maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/mlir/test/Dialect
History
Benoit Jacob 20daedacca 2d Arm Neon sdot op, and lowering to the intrinsic. 
This adds Sdot2d op, which is similar to the usual Neon
intrinsic except that it takes 2d vector operands, reflecting the
structure of the arithmetic that it's performing: 4 separate
4-dimensional dot products, whence the vector<4x4xi8> shape.

This also adds a new pass, arm-neon-2d-to-intr, lowering
this new 2d op to the 1d intrinsic.

Reviewed By: nicolasvasilache

Differential Revision: https://reviews.llvm.org/D102504
 		2021-06-10 14:36:39 -07:00
..
AMX Update syntax for amx.tile_muli to use two Unit attr to mark the zext case 2021-03-20 04:12:24 +00:00
Affine [MLIR][MemRef] Only allow fold of cast for the pointer operand, not the value 2021-06-08 11:43:09 -04:00
ArmNeon 2d Arm Neon sdot op, and lowering to the intrinsic. 2021-06-10 14:36:39 -07:00
ArmSVE [mlir][ArmSVE] Add basic load/store operations 2021-06-09 15:53:40 +01:00
Async [mlir] Async: Add error propagation support to async groups 2021-05-27 09:35:11 -07:00
Builtin [mlir] Add a new builtin `unrealized_conversion_cast` operation 2021-01-20 16:28:18 -08:00
Complex [mlir] Fold complex.create(complex.re(op), complex.im(op)) 2021-05-26 14:02:53 +02:00
DLTI [mlir] support data layout specs on ModuleOp 2021-03-24 15:13:38 +01:00
GPU [mlir][gpu] Add op to create MMA constant matrix 2021-06-10 08:34:04 -07:00
LLVMIR [mlir] make LLVMPointerType implement the data layout type interface 2021-06-10 11:24:16 +02:00
Linalg Folds linalg.pad_tensor with zero padding 2021-06-09 15:39:40 -07:00
Math [mlir] Check generated IR of math_polynomial_approx.mlir 2021-05-05 16:42:48 -07:00
MemRef [MLIR][MemRef] Only allow fold of cast for the pointer operand, not the value 2021-06-08 11:43:09 -04:00
OpenACC [mlir][openacc] Add canonicalization for standalone data operations for if condition 2021-06-07 11:40:59 -04:00
OpenMP [MLIR][OpenMP] Pretty printer and parser for omp.wsloop 2021-03-18 13:37:01 +00:00
PDL [mlir][PDL] Add support for variadic operands and results in PDL 2021-03-16 13:20:18 -07:00
PDLInterp [mlir][PDL] Add support for variadic operands and results in the PDL Interpreter 2021-03-16 13:20:19 -07:00
Quant [testsuite] Make testsuite more stable vs canonicalization change. NFC. 2021-03-19 18:11:12 -07:00
SCF [Canonicalize] Switch the default setting to "top down". 2021-05-25 13:42:11 -07:00
SPIRV [mlir][spirv] Use SingleBlock + NoTerminator for spv.module 2021-06-09 14:00:06 -04:00
Shape [MLIR][Shape] Remove duplicate operands of `shape.assuming_all` op 2021-05-31 14:37:55 +02:00
SparseTensor [mlir][sparse] add option for 32-bit indices in scatter/gather 2021-06-04 16:57:12 -07:00
Standard [MLIR] Conditional Branch Argument Propagation 2021-06-07 13:33:10 -04:00
Tensor [mlir][Tensor] Add folding for tensor.from_elements 2021-05-11 00:42:45 +02:00
Tosa [mlir][tosa] Remove tosa.identityn operator 2021-05-12 12:46:22 -07:00
Vector [Canonicalize] Switch the default setting to "top down". 2021-05-25 13:42:11 -07:00
X86Vector [mlir][vector][avx] add AVX dot product to X86Vector dialect with lowering 2021-04-15 15:01:39 -07:00
traits.mlir [mlir] Generalize broadcastable trait operands 2020-01-20 13:02:14 -08:00