mirror of
https://github.com/RRZE-HPC/OSACA.git
synced 2025-12-15 16:40:05 +01:00
08440ed5e1
Validating of OSACA predictions for IVB, SKX, ZEN1, ZEN2, A64FX and TX2 with different kernels. build_and_run.py contains the configuration used at RRZE's testcluster and UR's qpace4, Analysis.ipynb contains the analysis script and results. Raw data from measurements (122MB) will be attached to next OSACA release. For now, find the raw data here: https://hawo.net/~sijuhamm/d/UPIhBOtz/validation-data.tar.gz The analysis report can be viewed at https://nbviewer.jupyter.org/github/RRZE-HPC/OSACA/blob/validation/validation/Analysis.ipynb Quite a few changes on OSACA included: Feature: register change tracking via semantic understanding of operations Feature: recording LCD latency along path and exposing this to frontend Feature: support for memory reference aliases Feature: store throughput scaling (similar to load throughput scaling) Fix: model importer works with latest uops.info export Fix: immediate type tracking on ARM now preserves type in internal representaion Removed unused KerncraftAPI
18 lines
413 B
ArmAsm
18 lines
413 B
ArmAsm
mov x1, #111 // OSACA START MARKER
|
|
.byte 213,3,32,31 // OSACA START MARKER
|
|
// pointer_increment=8 bcc2ad06facad03d27f4cce90dbe3f50
|
|
.L4:
|
|
ldr d0, [x2]
|
|
ldr d3, [x1]
|
|
ldr d2, [x1, 16]
|
|
ldr d1, [x2, x4, lsl 3]
|
|
add x2, x2, 8
|
|
fadd d0, d0, d3
|
|
fadd d0, d0, d2
|
|
fadd d0, d0, d1
|
|
fmul d0, d0, d4
|
|
str d0, [x1, 8]!
|
|
cmp x5, x1
|
|
bne .L4
|
|
mov x1, #222 // OSACA END MARKER
|
|
.byte 213,3,32,31 // OSACA END MARKER |