mirror of
https://github.com/Gericom/teak-llvm.git
synced 2025-06-19 11:35:51 -04:00
58e7642669
Before this patch, CGLoop would dump all transformations for a loop into a single LoopID without encoding any order in which to apply them. rL348944 added the possibility to encode a transformation order using followup-attributes. When a loop has more than one transformation, use the follow-up attribute define the order in which they are applied. The emitted order is the defacto order as defined by the current LLVM pass pipeline, which is: LoopFullUnrollPass LoopDistributePass LoopVectorizePass LoopUnrollAndJamPass LoopUnrollPass MachinePipeliner This patch should therefore not change the assembly output, assuming that all explicit transformations can be applied, and no implicit transformations in-between. In the former case, WarnMissedTransformationsPass should emit a warning (except for MachinePipeliner which is not implemented yet). The latter could be avoided by adding 'llvm.loop.disable_nonforced' attributes. Because LoopUnrollAndJamPass processes a loop nest, generation of the MDNode is delayed to after the inner loop metadata have been processed. A temporary LoopID is therefore used to annotate instructions and RAUW'ed by the actual LoopID later. Differential Revision: https://reviews.llvm.org/D57978 llvm-svn: 357415
33 lines
1.6 KiB
C++
33 lines
1.6 KiB
C++
// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++11 -emit-llvm -o - %s | FileCheck %s
|
|
|
|
// Verify that the outer loop has the llvm.access.group property for the
|
|
// accesses outside and inside the inner loop, even when the inner loop
|
|
// is not perfectly nested.
|
|
void vectorize_imperfectly_nested_test(int *List, int Length) {
|
|
#pragma clang loop vectorize(assume_safety) interleave(disable) unroll(disable)
|
|
for (int i = 0; i < Length; ++i) {
|
|
List[i * Length] = 42;
|
|
#pragma clang loop vectorize(assume_safety) interleave(disable) unroll(disable)
|
|
for (int j = 1; j < Length - 1; ++j)
|
|
List[i * Length + j] = (i + j) * 2;
|
|
List[(i + 1) * Length - 1] = 21;
|
|
}
|
|
}
|
|
|
|
|
|
// CHECK: load i32, i32* %Length.addr, align 4, !llvm.access.group ![[ACCESS_GROUP_2:[0-9]+]]
|
|
|
|
// CHECK: %[[MUL:.+]] = mul nsw i32 %add, 2
|
|
// CHECK: store i32 %[[MUL]], i32* %{{.+}}, !llvm.access.group ![[ACCESS_GROUP_3:[0-9]+]]
|
|
// CHECK: br label %{{.+}}, !llvm.loop ![[INNER_LOOPID:[0-9]+]]
|
|
// CHECK: store i32 21, i32* %{{.+}}, !llvm.access.group ![[ACCESS_GROUP_2]]
|
|
// CHECK: br label %{{.+}}, !llvm.loop ![[OUTER_LOOPID:[0-9]+]]
|
|
|
|
// CHECK: ![[ACCESS_GROUP_2]] = distinct !{}
|
|
// CHECK: ![[ACCESS_GROUP_LIST_3:[0-9]+]] = !{![[ACCESS_GROUP_2]], ![[ACCESS_GROUP_4:[0-9]+]]}
|
|
// CHECK: ![[ACCESS_GROUP_4]] = distinct !{}
|
|
// CHECK: ![[INNER_LOOPID]] = distinct !{![[INNER_LOOPID]], ![[PARALLEL_ACCESSES_8:[0-9]+]]
|
|
// CHECK: ![[PARALLEL_ACCESSES_8]] = !{!"llvm.loop.parallel_accesses", ![[ACCESS_GROUP_4]]}
|
|
// CHECK: ![[OUTER_LOOPID]] = distinct !{![[OUTER_LOOPID]], ![[PARALLEL_ACCESSES_10:[0-9]+]]
|
|
// CHECK: ![[PARALLEL_ACCESSES_10]] = !{!"llvm.loop.parallel_accesses", ![[ACCESS_GROUP_2]]}
|