Krzysztof Drewniak 2ebd633f14 [mlir][AMDGPU] Add packed 8-bit float conversion ops and lowering ... Define operations that wrap the gfx940's new operations for converting between f32 and registers containing packed sets of four 8-bit floats. Define rocdl operations for the intrinsics and an AMDGPU dialect wrapper around them (to account for the fact that MLIR distinguishes the two float formats at the type level but that the LLVM IR does not). Define an ArithToAMDGPU pass, meant to run before conversion to LLVM, that replaces relevant calls to arith.extf and arith.truncf with the packed operations in the AMDGPU dialect. Note that the conversion currently only handles scalars and vectors of rank <= 1, as we do not have a usecase for multi-dimensional vector support right now. Reviewed By: jsjodin Differential Revision: https://reviews.llvm.org/D152457		2023-09-28 14:44:16 +00:00
..
add-debuginfo-func-scope.mlir
add-linkonce-comdat.mlir	[mlir] Add pass to add comdat to all linkonce functions (#65270)	2023-09-13 13:05:05 +01:00
attach-targets.mlir	[mlir][gpu] Add passes to attach (NVVM|ROCDL) target attributes to GPU Modules	2023-08-12 00:45:26 +00:00
call-intrin.mlir
call-location.mlir	[mlir] Fix verifier for call debug locations	2023-08-09 09:03:57 -07:00
callgraph.mlir	[mlir][llvm] Replace NullOp by ZeroOp (#67183)	2023-09-25 11:11:52 +02:00
canonicalize-typed-pointers.mlir
canonicalize.mlir	[mlir][llvm] Replace NullOp by ZeroOp (#67183)	2023-09-25 11:11:52 +02:00
comdat.mlir
constant-folding.mlir
debuginfo.mlir
dynamic-gep-index-typed-pointers.mlir
dynamic-gep-index.mlir
func.mlir	Add support for MLIR to llvm vscale attribute (#67012)	2023-09-25 14:32:18 +01:00
global-typed-pointers.mlir
global.mlir	[mlir][llvm] Use zeroinitializer for TargetExtType (#66510)	2023-09-18 17:49:36 +02:00
inlining-alias-scopes.mlir
inlining.mlir	[mlir][llvm] Allow inlining for dbg label	2023-09-01 14:55:38 +00:00
invalid-call-location.mlir	[mlir][LLVM] Introduce verfier for call debug locations	2023-08-07 05:53:27 +00:00
invalid-typed-pointers.mlir	[MLIR][LLVM] Add vararg support in LLVM::CallOp and InvokeOp (#67274)	2023-09-28 08:26:45 +02:00
invalid.mlir	[MLIR][LLVM] Add vararg support in LLVM::CallOp and InvokeOp (#67274)	2023-09-28 08:26:45 +02:00
layout-typed-pointers.mlir
layout.mlir
legalize-for-export.mlir
loop-metadata.mlir
mem2reg-dbginfo.mlir
mem2reg-intrinsics.mlir
mem2reg.mlir	[mlir][llvm] Replace NullOp by ZeroOp (#67183)	2023-09-25 11:11:52 +02:00
nvvm-typed-pointers.mlir
nvvm.mlir	[MLIR][NVVM] Add CTA Cluster barrier intrinsics for sm_90	2023-09-01 16:39:52 +02:00
opaque-ptr.mlir
optimize-for-nvvm.mlir
parameter-attrs-invalid-typed-pointers.mlir
parameter-attrs-invalid.mlir	[mlir] Move FunctionInterfaces to Interfaces directory and inherit from CallableOpInterface	2023-08-31 11:28:23 +00:00
request-c-wrappers.mlir
rocdl.mlir	[mlir][AMDGPU] Add packed 8-bit float conversion ops and lowering	2023-09-28 14:44:16 +00:00
roundtrip-typed-pointers.mlir	[mlir][llvm] Replace NullOp by ZeroOp (#67183)	2023-09-25 11:11:52 +02:00
roundtrip.mlir	[MLIR][LLVM] Add vararg support in LLVM::CallOp and InvokeOp (#67274)	2023-09-28 08:26:45 +02:00
sroa-intrinsics.mlir
sroa-statistics.mlir
sroa.mlir
tbaa-invalid.mlir
tbaa-roundtrip.mlir
terminator.mlir
type-consistency.mlir
types-invalid-typed-pointers.mlir
types-invalid.mlir	[mlir] Add helper method to print and parse cyclic attributes and types (#65210)	2023-09-04 18:19:18 +02:00
types-typed-pointers.mlir
types.mlir