Commit Graph

Select branches

Hide Pull Requests

master

Mono Color

• eb8d5a5e39 Integrate LLVM at llvm/llvm-project@b92a39ac13 A. Unique TensorFlower 2021-01-29 00:30:25 -0800
• 74b103fedf Integrate LLVM at llvm/llvm-project@081c1db02d A. Unique TensorFlower 2021-01-28 22:32:38 -0800
• c915b698b9 Integrate LLVM at llvm/llvm-project@e29552c5af A. Unique TensorFlower 2021-01-28 17:35:27 -0800
• c97cff9a7b [XLA:GPU] Migrate AllReduce thunk emission to MLIR. Rahul Joshi 2021-01-28 10:04:59 -0800
• 30ce82790d Upstream mhlo.reduce lowering to Linalg to MHLO repo. Hanhan Wang 2021-01-28 05:44:49 -0800
• 39589add22 Use the correct shape when converting mhlo.reshape Lei Zhang 2021-01-28 05:36:37 -0800
• e0a7be7fb1 [MLIR][CHLO] Add `chlo.lgamma` and lowering to `hlo` A. Unique TensorFlower 2021-01-28 04:33:55 -0800
• c3ddcd6c7f [MLIR][CHLO] Implement type inference for `is_inf`-like operations in CHLO A. Unique TensorFlower 2021-01-28 01:35:42 -0800
• fe2e5a175f [MLIR][HLO] Implement type inference for `is_finite` op A. Unique TensorFlower 2021-01-28 00:55:03 -0800
• c653db73c5 Integrate LLVM at llvm/llvm-project@c85b6bf33c A. Unique TensorFlower 2021-01-27 11:44:24 -0800
• d77c9ad6fa [MLIR][CHLO] Add `is_inf`, `is_pos_inf`, and `is_neg_inf` to CHLO dialect A. Unique TensorFlower 2021-01-27 08:59:58 -0800
• f4f728f18e Add SameOperandsAndResultShape trait to ConvertOp and IsFiniteOp. Adrian Kuegel 2021-01-27 05:09:01 -0800
• fa059259bc Add template for tf.Cast Adrian Kuegel 2021-01-27 04:48:55 -0800
• 44deae2aa1 [MLIR:HLO] Extend AllReduce to support multiple inputs and results (to model tuples). - Instead of SameTypeOperands, add custom verification to check if operands and results pairwise have the same type. Rahul Joshi 2021-01-26 17:23:49 -0800
• 471fc63c11 Integrate LLVM at llvm/llvm-project@f3f3c9c254 A. Unique TensorFlower 2021-01-25 09:48:19 -0800
• f6b24a6d54 [mlir][hlo] Make min/max always propagate NaNs Benjamin Kramer 2021-01-25 09:03:21 -0800
• b1438eebcb [mlir][hlo] Make min/max always propagate NaNs A. Unique TensorFlower 2021-01-25 05:42:24 -0800
• 6af4bccfde [mlir][hlo] Make min/max always propagate NaNs Benjamin Kramer 2021-01-25 05:14:30 -0800
• 0860e8de9b Integrate LLVM at llvm/llvm-project@0057cc5a21 A. Unique TensorFlower 2021-01-25 04:14:16 -0800
• e192d2a764 Integrate LLVM at llvm/llvm-project@e27197f360 A. Unique TensorFlower 2021-01-22 13:48:12 -0800
• 41c468ca52 Integrate LLVM at llvm/llvm-project@06f8a49693 A. Unique TensorFlower 2021-01-22 10:14:19 -0800
• dfafaac954 Integrate LLVM at llvm/llvm-project@85e7578c6d Tres Popp 2021-01-22 08:18:22 -0800
• b865148492 Integrate LLVM at llvm/llvm-project@def99ad68b Tres Popp 2021-01-22 05:29:24 -0800
• ae2d46414d [MLIR][KernelGen] Add erfc kernel for f16 A. Unique TensorFlower 2021-01-22 03:37:28 -0800
• ef8ccdaebc [MLIR] Add mhlo.logistic lowering to linalg A. Unique TensorFlower 2021-01-22 03:02:13 -0800
• c846f925d4 [MLIR][KernelGen] Add chlo.erfc lowering for f32 A. Unique TensorFlower 2021-01-22 02:32:39 -0800
• 56758a9562 [MLIR][KernelGen] Lower mhlo.log_plus_one to std.log1p A. Unique TensorFlower 2021-01-22 02:16:26 -0800
• f6bf9d5780 Integrate LLVM at llvm/llvm-project@2cb130f766 Tres Popp 2021-01-22 01:30:47 -0800
• 7644a47a69 Integrate LLVM at llvm/llvm-project@6699029b67 Tres Popp 2021-01-21 22:58:04 -0800
• d1c785381d [XLA/GPU] Add XLA HLO -> LMHLO conversion to several ops, and implement them in XLA/GPU. Tim Shen 2021-01-21 19:56:11 -0800
• ae10640d78 Integrate LLVM at llvm/llvm-project@39db5753f9 A. Unique TensorFlower 2021-01-21 17:43:06 -0800
• 3c88adce7e Integrate LLVM at llvm/llvm-project@9dd5aea1e0 A. Unique TensorFlower 2021-01-21 13:07:41 -0800
• e2d60e01ba Fix CMakeLists.txt Hanhan Wang 2021-01-21 12:40:46 -0800
• 8708e2c8d8 Integrate LLVM at llvm/llvm-project@0eeb15741b A. Unique TensorFlower 2021-01-21 08:42:15 -0800
• 61cfb8c690 Integrate LLVM at llvm/llvm-project@726de41e2b Tres Popp 2021-01-21 07:24:11 -0800
• 1a37078132 [MLIR][KernelGen] Add chlo.erfc lowerings for f64 A. Unique TensorFlower 2021-01-21 04:41:21 -0800
• bec2e625a2 [MLIR][KernelGen] Add approximation lowering for mhlo.erf operation on f64 A. Unique TensorFlower 2021-01-21 02:47:43 -0800
• 5bbe5d348c Integrate LLVM at llvm/llvm-project@71635ea5ff Tres Popp 2021-01-21 02:45:07 -0800
• 7aa64ee0b7 [MLIR] Migrate TF from STD complex ops to ComplexDialect. Alexander Belyaev 2021-01-21 01:21:23 -0800
• 46112c95c6 Use `uitofp` when converting a boolean to floating-point. Hanhan Wang 2021-01-21 00:14:31 -0800
• cf08128862 Integrate LLVM at llvm/llvm-project@e996f1d419 A. Unique TensorFlower 2021-01-20 21:58:11 -0800
• 70a351f301 Add chlo.acosh operation and associated lowerings. Stephan Herhut 2021-01-20 11:42:12 -0800
• a7e645f37e Fix incorrect include Jacques Pienaar 2021-01-20 10:23:35 -0800
• ba0346b071 Integrate LLVM at llvm/llvm-project@96ef4f307d Tres Popp 2021-01-20 07:08:32 -0800
• ec5f5667e1 [MLIR][KernelGen] Add `tf.Asinh` kernels and complete their lowerings A. Unique TensorFlower 2021-01-20 05:29:46 -0800
• 0e85b4d511 [MLIR][KernelGen] Add `tf.Asinh` kernels and complete their lowerings A. Unique TensorFlower 2021-01-19 10:50:33 -0800
• 96fb617413 [MLIR][KernelGen] Add erf kernel and missing lowering for f16 type A. Unique TensorFlower 2021-01-18 08:19:56 -0800
• 9e07bdf4ea [HLO] Move `SameOperandsAndResultShape` trait to Unary/BinaryElemenwiseOp classes. Alexander Belyaev 2021-01-18 06:46:28 -0800
• c11ea4ef5a [MLIR][KernelGen] Add `tf.Atanh` kernels A. Unique TensorFlower 2021-01-18 05:13:02 -0800
• ba2ee556f1 Handle negative exponents for lowering of hlo.pow Tres Popp 2021-01-18 03:46:41 -0800
• 3763740910 [MLIR][KernelGen] Add erf kernel for f32 arguments and missing lowerings A. Unique TensorFlower 2021-01-18 03:34:19 -0800
• b5dc600860 [MLIR] Fix line wraps in hlo_ops.td A. Unique TensorFlower 2021-01-18 01:40:42 -0800
• 6cb01c89b7 Integrate LLVM at llvm/llvm-project@8456c3a789 A. Unique TensorFlower 2021-01-16 01:23:11 -0800
• 38a7c136ae Integrate LLVM at llvm/llvm-project@86e604c4d6 A. Unique TensorFlower 2021-01-15 16:24:05 -0800
• 92a203f4f0 Integrate LLVM at llvm/llvm-project@104a9f99cc Stephan Herhut 2021-01-15 07:41:04 -0800
• bcdb3c3548 [MLIR] Lower mhlo.clamp to linalg A. Unique TensorFlower 2021-01-15 06:44:28 -0800
• 2af0dcd3e7 Integrate LLVM at llvm/llvm-project@7803636057 Stephan Herhut 2021-01-15 06:04:49 -0800
• 791d5afd28 [MLIR][KernelGen] Add `tf.Asinh` kernels and complete their lowerings A. Unique TensorFlower 2021-01-15 05:25:49 -0800
• 316f630728 [MLIR][KernelGen] Add cosh kernels and tests A. Unique TensorFlower 2021-01-15 04:30:14 -0800
• 9a1abaa212 Integrate LLVM at llvm/llvm-project@e2d7d3cb0e A. Unique TensorFlower 2021-01-14 18:04:30 -0800
• 4d62cd4dee Integrate LLVM at llvm/llvm-project@6abbba3fca Stephan Herhut 2021-01-14 06:52:27 -0800
• 5fff92f2b4 Integrate LLVM at llvm/llvm-project@ed205f63b4 Stephan Herhut 2021-01-14 02:35:10 -0800
• 3b9981fc60 Integrate LLVM at llvm/llvm-project@f4f158b2f8 A. Unique TensorFlower 2021-01-13 20:15:29 -0800
• 14ae39bc95 Integrate LLVM at llvm/llvm-project@17863614da A. Unique TensorFlower 2021-01-13 10:52:14 -0800
• 181d2cad31 [MLIR][KernelGen] Add `tf.Log1p` kernel and tests A. Unique TensorFlower 2021-01-13 05:36:19 -0800
• 300a7c11ce Upstream mhlo.dot_general lowering to Linalg to MHLO repo Hanhan Wang 2021-01-12 22:07:29 -0800
• 97a618f91a Integrate LLVM at llvm/llvm-project@6f4d460762 A. Unique TensorFlower 2021-01-12 16:36:18 -0800
• 0651d58edf [MLIR:HLO] Change LHLO Outfeed to support multiple inputs. Rahul Joshi 2021-01-12 14:12:43 -0800
• 0b85d5c510 [MLIR][KernelGen] Add asin kernels and tests A. Unique TensorFlower 2021-01-12 09:01:28 -0800
• b0e0ca830c Integrate LLVM at llvm/llvm-project@c8a914db5c Stephan Herhut 2021-01-12 07:07:37 -0800
• d52092a5cc Integrate LLVM at llvm/llvm-project@aefeb5f136 A. Unique TensorFlower 2021-01-11 20:23:46 -0800
• 5359ea620a Integrate LLVM at llvm/llvm-project@89878e8c96 Stephan Herhut 2021-01-11 11:07:25 -0800
• 8f58f844e5 Upstream mhlo.dot lowering to Linalg to MHLO repo. Hanhan Wang 2021-01-11 10:33:14 -0800
• 180f917446 [KERNEL_GEN] Add a pattern for hlo.dyn_broadcast->linalg to enable is_inf kernel. Alexander Belyaev 2021-01-11 10:11:39 -0800
• ecf1bf5132 [KERNEL_GEN] Add a canonicalization pattern to drop a redundant dynamic reshape. Alexander Belyaev 2021-01-11 06:36:14 -0800
• 47848764a5 Change hardcoded external/ include to match repository name Geoffrey Martin-Noble 2021-01-08 12:06:39 -0800
• ac38478350 Integrate LLVM at llvm/llvm-project@bcbdeafa9c Alexander Belyaev 2021-01-08 07:55:56 -0800
• 6c42f54298 [KERNEL_GEN] Restrict broadcast -> reshape canonicalization to identity dims. Alexander Belyaev 2021-01-07 15:29:30 -0800
• a8c0f2b944 Integrate LLVM at llvm/llvm-project@7f7b0dc4e1 Alexander Belyaev 2021-01-07 09:22:51 -0800
• 49a540bf72 Integrate LLVM at llvm/llvm-project@d38a0258a5 Alexander Belyaev 2021-01-05 08:01:06 -0800
• 095dc28e5c [KERNEL_GEN] Add canonicalizaton pattern to drop a redundant broadcast op. Alexander Belyaev 2021-01-05 02:59:52 -0800
• 2727ed4cf2 Integrate LLVM at llvm/llvm-project@8bee4d4e8f A. Unique TensorFlower 2020-12-31 07:33:38 -0800
• f8fbfdd061 Integrate LLVM at llvm/llvm-project@51a292d994 A. Unique TensorFlower 2020-12-30 15:44:28 -0800
• 181f19881b Integrate LLVM at llvm/llvm-project@2016f2c8a7 A. Unique TensorFlower 2020-12-30 09:10:25 -0800
• 2e215f75a5 Integrate LLVM at llvm/llvm-project@8001dcbd50 A. Unique TensorFlower 2020-12-29 22:40:12 -0800
• a9e2b45bd5 Integrate LLVM at llvm/llvm-project@930c74f12d A. Unique TensorFlower 2020-12-29 08:28:35 -0800
• 50fc56a208 Fix header include. Adrian Kuegel 2020-12-24 01:39:24 -0800
• b0bf2ef45b Integrate LLVM at llvm/llvm-project@c3acda0798 A. Unique TensorFlower 2020-12-23 23:53:08 -0800
• e3754d7b5c [MLIR:HLO] Change LHLO Infeed to support multiple outputs. Rahul Joshi 2020-12-23 14:55:15 -0800
• bd8e768e23 [MLIR:HLO] Rename LMHLO Infeed and Outfeed to InfeedOp and OutfeedOp. Rahul Joshi 2020-12-23 11:35:54 -0800
• 8252eafa99 [NFC] Factor out repeated code out of InferFusibilityOpInterface. Rahul Joshi 2020-12-22 12:03:07 -0800
• bc367971ec [MLIR:LHLO_GPU] Add additional constraints for batchnorm - Constrain batchnorm inputs and outputs to be fp memrefs. Rahul Joshi 2020-12-22 11:29:31 -0800
• ccdd07f8e4 Prepare to remove tensor_load and tensor_store special handling from hlo to lhlo legalization. Stephan Herhut 2020-12-22 06:27:57 -0800
• c4accdcc41 Integrate LLVM at llvm/llvm-project@1b97cdf885 A. Unique TensorFlower 2020-12-21 23:48:24 -0800
• a42213b870 Define lowering of [l]mhlo.pow. Tres Popp 2020-12-21 15:26:38 -0800
• 99a0ee378c Integrate LLVM at llvm/llvm-project@511cfe9441 A. Unique TensorFlower 2020-12-21 09:48:39 -0800
• 9fd87f5939 Integrate LLVM at llvm/llvm-project@f4c8b80318 A. Unique TensorFlower 2020-12-21 05:33:01 -0800
• ee74c519a6 Integrate LLVM at llvm/llvm-project@17b3ff511c A. Unique TensorFlower 2020-12-18 21:58:19 -0800
• 1e36f6d38d Integrate LLVM at llvm/llvm-project@9ca67d7f44 A. Unique TensorFlower 2020-12-18 13:07:53 -0800
• 9466cffaf3 Restrict CHLO Acos and Sinh op lowering to non complex types Smit Hinsu 2020-12-18 11:31:03 -0800