Do not scale tile loops
We now generate tile loops as:
for (int c1 = 0; c1 <= 47; c1 += 1)
for (int c2 = 0; c2 <= 47; c2 += 1)
for (int c3 = 0; c3 <= 31; c3 += 1)
for (int c4 = 0; c4 <= 31; c4 += 4)
#pragma simd
for (int c5 = c4; c5 <= c4 + 3; c5 += 1)
Stmt_for_body3(32 * c1 + c3, 32 * c2 + c5);
instead of
for (int c1 = 0; c1 <= 1535; c1 += 32)
for (int c2 = 0; c2 <= 1535; c2 += 32)
for (int c3 = 0; c3 <= 31; c3 += 1)
for (int c4 = 0; c4 <= 31; c4 += 4)
#pragma simd
for (int c5 = c4; c5 <= c4 + 3; c5 += 1)
Stmt_for_body3(c1 + c3, c2 + c5);
Run-time performance-wise this makes little difference, but this gives a large
reduction in compile time (10-30% on 17 LNT benchmarks). Apparently the isl
AST generator is not yet very efficient in generating the latter.
llvm-svn: 233675
diff --git a/polly/lib/Transform/ScheduleOptimizer.cpp b/polly/lib/Transform/ScheduleOptimizer.cpp
index 6f42199..942592a 100644
--- a/polly/lib/Transform/ScheduleOptimizer.cpp
+++ b/polly/lib/Transform/ScheduleOptimizer.cpp
@@ -431,6 +431,7 @@
isl_options_set_schedule_maximize_band_depth(S.getIslCtx(), IslMaximizeBands);
isl_options_set_schedule_max_constant_term(S.getIslCtx(), MaxConstantTerm);
isl_options_set_schedule_max_coefficient(S.getIslCtx(), MaxCoefficient);
+ isl_options_set_tile_scale_tile_loops(S.getIslCtx(), 0);
isl_options_set_on_error(S.getIslCtx(), ISL_ON_ERROR_CONTINUE);