Commit fee486e
authored
[NFC][SYCL] Replace #pragma unroll with dim_loop in accessor.hpp (#6939)
The utility was introduced in #6560
because "#pragma unroll" doesn't always work and template-based solution
is much more reliable. Original PR only changed the loops that resulted
in immediate performance difference but other occurrences were missed.
This PR updates remaining ones. Note that I've found them by looking
into the LLVM IR produced by our device compiler and having the loop
really unrolled improves readability of such dumps (and most likely
codesize/perf, although not significantly).1 parent 40872e5 commit fee486e
1 file changed
+4
-6
lines changed| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
1082 | 1082 | | |
1083 | 1083 | | |
1084 | 1084 | | |
1085 | | - | |
1086 | | - | |
| 1085 | + | |
1087 | 1086 | | |
1088 | 1087 | | |
1089 | 1088 | | |
| |||
1094 | 1093 | | |
1095 | 1094 | | |
1096 | 1095 | | |
1097 | | - | |
| 1096 | + | |
1098 | 1097 | | |
1099 | 1098 | | |
1100 | 1099 | | |
| |||
2362 | 2361 | | |
2363 | 2362 | | |
2364 | 2363 | | |
2365 | | - | |
2366 | | - | |
2367 | | - | |
| 2364 | + | |
| 2365 | + | |
2368 | 2366 | | |
2369 | 2367 | | |
2370 | 2368 | | |
| |||
0 commit comments