colin
/
mlir-hlo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
mlir-hlo/lib/Dialect/mhlo/IR
History
Feiwen 3afbe312f8 PR #49919: [MLIR][DISC] pattern conversion from tf2mhlo: ConvertUnpackOpDynamic, ConvertSignOpDynamic, ConvertSigmoidGradOpDynamic 
Imported from GitHub PR https://github.com/tensorflow/tensorflow/pull/49919

We are porting our MLIR-based dynamic shape compiler to tf community (From OP def, Patttern, to Optimization pass, etc).
This is the 5th PR about tf2mhlo pattern conversion, which including ConvertUnpackOpDynamic, ConvertSignOpDynamic, ConvertSigmoidGradOpDynamic.
The rest pattern conversions we will add:
- ConvertSqueezeOpxxx
- ConvertStridedSliceOpxxx
- ConvertPrintOp
Copybara import of the project:

--
21b3c3eb05b12956bcdb8b98cc54d9371dbf034d by azazhu <azazhu@gmail.com>:

[MLIR][DISC] pattern conversion from tf2mhlo: ConvertUnpackOpDynamic, ConvertSignOpDynamic, ConvertSigmoidGradOpDynamic

--
634630a4e2e426357290650bd579b35efecab5b3 by azazhu <azazhu@gmail.com>:

[MLIR][DISC] refine ConvertUnpackOpDynamic, ConvertSignOpDynamic, ConvertSigmoidGradOpDynamic

--
39a2bedd6dafb369ae960c5197b7a352bfdfbc80 by azazhu <azazhu@gmail.com>:

add RealDynamicSliceOp's canonicalize and fix CI

--
a1c38dd0963d602ed4812da0d77a096a95920ddb by azazhu <azazhu@gmail.com>:

fix CI for ConvertUnpackOpDynamic

--
5a8b4eb389ed6dc554104356c37f2f1550802b8c by azazhu <azazhu@gmail.com>:

fix typo in ConvertSigmoidGradOpDynamic

PiperOrigin-RevId: 379521079
 		2021-06-15 10:33:32 -07:00
..
CMakeLists.txt PR #50191: [MLIR][DISC] Add RAL (Runtime abstraction layer) Dialect 2021-06-14 11:27:43 -07:00
chlo_canonicalize.td Add chlo.constant_like op which splats a constant to shape of operand 2020-08-11 14:54:48 -07:00
chlo_ops.cc PR #49454: [MLIR][DISC] Upgrade to use the new `reifyReturnTypeShapes` interface. 2021-05-24 10:11:55 -07:00
disc_ral_ops.cc PR #50191: [MLIR][DISC] Add RAL (Runtime abstraction layer) Dialect 2021-06-14 11:27:43 -07:00
hlo_ops.cc PR #49919: [MLIR][DISC] pattern conversion from tf2mhlo: ConvertUnpackOpDynamic, ConvertSignOpDynamic, ConvertSigmoidGradOpDynamic 2021-06-15 10:33:32 -07:00
hlo_ops_base_enums.cc [MLIR:HLO] Generate enum decls for HLO and LHLO GPU dialects. 2020-12-02 11:39:23 -08:00
hlo_ops_base_structs.cc [HLO] Add custom print/parse for convolution dimension numbers (in LMHLO) 2021-05-12 08:52:46 -07:00
hlo_ops_common.cc [HLO] Add AllReduceScatter to MHLO and LMHLO dialects. 2021-06-14 09:37:07 -07:00
hlo_patterns.td Restrict canonicalization to avoid changing type 2021-03-16 16:54:05 -07:00
infer_fusibility_op_interface.cc More cleanup in mlir-hlo to prepare for the standalone build 2020-08-03 19:28:00 -07:00
init.cc Add GPU specific LMHLO level ops 2020-10-14 11:23:55 -07:00
lhlo_gpu_ops.cc [XLA:GPU] Add AllReduce{Start,Done} to MLIR LHLO dialect. 2021-06-15 03:55:19 -07:00
lhlo_gpu_ops_enums.cc [MLIR:HLO] Generate enum decls for HLO and LHLO GPU dialects. 2020-12-02 11:39:23 -08:00
lhlo_gpu_ops_structs.cc Make LMHLO's Dot have the same power as MHLO's DotGeneral. 2020-10-15 15:09:06 -07:00
lhlo_ops.cc [XLA:GPU] Add AllReduce{Start,Done} to MLIR LHLO dialect. 2021-06-15 03:55:19 -07:00
lhlo_ops_structs.cc [MLIR:LHLO] Add optional call target arg mapping to LMHLO CustomCall operations. 2021-02-22 08:43:00 -08:00
mhlo_canonicalize.td PR #49919: [MLIR][DISC] pattern conversion from tf2mhlo: ConvertUnpackOpDynamic, ConvertSignOpDynamic, ConvertSigmoidGradOpDynamic 2021-06-15 10:33:32 -07:00