[WIP] [AMD] Emit AMD specific intrinsics for dot

[binarman]

This PR:

• Makes AccelerateAMDMatmul pass to emit FMA i8xi8->i32 and fp16xfp16->fp32 cases
• Extends AMD FMA Dot code generation with new v_dot instructions for fp16xfp16 and int8 dtypes

This PR is a part of PR series. Final goal is to improve efficiency of small dot operations and bypass as much shared memory accesses as possible.

Rough list of PRs:

• Basic FMA dot fixes, dot 3d support and relaxing small dimensions for dot [Backend] Improve dot support to target FMA #4516
• Blocked->dotOp shared memory bypassing [Backend] Bypass conversion for suitable blocked to dotOperand layout #4538
• Accelerate AMD Matmul + emit dot operations (this PR) [WIP] [AMD] Emit AMD specific intrinsics for dot  #4594
• Layout optimization, so operand B is loaded in proper mfma layout and do not need to go through LDS [WIP] Optimize fma dot #4581
• Vectorization optimization of dot operands/results (in case llvm can not do this internally)
• Reduction operation hoisting out of the K loop (reduction operation is a byproduct of layout optimization step) Hoist reduction outside a loop #4559

[binarman]

This PR depends on #4516

[binarman]

Closing this PR for now.
Will reopen it if base PRs #4516 is merged.