mirror of
https://github.com/capstone-engine/llvm-capstone.git
synced 2024-11-23 13:50:11 +00:00
0c6f2f629c
The default version of OpenMP is updated from 5.0 to 5.1 which means if -fopenmp is specified but -fopenmp-version is not specified with clang, the default version of OpenMP is taken to be 5.1. After modifying the Frontend for that, various LIT tests were updated. This patch contains all such changes. At a high level, these are the patterns of changes observed in LIT tests - # RUN lines which mentioned `-fopenmp-version=50` need to kept only if the IR for version 5.0 and 5.1 are different. Otherwise only one RUN line with no version info(i.e. default version) needs to be there. # Test cases of this sort already had the RUN lines with respect to the older default version 5.0 and the version 5.1. Only swapping the version specification flag `-fopenmp-version` from newer version RUN line to older version RUN line is required. # Diagnostics: Remove the 5.0 version specific RUN lines if there was no difference in the Diagnostics messages with respect to the default 5.1. # Diagnostics: In case there was any difference in diagnostics messages between 5.0 and 5.1, mention version specific messages in tests. # If the test contained version specific ifdef's e.g. "#ifdef OMP5" but there were no RUN lines for any other version than 5.X, then bring the code guarded by ifdef's outside and remove the ifdef's. # Some tests had RUN lines for both 5.0 and 5.1 versions, but it is found that the IR for 5.0 is not different from the 5.1, therefore such RUN lines are redundant. So, such duplicated lines are removed. # To generate CHECK lines automatically, use the script llvm/utils/update_cc_test_checks.py Reviewed By: saiislam, ABataev Differential Revision: https://reviews.llvm.org/D129635 (cherry picked from commit 9dd2999907dc791136a75238a6000f69bf67cf4e)
254 lines
13 KiB
C++
254 lines
13 KiB
C++
// Check code generation
|
|
// RUN: %clang_cc1 -verify -triple x86_64-pc-linux-gnu -fopenmp -emit-llvm %s -o - | FileCheck %s --check-prefix=IR
|
|
|
|
// Check same results after serialization round-trip
|
|
// RUN: %clang_cc1 -verify -triple x86_64-pc-linux-gnu -fopenmp -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -verify -triple x86_64-pc-linux-gnu -fopenmp -include-pch %t -emit-llvm %s -o - | FileCheck %s --check-prefix=IR
|
|
// expected-no-diagnostics
|
|
|
|
// Account for multiple transformations of a loop before consumed by
|
|
// #pragma omp for.
|
|
|
|
#ifndef HEADER
|
|
#define HEADER
|
|
|
|
// placeholder for loop body code.
|
|
extern "C" void body(...) {}
|
|
|
|
|
|
// IR-LABEL: @func(
|
|
// IR-NEXT: [[ENTRY:.*]]:
|
|
// IR-NEXT: %[[START_ADDR:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[END_ADDR:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[STEP_ADDR:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTOMP_IV:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[TMP:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[I:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTCAPTURE_EXPR_:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTCAPTURE_EXPR_1:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTCAPTURE_EXPR_2:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTCAPTURE_EXPR_3:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTFLOOR_0_IV_I:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTCAPTURE_EXPR_6:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTCAPTURE_EXPR_8:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTCAPTURE_EXPR_12:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTCAPTURE_EXPR_14:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTFLOOR_0_IV__FLOOR_0_IV_I:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTOMP_LB:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTOMP_UB:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTOMP_STRIDE:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTOMP_IS_LAST:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTFLOOR_0_IV__FLOOR_0_IV_I18:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTTILE_0_IV__FLOOR_0_IV_I:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[DOTTILE_0_IV_I:.+]] = alloca i32, align 4
|
|
// IR-NEXT: %[[TMP0:.+]] = call i32 @__kmpc_global_thread_num(ptr @2)
|
|
// IR-NEXT: store i32 %[[START:.+]], ptr %[[START_ADDR]], align 4
|
|
// IR-NEXT: store i32 %[[END:.+]], ptr %[[END_ADDR]], align 4
|
|
// IR-NEXT: store i32 %[[STEP:.+]], ptr %[[STEP_ADDR]], align 4
|
|
// IR-NEXT: %[[TMP1:.+]] = load i32, ptr %[[START_ADDR]], align 4
|
|
// IR-NEXT: store i32 %[[TMP1]], ptr %[[I]], align 4
|
|
// IR-NEXT: %[[TMP2:.+]] = load i32, ptr %[[START_ADDR]], align 4
|
|
// IR-NEXT: store i32 %[[TMP2]], ptr %[[DOTCAPTURE_EXPR_]], align 4
|
|
// IR-NEXT: %[[TMP3:.+]] = load i32, ptr %[[END_ADDR]], align 4
|
|
// IR-NEXT: store i32 %[[TMP3]], ptr %[[DOTCAPTURE_EXPR_1]], align 4
|
|
// IR-NEXT: %[[TMP4:.+]] = load i32, ptr %[[STEP_ADDR]], align 4
|
|
// IR-NEXT: store i32 %[[TMP4]], ptr %[[DOTCAPTURE_EXPR_2]], align 4
|
|
// IR-NEXT: %[[TMP5:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_1]], align 4
|
|
// IR-NEXT: %[[TMP6:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_]], align 4
|
|
// IR-NEXT: %[[SUB:.+]] = sub i32 %[[TMP5]], %[[TMP6]]
|
|
// IR-NEXT: %[[SUB4:.+]] = sub i32 %[[SUB]], 1
|
|
// IR-NEXT: %[[TMP7:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_2]], align 4
|
|
// IR-NEXT: %[[ADD:.+]] = add i32 %[[SUB4]], %[[TMP7]]
|
|
// IR-NEXT: %[[TMP8:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_2]], align 4
|
|
// IR-NEXT: %[[DIV:.+]] = udiv i32 %[[ADD]], %[[TMP8]]
|
|
// IR-NEXT: %[[SUB5:.+]] = sub i32 %[[DIV]], 1
|
|
// IR-NEXT: store i32 %[[SUB5]], ptr %[[DOTCAPTURE_EXPR_3]], align 4
|
|
// IR-NEXT: store i32 0, ptr %[[DOTFLOOR_0_IV_I]], align 4
|
|
// IR-NEXT: %[[TMP9:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_3]], align 4
|
|
// IR-NEXT: %[[ADD7:.+]] = add i32 %[[TMP9]], 1
|
|
// IR-NEXT: store i32 %[[ADD7]], ptr %[[DOTCAPTURE_EXPR_6]], align 4
|
|
// IR-NEXT: %[[TMP10:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_6]], align 4
|
|
// IR-NEXT: %[[SUB9:.+]] = sub i32 %[[TMP10]], -3
|
|
// IR-NEXT: %[[DIV10:.+]] = udiv i32 %[[SUB9]], 4
|
|
// IR-NEXT: %[[SUB11:.+]] = sub i32 %[[DIV10]], 1
|
|
// IR-NEXT: store i32 %[[SUB11]], ptr %[[DOTCAPTURE_EXPR_8]], align 4
|
|
// IR-NEXT: %[[TMP11:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_8]], align 4
|
|
// IR-NEXT: %[[ADD13:.+]] = add i32 %[[TMP11]], 1
|
|
// IR-NEXT: store i32 %[[ADD13]], ptr %[[DOTCAPTURE_EXPR_12]], align 4
|
|
// IR-NEXT: %[[TMP12:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_12]], align 4
|
|
// IR-NEXT: %[[SUB15:.+]] = sub i32 %[[TMP12]], -2
|
|
// IR-NEXT: %[[DIV16:.+]] = udiv i32 %[[SUB15]], 3
|
|
// IR-NEXT: %[[SUB17:.+]] = sub i32 %[[DIV16]], 1
|
|
// IR-NEXT: store i32 %[[SUB17]], ptr %[[DOTCAPTURE_EXPR_14]], align 4
|
|
// IR-NEXT: store i32 0, ptr %[[DOTFLOOR_0_IV__FLOOR_0_IV_I]], align 4
|
|
// IR-NEXT: %[[TMP13:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_12]], align 4
|
|
// IR-NEXT: %[[CMP:.+]] = icmp ult i32 0, %[[TMP13]]
|
|
// IR-NEXT: br i1 %[[CMP]], label %[[OMP_PRECOND_THEN:.+]], label %[[OMP_PRECOND_END:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[OMP_PRECOND_THEN]]:
|
|
// IR-NEXT: store i32 0, ptr %[[DOTOMP_LB]], align 4
|
|
// IR-NEXT: %[[TMP14:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_14]], align 4
|
|
// IR-NEXT: store i32 %[[TMP14]], ptr %[[DOTOMP_UB]], align 4
|
|
// IR-NEXT: store i32 1, ptr %[[DOTOMP_STRIDE]], align 4
|
|
// IR-NEXT: store i32 0, ptr %[[DOTOMP_IS_LAST]], align 4
|
|
// IR-NEXT: call void @__kmpc_for_static_init_4u(ptr @1, i32 %[[TMP0]], i32 34, ptr %[[DOTOMP_IS_LAST]], ptr %[[DOTOMP_LB]], ptr %[[DOTOMP_UB]], ptr %[[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// IR-NEXT: %[[TMP15:.+]] = load i32, ptr %[[DOTOMP_UB]], align 4
|
|
// IR-NEXT: %[[TMP16:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_14]], align 4
|
|
// IR-NEXT: %[[CMP19:.+]] = icmp ugt i32 %[[TMP15]], %[[TMP16]]
|
|
// IR-NEXT: br i1 %[[CMP19]], label %[[COND_TRUE:.+]], label %[[COND_FALSE:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[COND_TRUE]]:
|
|
// IR-NEXT: %[[TMP17:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_14]], align 4
|
|
// IR-NEXT: br label %[[COND_END:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[COND_FALSE]]:
|
|
// IR-NEXT: %[[TMP18:.+]] = load i32, ptr %[[DOTOMP_UB]], align 4
|
|
// IR-NEXT: br label %[[COND_END]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[COND_END]]:
|
|
// IR-NEXT: %[[COND:.+]] = phi i32 [ %[[TMP17]], %[[COND_TRUE]] ], [ %[[TMP18]], %[[COND_FALSE]] ]
|
|
// IR-NEXT: store i32 %[[COND]], ptr %[[DOTOMP_UB]], align 4
|
|
// IR-NEXT: %[[TMP19:.+]] = load i32, ptr %[[DOTOMP_LB]], align 4
|
|
// IR-NEXT: store i32 %[[TMP19]], ptr %[[DOTOMP_IV]], align 4
|
|
// IR-NEXT: br label %[[OMP_INNER_FOR_COND:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[OMP_INNER_FOR_COND]]:
|
|
// IR-NEXT: %[[TMP20:.+]] = load i32, ptr %[[DOTOMP_IV]], align 4
|
|
// IR-NEXT: %[[TMP21:.+]] = load i32, ptr %[[DOTOMP_UB]], align 4
|
|
// IR-NEXT: %[[ADD20:.+]] = add i32 %[[TMP21]], 1
|
|
// IR-NEXT: %[[CMP21:.+]] = icmp ult i32 %[[TMP20]], %[[ADD20]]
|
|
// IR-NEXT: br i1 %[[CMP21]], label %[[OMP_INNER_FOR_BODY:.+]], label %[[OMP_INNER_FOR_END:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[OMP_INNER_FOR_BODY]]:
|
|
// IR-NEXT: %[[TMP22:.+]] = load i32, ptr %[[DOTOMP_IV]], align 4
|
|
// IR-NEXT: %[[MUL:.+]] = mul i32 %[[TMP22]], 3
|
|
// IR-NEXT: %[[ADD22:.+]] = add i32 0, %[[MUL]]
|
|
// IR-NEXT: store i32 %[[ADD22]], ptr %[[DOTFLOOR_0_IV__FLOOR_0_IV_I18]], align 4
|
|
// IR-NEXT: %[[TMP23:.+]] = load i32, ptr %[[DOTFLOOR_0_IV__FLOOR_0_IV_I18]], align 4
|
|
// IR-NEXT: store i32 %[[TMP23]], ptr %[[DOTTILE_0_IV__FLOOR_0_IV_I]], align 4
|
|
// IR-NEXT: br label %[[FOR_COND:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[FOR_COND]]:
|
|
// IR-NEXT: %[[TMP24:.+]] = load i32, ptr %[[DOTTILE_0_IV__FLOOR_0_IV_I]], align 4
|
|
// IR-NEXT: %[[TMP25:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_8]], align 4
|
|
// IR-NEXT: %[[ADD23:.+]] = add i32 %[[TMP25]], 1
|
|
// IR-NEXT: %[[TMP26:.+]] = load i32, ptr %[[DOTFLOOR_0_IV__FLOOR_0_IV_I18]], align 4
|
|
// IR-NEXT: %[[ADD24:.+]] = add i32 %[[TMP26]], 3
|
|
// IR-NEXT: %[[CMP25:.+]] = icmp ult i32 %[[ADD23]], %[[ADD24]]
|
|
// IR-NEXT: br i1 %[[CMP25]], label %[[COND_TRUE26:.+]], label %[[COND_FALSE28:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[COND_TRUE26]]:
|
|
// IR-NEXT: %[[TMP27:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_8]], align 4
|
|
// IR-NEXT: %[[ADD27:.+]] = add i32 %[[TMP27]], 1
|
|
// IR-NEXT: br label %[[COND_END30:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[COND_FALSE28]]:
|
|
// IR-NEXT: %[[TMP28:.+]] = load i32, ptr %[[DOTFLOOR_0_IV__FLOOR_0_IV_I18]], align 4
|
|
// IR-NEXT: %[[ADD29:.+]] = add i32 %[[TMP28]], 3
|
|
// IR-NEXT: br label %[[COND_END30]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[COND_END30]]:
|
|
// IR-NEXT: %[[COND31:.+]] = phi i32 [ %[[ADD27]], %[[COND_TRUE26]] ], [ %[[ADD29]], %[[COND_FALSE28]] ]
|
|
// IR-NEXT: %[[CMP32:.+]] = icmp ult i32 %[[TMP24]], %[[COND31]]
|
|
// IR-NEXT: br i1 %[[CMP32]], label %[[FOR_BODY:.+]], label %[[FOR_END51:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[FOR_BODY]]:
|
|
// IR-NEXT: %[[TMP29:.+]] = load i32, ptr %[[DOTTILE_0_IV__FLOOR_0_IV_I]], align 4
|
|
// IR-NEXT: %[[MUL33:.+]] = mul i32 %[[TMP29]], 4
|
|
// IR-NEXT: %[[ADD34:.+]] = add i32 0, %[[MUL33]]
|
|
// IR-NEXT: store i32 %[[ADD34]], ptr %[[DOTFLOOR_0_IV_I]], align 4
|
|
// IR-NEXT: %[[TMP30:.+]] = load i32, ptr %[[DOTFLOOR_0_IV_I]], align 4
|
|
// IR-NEXT: store i32 %[[TMP30]], ptr %[[DOTTILE_0_IV_I]], align 4
|
|
// IR-NEXT: br label %[[FOR_COND35:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[FOR_COND35]]:
|
|
// IR-NEXT: %[[TMP31:.+]] = load i32, ptr %[[DOTTILE_0_IV_I]], align 4
|
|
// IR-NEXT: %[[TMP32:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_3]], align 4
|
|
// IR-NEXT: %[[ADD36:.+]] = add i32 %[[TMP32]], 1
|
|
// IR-NEXT: %[[TMP33:.+]] = load i32, ptr %[[DOTFLOOR_0_IV_I]], align 4
|
|
// IR-NEXT: %[[ADD37:.+]] = add nsw i32 %[[TMP33]], 4
|
|
// IR-NEXT: %[[CMP38:.+]] = icmp ult i32 %[[ADD36]], %[[ADD37]]
|
|
// IR-NEXT: br i1 %[[CMP38]], label %[[COND_TRUE39:.+]], label %[[COND_FALSE41:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[COND_TRUE39]]:
|
|
// IR-NEXT: %[[TMP34:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_3]], align 4
|
|
// IR-NEXT: %[[ADD40:.+]] = add i32 %[[TMP34]], 1
|
|
// IR-NEXT: br label %[[COND_END43:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[COND_FALSE41]]:
|
|
// IR-NEXT: %[[TMP35:.+]] = load i32, ptr %[[DOTFLOOR_0_IV_I]], align 4
|
|
// IR-NEXT: %[[ADD42:.+]] = add nsw i32 %[[TMP35]], 4
|
|
// IR-NEXT: br label %[[COND_END43]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[COND_END43]]:
|
|
// IR-NEXT: %[[COND44:.+]] = phi i32 [ %[[ADD40]], %[[COND_TRUE39]] ], [ %[[ADD42]], %[[COND_FALSE41]] ]
|
|
// IR-NEXT: %[[CMP45:.+]] = icmp ult i32 %[[TMP31]], %[[COND44]]
|
|
// IR-NEXT: br i1 %[[CMP45]], label %[[FOR_BODY46:.+]], label %[[FOR_END:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[FOR_BODY46]]:
|
|
// IR-NEXT: %[[TMP36:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_]], align 4
|
|
// IR-NEXT: %[[TMP37:.+]] = load i32, ptr %[[DOTTILE_0_IV_I]], align 4
|
|
// IR-NEXT: %[[TMP38:.+]] = load i32, ptr %[[DOTCAPTURE_EXPR_2]], align 4
|
|
// IR-NEXT: %[[MUL47:.+]] = mul i32 %[[TMP37]], %[[TMP38]]
|
|
// IR-NEXT: %[[ADD48:.+]] = add i32 %[[TMP36]], %[[MUL47]]
|
|
// IR-NEXT: store i32 %[[ADD48]], ptr %[[I]], align 4
|
|
// IR-NEXT: %[[TMP39:.+]] = load i32, ptr %[[START_ADDR]], align 4
|
|
// IR-NEXT: %[[TMP40:.+]] = load i32, ptr %[[END_ADDR]], align 4
|
|
// IR-NEXT: %[[TMP41:.+]] = load i32, ptr %[[STEP_ADDR]], align 4
|
|
// IR-NEXT: %[[TMP42:.+]] = load i32, ptr %[[I]], align 4
|
|
// IR-NEXT: call void (...) @body(i32 noundef %[[TMP39]], i32 noundef %[[TMP40]], i32 noundef %[[TMP41]], i32 noundef %[[TMP42]])
|
|
// IR-NEXT: br label %[[FOR_INC:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[FOR_INC]]:
|
|
// IR-NEXT: %[[TMP43:.+]] = load i32, ptr %[[DOTTILE_0_IV_I]], align 4
|
|
// IR-NEXT: %[[INC:.+]] = add nsw i32 %[[TMP43]], 1
|
|
// IR-NEXT: store i32 %[[INC]], ptr %[[DOTTILE_0_IV_I]], align 4
|
|
// IR-NEXT: br label %[[FOR_COND35]], !llvm.loop ![[LOOP2:[0-9]+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[FOR_END]]:
|
|
// IR-NEXT: br label %[[FOR_INC49:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[FOR_INC49]]:
|
|
// IR-NEXT: %[[TMP44:.+]] = load i32, ptr %[[DOTTILE_0_IV__FLOOR_0_IV_I]], align 4
|
|
// IR-NEXT: %[[INC50:.+]] = add i32 %[[TMP44]], 1
|
|
// IR-NEXT: store i32 %[[INC50]], ptr %[[DOTTILE_0_IV__FLOOR_0_IV_I]], align 4
|
|
// IR-NEXT: br label %[[FOR_COND]], !llvm.loop ![[LOOP4:[0-9]+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[FOR_END51]]:
|
|
// IR-NEXT: br label %[[OMP_BODY_CONTINUE:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[OMP_BODY_CONTINUE]]:
|
|
// IR-NEXT: br label %[[OMP_INNER_FOR_INC:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[OMP_INNER_FOR_INC]]:
|
|
// IR-NEXT: %[[TMP45:.+]] = load i32, ptr %[[DOTOMP_IV]], align 4
|
|
// IR-NEXT: %[[ADD52:.+]] = add i32 %[[TMP45]], 1
|
|
// IR-NEXT: store i32 %[[ADD52]], ptr %[[DOTOMP_IV]], align 4
|
|
// IR-NEXT: br label %[[OMP_INNER_FOR_COND]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[OMP_INNER_FOR_END]]:
|
|
// IR-NEXT: br label %[[OMP_LOOP_EXIT:.+]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[OMP_LOOP_EXIT]]:
|
|
// IR-NEXT: call void @__kmpc_for_static_fini(ptr @1, i32 %[[TMP0]])
|
|
// IR-NEXT: br label %[[OMP_PRECOND_END]]
|
|
// IR-EMPTY:
|
|
// IR-NEXT: [[OMP_PRECOND_END]]:
|
|
// IR-NEXT: call void @__kmpc_barrier(ptr @3, i32 %[[TMP0]])
|
|
// IR-NEXT: ret void
|
|
// IR-NEXT: }
|
|
extern "C" void func(int start, int end, int step) {
|
|
#pragma omp for
|
|
#pragma omp tile sizes(3)
|
|
#pragma omp tile sizes(4)
|
|
for (int i = start; i < end; i += step)
|
|
body(start, end, step, i);
|
|
}
|
|
|
|
#endif /* HEADER */
|
|
// IR: ![[META0:[0-9]+]] = !{i32 1, !"wchar_size", i32 4}
|
|
// IR: ![[META1:[0-9]+]] = !{!"{{[^"]*}}"}
|
|
// IR: ![[LOOP2]] = distinct !{![[LOOP2]], ![[LOOPPROP3:[0-9]+]]}
|
|
// IR: ![[LOOPPROP3]] = !{!"llvm.loop.mustprogress"}
|
|
// IR: ![[LOOP4]] = distinct !{![[LOOP4]], ![[LOOPPROP3]]}
|