1, add explicit value cache in emitting indices calculation;
2, move the indices calculation emitting logics into
ConvertTritonGPUOpToLLVMPatternBase to avoid the redundant build cost by
templates. Refer to the discussion in this thread by @LyricZhao :
https://triton-lang.slack.com/archives/C042VBSQWNS/p1671336755922969
Continue the work https://github.com/openai/triton/pull/990
# Background
The `versionMinor` in MmaEncodingAttr holds some states of DotOp's
operands in Volta, while such operands will be modified by some
patterns, making the states out-of-date.
This PR helps to correct the states.
# Implementation
It adds three new patterns:
1. `CollectMmaToUpdateForVolta` helps to collect and build a map holding
the MmaEncodingAttr instances with wrong states and create new correct
ones for them,
2. `UpdateMMAVersionMinorForVolta` helps to replace the Ops generating
the wrong MmaEncodingAttr instances with new correct ones, currently it
supports the following Ops
a. `convert_layout[X -> mma]`
b. `arith.constant SplatAttr : !tensor<mma>`
c. `dot ... : !tensor<mma>`
# Limitation
This PR chooses the mapping way to bypass the IR walk complexity from
the circular dependency between dot_operand[parent] and mma.
We use the MmaEncodingAttr instance as the mapping key, but there might
be multiple DotOp holding different DotOprand(IsMMAv1Row) that have the
same wrong MmaEncodingAttr instance.
To make each DotOp's (wrong) MmaEncodingAttr unique, we might need an ID
field to MmaEncodingAttr.
