Update Ops documentation for ONNX 1.16.2 (#2942)

* Update Ops documentation for ONNX 1.16.2 * Fix format --------- Co-authored-by: Megan Hampton <[email protected]>
onnx · Sep 16, 2024 · 37b8393 · 37b8393
1 parent 2f2ccc5
commit 37b8393
Show file tree

Hide file tree

Showing 2 changed files with 36 additions and 31 deletions.
diff --git a/docs/SupportedONNXOps-cpu.md b/docs/SupportedONNXOps-cpu.md
@@ -36,8 +36,8 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **BitwiseOr** |18 - * | | |
 | **BitwiseXor** |18 - * | | |
 | **BlackmanWindow** |none | | | |
-| **Cast** |6 - * |Cast only between float and double types. Only ppc64le and MacOS platforms support float16. | |
-| **CastLike** |19 - * |CastLike only between float and double types. Only ppc64le and MacOS platforms support float16. | |
+| **Cast** |6 - * |Cast only between float and double types. Only ppc64le and MacOS platforms support float16. Does not support int4 and uint4. | |
+| **CastLike** |19 - * |CastLike only between float and double types. Only ppc64le and MacOS platforms support float16. Does not support int4 and uint4. | |
 | **CastMap** |none | | | |
 | **CategoryMapper** |none | | | |
 | **Ceil** |6 - * | | |
@@ -48,8 +48,8 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **Compress** |9 - * | | |
 | **Concat** |6 - * | | |
 | **ConcatFromSequence** |none | | | |
-| **Constant** |6 - * | | |
-| **ConstantOfShape** |9 - * | | |
+| **Constant** |6 - * |Does not support int4 and uint4. | |
+| **ConstantOfShape** |9 - * |Does not support int4 and uint4. | |
 | **Conv** |6 - * | | |
 | **ConvInteger** |none | | | |
 | **ConvTranspose** |6 - * |Spatial dimensions (H and W in input `X`, and kH and kW in input `W`) must be static dimension. | |
@@ -59,7 +59,7 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **DFT** |17 - * | | |
 | **DeformConv** |none | | | |
 | **DepthToSpace** |13 - * | | |
-| **DequantizeLinear** |10 - * |Only support for per-tensor or layer dequantization. No support for per-axis dequantization. | |
+| **DequantizeLinear** |10 - * |Only support for per-tensor or layer dequantization. No support for per-axis dequantization. Does not support int4 and uint4. | |
 | **Det** |none | | | |
 | **DictVectorizer** |none | | | |
 | **Div** |6 - * |No support for short integers. | |
@@ -73,7 +73,7 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **Expand** |8 - * |Input `shape` must have static shape. | |
 | **EyeLike** |none | | | |
 | **FeatureVectorizer** |none | | | |
-| **Flatten** |6 - * | | |
+| **Flatten** |6 - * |Does not support int4 and uint4. | |
 | **Floor** |6 - * | | |
 | **GRU** |7 - * |W, B and R must be constants. | |
 | **Gather** |6 - * | | |
@@ -94,8 +94,8 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **HardSigmoid** |6 - * | | |
 | **HardSwish** |none | | | |
 | **Hardmax** |6 - * | | |
-| **Identity** |16 - * |Sequence identity not supported. | |
-| **If** |16 - * |Sequence and Optional outputs are not supported. | |
+| **Identity** |16 - * |Sequence identity not supported. Does not support int4 and uint4. | |
+| **If** |16 - * |Sequence and Optional outputs are not supported. Does not support int4 and uint4. | |
 | **Imputer** |none | | | |
 | **InstanceNormalization** |6 - * | | |
 | **IsInf** |20 - * |Currently no support for float16 infinity value. Only for float32 and float64. | |
@@ -111,7 +111,7 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **LinearRegressor** |none | | | |
 | **Log** |6 - * | | |
 | **LogSoftmax** |13 - * |Axis 0, 1, and default currently disabled due to changes in ONNX 1.8.1/Opset 13. |Temporally removed due to changes in onnx 1.8.1. |
-| **Loop** |6 - * |Input must have static shape. | |
+| **Loop** |6 - * |Input must have static shape. Does not support int4 and uint4. | |
 | **LpNormalization** |none | | | |
 | **LpPool** |none | | | |
 | **MatMul** |6 - * | | |
@@ -142,11 +142,11 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **OptionalHasElement** |none | | | |
 | **Or** |7 - * | | |
 | **PRelu** |6 - * | | |
-| **Pad** |6 - * |axes input not supported. | |
+| **Pad** |6 - * |axes input not supported. Does not support int4 and uint4. | |
 | **Pow** |7 - * |No support for power with integer types. | |
 | **QLinearConv** |none | | | |
 | **QLinearMatMul** |none | | | |
-| **QuantizeLinear** |10 - * |Do not support per-axis and i8 quantization. | |
+| **QuantizeLinear** |10 - * |Does not support per-axis and i8 quantization. Does not support int4 and uint4. | |
 | **RNN** |7 - * |W, B and R must be constants. | |
 | **RandomNormal** |none | | | |
 | **RandomNormalLike** |none | | | |
@@ -165,7 +165,7 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **ReduceSum** |6 - * |Default axis and do_not_keep_dim not supported. |Default axis and do_not_keep_dim temporarily removed due to changes in onnx 1.8.1. |
 | **ReduceSumSquare** |13 - * |Default axis and do_not_keep_dim not supported. | |
 | **Relu** |6 - * | | |
-| **Reshape** |6 - * |allowzero not supported. Input `shape` must have static dimension. | |
+| **Reshape** |6 - * |allowzero not supported. Input `shape` must have static dimension. Does not support int4 and uint4. | |
 | **Resize** |10 - * |Missing support for linear, cubic, crop, pytorch_half_pixel, and floor. Attributes antialias, axes and keep_aspect_ratio_policy are not supported. `scales` and `sizes` must have static dimension. | |
 | **ReverseSequence** |10 - * | | |
 | **RoiAlign** |none | | | |
@@ -174,7 +174,7 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **SVMClassifier** |none | | | |
 | **SVMRegressor** |none | | | |
 | **Scaler** |none | | | |
-| **Scan** |8 - * |Does not support dynamic shapes. |Precision issue with newer opset, maybe just unsupported. Dynamic shape?. |
+| **Scan** |8 - * |Does not support dynamic shapes. Does not support int4 and uint4. |Precision issue with newer opset, maybe just unsupported. Dynamic shape?. |
 | **Scatter** |none | | | |
 | **ScatterElements** |11 - * |Does not support duplicate indices. | |
 | **ScatterND** |11 - * |Does not support scatternd add/multiply. | |
@@ -186,13 +186,13 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **SequenceInsert** |11 - * |Does not support unranked sequence element. | |
 | **SequenceLength** |none | | | |
 | **SequenceMap** |none | | | |
-| **Shape** |15 - * |Does not support start and end attributes. | |
+| **Shape** |15 - * |Does not support start and end attributes. Does not support int4 and uint4. | |
 | **Shrink** |none | | | |
 | **Sigmoid** |6 - * | | |
 | **Sign** |9 - * | | |
 | **Sin** |7 - * | | |
 | **Sinh** |9 - * | | |
-| **Size** |13 - * | | |
+| **Size** |13 - * |Does not support int4 and uint4. | |
 | **Slice** |13 - * |Axis must be a constant argument. |Add tests to slices, currently have none. |
 | **Softmax** |6 - * | | |
 | **SoftmaxCrossEntropyLoss** |none | | | |
@@ -202,7 +202,7 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **Split** |6 - * |Does not support static and dynamic shape, zero size splits. |Temporally removed due to changes in onnx 1.8.1. |
 | **SplitToSequence** |none | | | |
 | **Sqrt** |6 - * | | |
-| **Squeeze** |6 - * |Does not support static and dynamic shape. |Temporally removed due to changes in onnx 1.8.1. |
+| **Squeeze** |6 - * |Does not support static and dynamic shape. Does not support int4 and uint4. |Temporally removed due to changes in onnx 1.8.1. |
 | **StringNormalizer** |none | | | |
 | **Sub** |6 - * |Does not support short integers. | |
 | **Sum** |6 - * | | |
@@ -212,12 +212,12 @@ Onnx-mlir currently supports ONNX operations targeting up to opset 21. Limitatio
 | **ThresholdedRelu** |none | | | |
 | **Tile** |6 - * | | |
 | **TopK** |10 - * |`K`, the number of top elements to retrieve, must have static shape. | |
-| **Transpose** |6 - * | | |
+| **Transpose** |6 - * |Does not support int4 and uint4. | |
 | **TreeEnsembleClassifier** |none | | | |
 | **TreeEnsembleRegressor** |none | | | |
 | **Trilu** |14 - * | | |
 | **Unique** |11 - * | | |
-| **Unsqueeze** |6 - * |Does not support static and dynamic shape. |Temporally removed due to changes in onnx 1.8.1. |
+| **Unsqueeze** |6 - * |Does not support static and dynamic shape. Does not support int4 and uint4. |Temporally removed due to changes in onnx 1.8.1. |
 | **Upsample** |7 - * |Input `X` and `Y` must have static shape. | |
 | **Where** |9 - * | | |
 | **Xor** |7 - * | | |

diff --git a/test/backend/inference_backend.py b/test/backend/inference_backend.py
@@ -395,7 +395,7 @@ def get_test_models():
         },
         # ==OP== Cast
         # ==MIN== 6
-        # ==LIM== Cast only between float and double types. Only ppc64le and MacOS platforms support float16.
+        # ==LIM== Cast only between float and double types. Only ppc64le and MacOS platforms support float16. Does not support int4 and uint4.
         "test_cast_FLOAT_to_DOUBLE_cpu": {
             STATIC_SHAPE: {},
             DYNAMIC_SHAPE: {-1: {-1}},
@@ -434,7 +434,7 @@ def get_test_models():
         "test_cast_STRING_to_FLOAT_cpu": {},  # appears unsupported at this time
         # ==OP== CastLike
         # ==MIN== 19
-        # ==LIM== CastLike only between float and double types. Only ppc64le and MacOS platforms support float16.
+        # ==LIM== CastLike only between float and double types. Only ppc64le and MacOS platforms support float16. Does not support int4 and uint4.
         "test_castlike_FLOAT_to_DOUBLE_cpu": {
             STATIC_SHAPE: {},
             DYNAMIC_SHAPE: {-1: {-1}},
@@ -615,10 +615,12 @@ def get_test_models():
         },
         # ==OP== Constant
         # ==MIN== 1
+        # ==LIM== Does not support int4 and uint4.
         # By def, no dynamic shapes.
         "test_constant_cpu": {STATIC_SHAPE: {}},
         # ==OP== ConstantOfShape
         # ==MIN== 9
+        # ==LIM== Does not support int4 and uint4.
         # By def, no dynamic shapes.
         "test_constantofshape_float_ones_cpu": {STATIC_SHAPE: {}},
         "test_constantofshape_int_zeros_cpu": {STATIC_SHAPE: {}},
@@ -790,7 +792,7 @@ def get_test_models():
         },
         # ==OP== DequantizeLinear
         # ==MIN== 10
-        # ==LIM== Only support for per-tensor or layer dequantization. No support for per-axis dequantization.
+        # ==LIM== Only support for per-tensor or layer dequantization. No support for per-axis dequantization. Does not support int4 and uint4.
         # "test_dequantizelinear_axis_cpu": {STATIC_SHAPE:{}, DYNAMIC_SHAPE:{-1:{-1}}, CONSTANT_INPUT:{-1}},
         "test_dequantizelinear_cpu": {
             STATIC_SHAPE: {},
@@ -981,6 +983,7 @@ def get_test_models():
         },
         # ==OP== Flatten
         # ==MIN== 1
+        # ==LIM== Does not support int4 and uint4.
         "test_flatten_axis0_cpu": {
             STATIC_SHAPE: {},
             DYNAMIC_SHAPE: {-1: {-1}},
@@ -1358,7 +1361,7 @@ def get_test_models():
         },
         # ==OP== Identity
         # ==MIN== 16
-        # ==LIM== Sequence identity not supported.
+        # ==LIM== Sequence identity not supported. Does not support int4 and uint4.
         "test_identity_cpu": {
             STATIC_SHAPE: {},
             DYNAMIC_SHAPE: {-1: {-1}},
@@ -1368,7 +1371,7 @@ def get_test_models():
         # "test_identity_opt_cpu": {STATIC_SHAPE:{}, DYNAMIC_SHAPE:{-1:{-1}}, CONSTANT_INPUT:{-1}},
         # ==OP== If
         # ==MIN== 16
-        # ==LIM== Sequence and Optional outputs are not supported.
+        # ==LIM== Sequence and Optional outputs are not supported. Does not support int4 and uint4.
         "test_if_cpu": {
             STATIC_SHAPE: {},
             DYNAMIC_SHAPE: {-1: {-1}},
@@ -1785,7 +1788,7 @@ def get_test_models():
         },
         # ==OP== Loop
         # ==MIN== 1
-        # ==LIM== Input must have static shape.
+        # ==LIM== Input must have static shape. Does not support int4 and uint4.
         "test_loop11_cpu": {
             STATIC_SHAPE: {},
             # Need to enable ConvertSeqToMemrefPass for dynamic test.
@@ -2264,7 +2267,7 @@ def get_test_models():
         },
         # ==OP== Pad
         # ==MIN== 2
-        # ==LIM== axes input not supported
+        # ==LIM== axes input not supported. Does not support int4 and uint4.
         "test_constant_pad_cpu": {
             STATIC_SHAPE: {},
             DYNAMIC_SHAPE: {0: {-1}},
@@ -2317,7 +2320,7 @@ def get_test_models():
         },
         # ==OP== QuantizeLinear
         # ==MIN== 10
-        # ==LIM== Do not support per-axis and i8 quantization.
+        # ==LIM== Does not support per-axis and i8 quantization. Does not support int4 and uint4.
         # "test_quantizelinear_axis_cpu": {STATIC_SHAPE:{}, DYNAMIC_SHAPE:{-1:{-1}}, CONSTANT_INPUT:{-1}},
         "test_quantizelinear_cpu": {
             STATIC_SHAPE: {},
@@ -2623,7 +2626,7 @@ def get_test_models():
         },
         # ==OP== Reshape
         # ==MIN== 5
-        # ==LIM== allowzero not supported. Input `shape` must have static dimension.
+        # ==LIM== allowzero not supported. Input `shape` must have static dimension. Does not support int4 and uint4.
         "test_reshape_extended_dims_cpu": {
             STATIC_SHAPE: {},
             DYNAMIC_SHAPE: {0: {-1}},
@@ -2802,7 +2805,7 @@ def get_test_models():
         },
         # ==OP== Scan
         # ==MIN== 8
-        # ==LIM== Does not support dynamic shapes.
+        # ==LIM== Does not support dynamic shapes. Does not support int4 and uint4.
         # ==TODO== Precision issue with newer opset, maybe just unsupported. Dynamic shape?
         #  "test_scan_sum_cpu": {STATIC_SHAPE:{}},
         "test_scan9_sum_cpu": {STATIC_SHAPE: {}},
@@ -2859,7 +2862,7 @@ def get_test_models():
         # "test_sequence_insert_at_back_cpu": {STATIC_SHAPE:{}, DYNAMIC_SHAPE:{-1:{-1}}, CONSTANT_INPUT:{-1}},
         # ==OP== Shape
         # ==MIN== 15
-        # ==LIM== Does not support start and end attributes.
+        # ==LIM== Does not support start and end attributes. Does not support int4 and uint4.
         "test_shape_cpu": {
             STATIC_SHAPE: {},
             DYNAMIC_SHAPE: {-1: {-1}},
@@ -2915,6 +2918,7 @@ def get_test_models():
         },
         # ==OP== Size
         # ==MIN== 13
+        # ==LIM== Does not support int4 and uint4.
         "test_size_cpu": {
             STATIC_SHAPE: {},
             DYNAMIC_SHAPE: {-1: {-1}},
@@ -3042,7 +3046,7 @@ def get_test_models():
         },
         # ==OP== Squeeze
         # ==MIN== 1
-        # ==LIM== Does not support static and dynamic shape.
+        # ==LIM== Does not support static and dynamic shape. Does not support int4 and uint4.
         # ==TODO== Temporally removed due to changes in onnx 1.8.1
         # "test_squeeze_cpu": {STATIC_SHAPE:{}, DYNAMIC_SHAPE:{-1:{-1}}, CONSTANT_INPUT:{-1}},
         # "test_squeeze_negative_axes_cpu": {STATIC_SHAPE:{}, DYNAMIC_SHAPE:{-1:{-1}}, CONSTANT_INPUT:{-1}},
@@ -3141,6 +3145,7 @@ def get_test_models():
         },
         # ==OP== Transpose
         # ==MIN== 1
+        # ==LIM== Does not support int4 and uint4.
         "test_transpose_default_cpu": {
             STATIC_SHAPE: {},
             DYNAMIC_SHAPE: {-1: {-1}},
@@ -3286,7 +3291,7 @@ def get_test_models():
         },
         # ==OP== Unsqueeze
         # ==MIN== 1
-        # ==LIM== Does not support static and dynamic shape.
+        # ==LIM== Does not support static and dynamic shape. Does not support int4 and uint4.
         # ==TODO== Temporally removed due to changes in onnx 1.8.1
         # "test_unsqueeze_axis_0_cpu": {STATIC_SHAPE:{}, DYNAMIC_SHAPE:{-1:{-1}}, CONSTANT_INPUT:{-1}},
         # "test_unsqueeze_axis_1_cpu": {STATIC_SHAPE:{}, DYNAMIC_SHAPE:{-1:{-1}}, CONSTANT_INPUT:{-1}},