Skip to main content

Browse the archive

Revision 3657cf5f363fd64aeaf06432e62e3960800927b0 authored by Andrew Adams on 26 January 2024, 17:26:12 UTC, committed by GitHub on 26 January 2024, 17:26:12 UTC 
Fix bounds_of_nested_lanes (#8039)
 
* Fix bounds_of_nested_lanes

bounds_of_nested_lanes assumed that one layer of nested vectorization
could be removed at a time. When faced with the expression:

min(ramp(x8(a), x8(b), 5), x40(27))

It panicked, because on the left hand side it reduced the bounds to
x8(a) ... x8(a) + x8(b) * 4, and on the right hand side it reduced the
bounds to 27. It then attempted to take a min of mismatched types.

In general we can't assume that binary operators on nested vectors have
the same nesting structure on both sides, so I just rewrote it to reduce
directly to a scalar.

Fixes #8038
1 parent 4590a09
History
File Mode Size
figures
images
.clang-format -rw-r--r-- 50 bytes
.gitignore -rw-r--r-- 75 bytes
CMakeLists.txt -rw-r--r-- 9.6 KB
clock.h -rw-r--r-- 494 bytes
lesson_01_basics.cpp -rw-r--r-- 4.4 KB
lesson_02_input_image.cpp -rw-r--r-- 4.0 KB
lesson_03_debugging_1.cpp -rw-r--r-- 2.6 KB
lesson_04_debugging_2.cpp -rw-r--r-- 6.4 KB
lesson_05_scheduling_1.cpp -rw-r--r-- 23.1 KB
lesson_06_realizing_over_shifted_domains.cpp -rw-r--r-- 3.8 KB
lesson_07_multi_stage_pipelines.cpp -rw-r--r-- 6.9 KB
lesson_08_scheduling_2.cpp -rw-r--r-- 29.0 KB
lesson_09_update_definitions.cpp -rw-r--r-- 34.7 KB
lesson_10_aot_compilation_generate.cpp -rw-r--r-- 3.3 KB
lesson_10_aot_compilation_run.cpp -rw-r--r-- 2.7 KB
lesson_11_cross_compilation.cpp -rw-r--r-- 6.1 KB
lesson_12_using_the_gpu.cpp -rw-r--r-- 11.2 KB
lesson_13_tuples.cpp -rw-r--r-- 11.1 KB
lesson_14_types.cpp -rw-r--r-- 8.9 KB
lesson_15_generators.cpp -rw-r--r-- 6.7 KB
lesson_15_generators_usage.sh -rwxr-xr-x 8.1 KB
lesson_16_rgb_generate.cpp -rw-r--r-- 9.6 KB
lesson_16_rgb_run.cpp -rw-r--r-- 5.2 KB
lesson_17_predicated_rdom.cpp -rw-r--r-- 8.1 KB
lesson_18_parallel_associative_reductions.cpp -rw-r--r-- 13.1 KB
lesson_19_wrapper_funcs.cpp -rw-r--r-- 14.3 KB
lesson_20_cloning_funcs.cpp -rw-r--r-- 5.6 KB
lesson_21_auto_scheduler_generate.cpp -rw-r--r-- 11.2 KB
lesson_21_auto_scheduler_run.cpp -rw-r--r-- 2.0 KB
lesson_22_jit_performance.cpp -rw-r--r-- 11.0 KB
lesson_23_serialization.cpp -rw-r--r-- 5.3 KB
lesson_24_async.cpp -rw-r--r-- 14.4 KB
todo.txt -rw-r--r-- 1.1 KB
back to top