salijagic
86 lines
2.8 KiB
Markdown
86 lines
2.8 KiB
Markdown
# Optimization: Inlining
|
|
|
|
- **Author**: Smail
|
|
- **Predecessor**: variant_inlining_7_symmetry_2.cpp
|
|
- **File(s)**: variants/variant_inlining_7_symmetry_2_ilp_1.cpp
|
|
- **Status**: TBA
|
|
|
|
## What this changes
|
|
|
|
Implemented ILP with loop unrolling and accumulators, each factor 4.
|
|
|
|
|
|
## Code (relevant snippet)
|
|
|
|
TBD - see `variants/variant_inlining_7_symmetry_1.cpp` for the final version, and the
|
|
individual file headers for the incremental steps.
|
|
|
|
## Benchmark
|
|
|
|
Conditions: single run (TODO: switch to min-of-N), N_ITER=1000,
|
|
-O3 -march=native -flto. Predecessor reference for the same config is the
|
|
baseline row.
|
|
|
|
### x86
|
|
|
|
**Machine**:
|
|
|
|
```
|
|
Processors: 16 x AMD Ryzen AI 7 350 w/ Radeon 860M
|
|
Memory: 32 GiB of RAM (30.6 GiB usable)
|
|
Graphics Processor: AMD Radeon 860M Graphics
|
|
Manufacturer: LENOVO
|
|
Product Name: 83HX
|
|
System Version: IdeaPad Slim 5 14AKP10
|
|
```
|
|
|
|
**Frequency**: 2 GHz
|
|
|
|
Existing single-point measurement (N unspecified, kept from the previous
|
|
OPTIMIZATIONS.md; W matches roughly N=120 at N_ITER=1000):
|
|
|
|
| Variant | W(n) [Flops] | T(n) [Cycles] | Performance [Flops/Cycle] |
|
|
| -------- | ---------------- | -------------- | ------------------------- |
|
|
| Baseline | 1'058'400'000.00 | 850'352'900.00 | 1.24 |
|
|
| Inlining | 1'058'400'000.00 | 756'088'260.00 | 1.40 |
|
|
| Symmetry | | | |
|
|
|
|
Inlining is about 12.9% faster on this point. A full N sweep with min-of-3 is TODO.
|
|
|
|
Full sweep (TODO):
|
|
|
|
| N | W(n) [Flops] | T(n) [Cycles] | Performance [Flops/Cycle] | Diff vs Predecessor |
|
|
| ---- | ------------ | ------------- | ------------------------- | ------------------- |
|
|
| 50 | | | | |
|
|
| 100 | | | | |
|
|
| 200 | | | | |
|
|
| 500 | | | | |
|
|
| 1000 | | | | |
|
|
|
|
### ARM (Apple)
|
|
|
|
**Machine**:
|
|
|
|
```
|
|
TBD
|
|
```
|
|
|
|
**Frequency**: TBD
|
|
|
|
| N | W(n) [Flops] | T(n) [Cycles] | Performance [Flops/Cycle] | Diff vs Predecessor |
|
|
| ---- | ------------ | ------------- | ------------------------- | ------------------- |
|
|
| 50 | | | | |
|
|
| 100 | | | | |
|
|
| 200 | | | | |
|
|
| 500 | | | | |
|
|
| 1000 | | | | |
|
|
|
|
## Analysis
|
|
|
|
Speedup likely comes mainly from halving the number of `sqrt` flops.
|
|
|
|
|
|
## Takeaway
|
|
|
|
TBD
|