mirror of
https://github.com/Gericom/teak-llvm.git
synced 2025-06-25 06:18:56 -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
42 lines
2.7 KiB
C++
42 lines
2.7 KiB
C++
// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++11 -emit-llvm -o - %s | FileCheck %s
|
|
|
|
extern "C" void followup_outer(int n, int *x) {
|
|
#pragma clang loop pipeline_initiation_interval(10)
|
|
#pragma clang loop unroll_count(4)
|
|
#pragma unroll_and_jam
|
|
#pragma clang loop vectorize(assume_safety)
|
|
#pragma clang loop distribute(enable)
|
|
for(int j = 0; j < n; j++) {
|
|
x[j] = 10;
|
|
}
|
|
}
|
|
|
|
|
|
// CHECK-LABEL: define void @followup_outer
|
|
// CHECK: br label %for.cond, !llvm.loop ![[LOOP_3:[0-9]+]]
|
|
|
|
// CHECK-DAG: ![[ACCESSGROUP_2:[0-9]+]] = distinct !{}
|
|
|
|
// CHECK-DAG: ![[LOOP_3:[0-9]+]] = distinct !{![[LOOP_3:[0-9]+]], ![[PARALLEL_ACCESSES_4:[0-9]+]], ![[DISTRIBUTE_5:[0-9]+]], ![[DISTRIBUTE_FOLLOWUP_6:[0-9]+]]}
|
|
// CHECK-DAG: ![[PARALLEL_ACCESSES_4:[0-9]+]] = !{!"llvm.loop.parallel_accesses", ![[ACCESSGROUP_2]]}
|
|
// CHECK-DAG: ![[DISTRIBUTE_5:[0-9]+]] = !{!"llvm.loop.distribute.enable", i1 true}
|
|
// CHECK-DAG: ![[DISTRIBUTE_FOLLOWUP_6:[0-9]+]] = !{!"llvm.loop.distribute.followup_all", ![[LOOP_7:[0-9]+]]}
|
|
|
|
// CHECK-DAG: ![[LOOP_7:[0-9]+]] = distinct !{![[LOOP_7:[0-9]+]], ![[PARALLEL_ACCESSES_4:[0-9]+]], ![[VECTORIZE_8:[0-9]+]], ![[VECTORIZE_FOLLOWUP_9:[0-9]+]]}
|
|
// CHECK-DAG: ![[VECTORIZE_8:[0-9]+]] = !{!"llvm.loop.vectorize.enable", i1 true}
|
|
// CHECK-DAG: ![[VECTORIZE_FOLLOWUP_9:[0-9]+]] = !{!"llvm.loop.vectorize.followup_all", ![[LOOP_10:[0-9]+]]}
|
|
|
|
// CHECK-DAG: ![[LOOP_10:[0-9]+]] = distinct !{![[LOOP_10:[0-9]+]], ![[PARALLEL_ACCESSES_4:[0-9]+]], ![[ISVECTORIZED_11:[0-9]+]], ![[UNROLLANDJAM_12:[0-9]+]], ![[UNROLLANDJAM_FOLLOWUPOUTER_13:[0-9]+]]}
|
|
// CHECK-DAG: ![[ISVECTORIZED_11:[0-9]+]] = !{!"llvm.loop.isvectorized"}
|
|
// CHECK-DAG: ![[UNROLLANDJAM_12:[0-9]+]] = !{!"llvm.loop.unroll_and_jam.enable"}
|
|
// CHECK-DAG: ![[UNROLLANDJAM_FOLLOWUPOUTER_13:[0-9]+]] = !{!"llvm.loop.unroll_and_jam.followup_outer", ![[LOOP_14:[0-9]+]]}
|
|
|
|
// CHECK-DAG: ![[LOOP_14:[0-9]+]] = distinct !{![[LOOP_14:[0-9]+]], ![[PARALLEL_ACCESSES_4:[0-9]+]], ![[ISVECTORIZED_11:[0-9]+]], ![[UNROLLANDJAM_DISABLE_15:[0-9]+]], ![[UNROLL_COUNT_16:[0-9]+]], ![[UNROLL_FOLLOWUP_17:[0-9]+]]}
|
|
// CHECK-DAG: ![[UNROLLANDJAM_DISABLE_15:[0-9]+]] = !{!"llvm.loop.unroll_and_jam.disable"}
|
|
// CHECK-DAG: ![[UNROLL_COUNT_16:[0-9]+]] = !{!"llvm.loop.unroll.count", i32 4}
|
|
// CHECK-DAG: ![[UNROLL_FOLLOWUP_17:[0-9]+]] = !{!"llvm.loop.unroll.followup_all", ![[LOOP_18:[0-9]+]]}
|
|
|
|
// CHECK-DAG: ![[LOOP_18:[0-9]+]] = distinct !{![[LOOP_18:[0-9]+]], ![[PARALLEL_ACCESSES_4:[0-9]+]], ![[ISVECTORIZED_11:[0-9]+]], ![[UNROLLANDJAM_DISABLE_15:[0-9]+]], ![[UNROLL_DISABLE_19:[0-9]+]], ![[INITIATIONINTERVAL_20:[0-9]+]]}
|
|
// CHECK-DAG: ![[UNROLL_DISABLE_19:[0-9]+]] = !{!"llvm.loop.unroll.disable"}
|
|
// CHECK-DAG: ![[INITIATIONINTERVAL_20:[0-9]+]] = !{!"llvm.loop.pipeline.initiationinterval", i32 10}
|