Summary:

This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes:
- swapping with q/dq nodes to do it in lower bitwidth
- becoming slice_nop when possible (through memory planning constraints)
- a few simplification passes on slices
- possibly finding patterns with slice/cat being a nop
- we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand

Differential Revision: D73312379

Summary:
Pull Request resolved: #10318

This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes:
- swapping with q/dq nodes to do it in lower bitwidth
- becoming slice_nop when possible (through memory planning constraints)
- a few simplification passes on slices
- possibly finding patterns with slice/cat being a nop
- we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand

Differential Revision: D73312379

Summary:

This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes:
- swapping with q/dq nodes to do it in lower bitwidth
- becoming slice_nop when possible (through memory planning constraints)
- a few simplification passes on slices
- possibly finding patterns with slice/cat being a nop
- we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand

Differential Revision: D73312379

Summary:
Pull Request resolved: #10318

This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes:
- swapping with q/dq nodes to do it in lower bitwidth
- becoming slice_nop when possible (through memory planning constraints)
- a few simplification passes on slices
- possibly finding patterns with slice/cat being a nop
- we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand

Differential Revision: D73312379

Summary:

This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes:
- swapping with q/dq nodes to do it in lower bitwidth
- becoming slice_nop when possible (through memory planning constraints)
- a few simplification passes on slices
- possibly finding patterns with slice/cat being a nop
- we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand

Reviewed By: zonglinpeng

Differential Revision: D73312379

Summary:

This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes:
- swapping with q/dq nodes to do it in lower bitwidth
- becoming slice_nop when possible (through memory planning constraints)
- a few simplification passes on slices
- possibly finding patterns with slice/cat being a nop
- we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand

Reviewed By: zonglinpeng

Differential Revision: D73312379

Summary:
Pull Request resolved: #10318

This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes:
- swapping with q/dq nodes to do it in lower bitwidth
- becoming slice_nop when possible (through memory planning constraints)
- a few simplification passes on slices
- possibly finding patterns with slice/cat being a nop
- we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand

Reviewed By: zonglinpeng

Differential Revision: D73312379

Summary:

This is useful for a few reasons, which are all related to the fact that we have a lot of things in place for slice ops, so the compiler can optimize much better if we replace `split_with_sizes`. That includes:
- swapping with q/dq nodes to do it in lower bitwidth
- becoming slice_nop when possible (through memory planning constraints)
- a few simplification passes on slices
- possibly finding patterns with slice/cat being a nop
- we have an optimized slice op on HiFi already. We will get the split op soon to be fair, we can do some profiling then, but the above points will still stand

Reviewed By: zonglinpeng

Differential Revision: D73312379