From 79f13b06b05a714ada05affe23b8abfa52509fe2 Mon Sep 17 00:00:00 2001 From: Mengwei Liu Date: Fri, 4 Oct 2024 15:11:14 -0700 Subject: [PATCH] Update compiler-backend-dialect.md (#5890) Summary: Update the backend operator list Pull Request resolved: https://github.com/pytorch/executorch/pull/5890 Reviewed By: helunwencser Differential Revision: D63916244 Pulled By: larryliu0820 fbshipit-source-id: b7dee4939912e0d0bcfa2a5f51ac3d7b07d89954 (cherry picked from commit d9aeca556566104c2594ec482a673b9ec5b11390) --- docs/source/compiler-backend-dialect.md | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/docs/source/compiler-backend-dialect.md b/docs/source/compiler-backend-dialect.md index 0a8ad973a7..0ab8fe79f2 100644 --- a/docs/source/compiler-backend-dialect.md +++ b/docs/source/compiler-backend-dialect.md @@ -145,6 +145,12 @@ There are the backend operators currently using `bind_pattern_to_op` API. * `executorch_prims::floordiv.int(SymInt a, SymInt b) -> SymInt` * pattern: builtin.floordiv * backend: executor +* `executorch_prims::truediv.int(Scalar a, Scalar b) -> Scalar` + * pattern: builtin.div + * backend: executor +* `executorch_prims::sym_float.Scalar(Scalar a) -> Scalar` + * pattern: builtin.float + * backend: executor * `executorch_prims::gt.int(SymInt a, SymInt b) -> bool` * pattern: builtin.gt * backend: executor @@ -160,6 +166,12 @@ There are the backend operators currently using `bind_pattern_to_op` API. * `executorch_prims::eq.int(SymInt a, SymInt b) -> bool` * pattern: builtin.eq * backend: executor +* `executorch_prims::mod.Scalar(SymInt a, SymInt b) -> SymInt` + * pattern: builtin.divmod + * backend: executor +* `executorch_prims::neg.Scalar(Scalar a) -> Scalar` + * pattern: operator.ne + * backend: executor * `quantized_decomposed::embedding_byte(Tensor weight, Tensor weight_scales, Tensor weight_zero_points, int weight_quant_min, int weight_quant_max, Tensor indices) -> Tensor` * pattern: [source](https://github.com/pytorch/executorch/blob/main/exir/passes/_quant_patterns_and_replacements.py) * backend: quantization