone300
-@pytest.mark.xfail(
-    reason="MLETORCH-707: AssertionError: Output 0 does not match reference output."
-)
-def test_rsqrt_16a8w_u55_INT(test_tensor: torch.Tensor):
+def test_rsqrt_16a8w_u55_INT16(test_tensor: torch.Tensor):
     """Test rsqrt operation with int16 I/O quantization for U55"""
     # Use wider tolerances for int16 I/O quantization on U55
     pipeline = EthosU55PipelineINT[input_t1](

backends/arm/test/ops/test_sigmoid.py

@@ -8,7 +8,6 @@
 
 from typing import Tuple
 
-import pytest
 import torch
 from executorch.backends.arm.quantizer.arm_quantizer import (
     get_symmetric_a16w8_quantization_config,
@@ -312,10 +311,7 @@ def test_sigmoid_16a8w_tosa_INT(test_data: torch.Tensor):
 
 @common.parametrize("test_data", test_data_suite)
 @common.XfailIfNoCorstone300
-@pytest.mark.xfail(
-    reason="MLETORCH-707: AssertionError: Output 0 does not match reference output."
-)
-def test_sigmoid_16a8w_u55_INT(test_data: torch.Tensor):
+def test_sigmoid_16a8w_u55_INT16(test_data: torch.Tensor):
     """Test sigmoid operation with 16A8W quantization on U55 (16-bit activations, 8-bit weights)"""
     per_channel_quantization = False
 

backends/arm/test/ops/test_tanh.py

@@ -6,7 +6,6 @@
 
 from typing import Tuple
 
-import pytest
 import torch
 
 from executorch.backends.arm.test import common
@@ -132,10 +131,7 @@ def test_tanh_16a8w_tosa_INT(test_data: torch.Tensor):
 
 @common.parametrize("test_data", test_data_suite)
 @common.XfailIfNoCorstone300
-@pytest.mark.xfail(
-    reason="MLETORCH-707: AssertionError: Output 0 does not match reference output."
-)
-def test_tanh_16a8w_u55_INT(test_data: torch.Tensor):
+def test_tanh_16a8w_u55_INT16(test_data: torch.Tensor):
     """Test tanh operation with 16A8W quantization on U55 (16-bit activations, 8-bit weights)"""
     per_channel_quantization = False
 

backends/arm/test/ops/test_var.py

@@ -87,21 +87,6 @@ class VarDim(torch.nn.Module):
         ),
     }
 
-    test_parameters_u55_xfails = {
-        "var_3d_dim_neg_2_keep_dim_unbiased": lambda: (
-            torch.rand(1, 50, 10),
-            -2,
-            True,
-            False,
-        ),
-        "var_3d_dim_neg_1_keep_dim_biased": lambda: (
-            torch.rand(1, 50, 10, 20),
-            -1,
-            True,
-            True,
-        ),
-    }
-
     def __init__(self, dim: int = -1, keepdim: bool = True, unbiased: bool = False):
         super().__init__()
         self.dim = dim
@@ -352,16 +337,9 @@ def test_var_dim_tosa_INT_correction(test_data: Tuple):
     pipeline.run()
 
 
-# TODO: Xfail "var_3d_dims_keep_dim_0_correction" until the Ethos-U Vela compiler ships commit
-# 642f7517d3a6bd053032e1942822f6e38ccd546f. That patch fixes the bug that causes the test to fail.
 @common.parametrize(
     "test_data",
     VarCorrection.test_parameters,
-    xfails={
-        "var_3d_dims_keep_dim_0_correction": (
-            "Blocked by Vela commit 642f7517d3a6bd053032e1942822f6e38ccd546f"
-        ),
-    },
 )
 @common.XfailIfNoCorstone300
 def test_var_dim_u55_INT_correction(test_data: Tuple):