| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --filter "br i1|!prof|!llvm.loop|^.*:" --version 6 |
| ; RUN: opt -passes=loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S %s | FileCheck %s --check-prefix=VF4IC1 |
| ; RUN: opt -passes=loop-vectorize -force-vector-width=2 -force-vector-interleave=2 -S %s | FileCheck %s --check-prefix=VF2IC2 |
| |
| ; Predicated store where the condition is taken 1 in 8 iterations. |
| define void @predicated_store(ptr %a, i32 %n) { |
| ; VF4IC1-LABEL: define void @predicated_store( |
| ; VF4IC1-SAME: ptr [[A:%.*]], i32 [[N:%.*]]) { |
| ; VF4IC1: [[ENTRY:.*:]] |
| ; VF4IC1: br i1 [[MIN_ITERS_CHECK:%.*]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]], !prof [[PROF0:![0-9]+]] |
| ; VF4IC1: [[VECTOR_PH]]: |
| ; VF4IC1: [[VECTOR_BODY:.*]]: |
| ; VF4IC1: br i1 [[TMP2:%.*]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]] |
| ; VF4IC1: [[PRED_STORE_IF]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE]]: |
| ; VF4IC1: br i1 [[TMP5:%.*]], label %[[PRED_STORE_IF1:.*]], label %[[PRED_STORE_CONTINUE2:.*]] |
| ; VF4IC1: [[PRED_STORE_IF1]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE2]]: |
| ; VF4IC1: br i1 [[TMP10:%.*]], label %[[PRED_STORE_IF3:.*]], label %[[PRED_STORE_CONTINUE4:.*]] |
| ; VF4IC1: [[PRED_STORE_IF3]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE4]]: |
| ; VF4IC1: br i1 [[TMP15:%.*]], label %[[PRED_STORE_IF5:.*]], label %[[PRED_STORE_CONTINUE6:.*]] |
| ; VF4IC1: [[PRED_STORE_IF5]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE6]]: |
| ; VF4IC1: br i1 [[TMP20:%.*]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !prof [[PROF1:![0-9]+]], !llvm.loop [[LOOP2:![0-9]+]] |
| ; VF4IC1: [[MIDDLE_BLOCK]]: |
| ; VF4IC1: br i1 [[CMP_N:%.*]], label %[[EXIT:.*]], label %[[SCALAR_PH]], !prof [[PROF6:![0-9]+]] |
| ; VF4IC1: [[SCALAR_PH]]: |
| ; VF4IC1: [[LOOP:.*]]: |
| ; VF4IC1: br i1 [[CMP:%.*]], label %[[IF_THEN:.*]], label %[[LATCH:.*]], !prof [[PROF7:![0-9]+]] |
| ; VF4IC1: [[IF_THEN]]: |
| ; VF4IC1: [[LATCH]]: |
| ; VF4IC1: br i1 [[EXITCOND:%.*]], label %[[EXIT]], label %[[LOOP]], !prof [[PROF8:![0-9]+]], !llvm.loop [[LOOP9:![0-9]+]] |
| ; VF4IC1: [[EXIT]]: |
| ; |
| ; VF2IC2-LABEL: define void @predicated_store( |
| ; VF2IC2-SAME: ptr [[A:%.*]], i32 [[N:%.*]]) { |
| ; VF2IC2: [[ENTRY:.*:]] |
| ; VF2IC2: br i1 [[MIN_ITERS_CHECK:%.*]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]], !prof [[PROF0:![0-9]+]] |
| ; VF2IC2: [[VECTOR_PH]]: |
| ; VF2IC2: [[VECTOR_BODY:.*]]: |
| ; VF2IC2: br i1 [[TMP4:%.*]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]] |
| ; VF2IC2: [[PRED_STORE_IF]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE]]: |
| ; VF2IC2: br i1 [[TMP7:%.*]], label %[[PRED_STORE_IF2:.*]], label %[[PRED_STORE_CONTINUE3:.*]] |
| ; VF2IC2: [[PRED_STORE_IF2]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE3]]: |
| ; VF2IC2: br i1 [[TMP12:%.*]], label %[[PRED_STORE_IF4:.*]], label %[[PRED_STORE_CONTINUE5:.*]] |
| ; VF2IC2: [[PRED_STORE_IF4]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE5]]: |
| ; VF2IC2: br i1 [[TMP17:%.*]], label %[[PRED_STORE_IF6:.*]], label %[[PRED_STORE_CONTINUE7:.*]] |
| ; VF2IC2: [[PRED_STORE_IF6]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE7]]: |
| ; VF2IC2: br i1 [[TMP22:%.*]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !prof [[PROF1:![0-9]+]], !llvm.loop [[LOOP2:![0-9]+]] |
| ; VF2IC2: [[MIDDLE_BLOCK]]: |
| ; VF2IC2: br i1 [[CMP_N:%.*]], label %[[EXIT:.*]], label %[[SCALAR_PH]], !prof [[PROF6:![0-9]+]] |
| ; VF2IC2: [[SCALAR_PH]]: |
| ; VF2IC2: [[LOOP:.*]]: |
| ; VF2IC2: br i1 [[CMP:%.*]], label %[[IF_THEN:.*]], label %[[LATCH:.*]], !prof [[PROF7:![0-9]+]] |
| ; VF2IC2: [[IF_THEN]]: |
| ; VF2IC2: [[LATCH]]: |
| ; VF2IC2: br i1 [[EXITCOND:%.*]], label %[[EXIT]], label %[[LOOP]], !prof [[PROF8:![0-9]+]], !llvm.loop [[LOOP9:![0-9]+]] |
| ; VF2IC2: [[EXIT]]: |
| ; |
| entry: |
| br label %loop |
| |
| loop: |
| %iv = phi i32 [ 0, %entry ], [ %iv.next, %latch ] |
| %gep = getelementptr inbounds i32, ptr %a, i32 %iv |
| %val = load i32, ptr %gep, align 4 |
| %cmp = icmp sgt i32 %val, 0 |
| br i1 %cmp, label %if.then, label %latch, !prof !1 |
| |
| if.then: |
| %add = add i32 %val, 1 |
| store i32 %add, ptr %gep, align 4 |
| br label %latch |
| |
| latch: |
| %iv.next = add nuw nsw i32 %iv, 1 |
| %exitcond = icmp eq i32 %iv.next, %n |
| br i1 %exitcond, label %exit, label %loop, !prof !0 |
| |
| exit: |
| ret void |
| } |
| |
| ; Predicated store guarded by %c1 (taken 1/2) and %c2 (taken 1/4), so it |
| ; executes 1 in 8 iterations. |
| define void @predicated_store_sunk_address(ptr %a, ptr %b, i32 %n) { |
| ; VF4IC1-LABEL: define void @predicated_store_sunk_address( |
| ; VF4IC1-SAME: ptr [[A:%.*]], ptr [[B:%.*]], i32 [[N:%.*]]) { |
| ; VF4IC1: [[ENTRY:.*:]] |
| ; VF4IC1: br i1 [[MIN_ITERS_CHECK:%.*]], label %[[SCALAR_PH:.*]], label %[[VECTOR_MEMCHECK:.*]], !prof [[PROF0]] |
| ; VF4IC1: [[VECTOR_MEMCHECK]]: |
| ; VF4IC1: br i1 [[DIFF_CHECK:%.*]], label %[[SCALAR_PH]], label %[[VECTOR_PH:.*]], !prof [[PROF0]] |
| ; VF4IC1: [[VECTOR_PH]]: |
| ; VF4IC1: [[VECTOR_BODY:.*]]: |
| ; VF4IC1: br i1 [[TMP6:%.*]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]] |
| ; VF4IC1: [[PRED_STORE_IF]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE]]: |
| ; VF4IC1: br i1 [[TMP9:%.*]], label %[[PRED_STORE_IF3:.*]], label %[[PRED_STORE_CONTINUE4:.*]] |
| ; VF4IC1: [[PRED_STORE_IF3]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE4]]: |
| ; VF4IC1: br i1 [[TMP13:%.*]], label %[[PRED_STORE_IF5:.*]], label %[[PRED_STORE_CONTINUE6:.*]] |
| ; VF4IC1: [[PRED_STORE_IF5]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE6]]: |
| ; VF4IC1: br i1 [[TMP17:%.*]], label %[[PRED_STORE_IF7:.*]], label %[[PRED_STORE_CONTINUE8:.*]] |
| ; VF4IC1: [[PRED_STORE_IF7]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE8]]: |
| ; VF4IC1: br i1 [[TMP21:%.*]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !prof [[PROF1]], !llvm.loop [[LOOP11:![0-9]+]] |
| ; VF4IC1: [[MIDDLE_BLOCK]]: |
| ; VF4IC1: br i1 [[CMP_N:%.*]], label %[[EXIT:.*]], label %[[SCALAR_PH]], !prof [[PROF6]] |
| ; VF4IC1: [[SCALAR_PH]]: |
| ; VF4IC1: [[LOOP:.*]]: |
| ; VF4IC1: br i1 [[C1:%.*]], label %[[M:.*]], label %[[LATCH:.*]], !prof [[PROF12:![0-9]+]] |
| ; VF4IC1: [[M]]: |
| ; VF4IC1: br i1 [[C2:%.*]], label %[[IF:.*]], label %[[LATCH]], !prof [[PROF6]] |
| ; VF4IC1: [[IF]]: |
| ; VF4IC1: [[LATCH]]: |
| ; VF4IC1: br i1 [[EXITCOND:%.*]], label %[[EXIT]], label %[[LOOP]], !prof [[PROF8]], !llvm.loop [[LOOP13:![0-9]+]] |
| ; VF4IC1: [[EXIT]]: |
| ; |
| ; VF2IC2-LABEL: define void @predicated_store_sunk_address( |
| ; VF2IC2-SAME: ptr [[A:%.*]], ptr [[B:%.*]], i32 [[N:%.*]]) { |
| ; VF2IC2: [[ENTRY:.*:]] |
| ; VF2IC2: br i1 [[MIN_ITERS_CHECK:%.*]], label %[[SCALAR_PH:.*]], label %[[VECTOR_MEMCHECK:.*]], !prof [[PROF0]] |
| ; VF2IC2: [[VECTOR_MEMCHECK]]: |
| ; VF2IC2: br i1 [[DIFF_CHECK:%.*]], label %[[SCALAR_PH]], label %[[VECTOR_PH:.*]], !prof [[PROF0]] |
| ; VF2IC2: [[VECTOR_PH]]: |
| ; VF2IC2: [[VECTOR_BODY:.*]]: |
| ; VF2IC2: br i1 [[TMP10:%.*]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]] |
| ; VF2IC2: [[PRED_STORE_IF]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE]]: |
| ; VF2IC2: br i1 [[TMP13:%.*]], label %[[PRED_STORE_IF4:.*]], label %[[PRED_STORE_CONTINUE5:.*]] |
| ; VF2IC2: [[PRED_STORE_IF4]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE5]]: |
| ; VF2IC2: br i1 [[TMP17:%.*]], label %[[PRED_STORE_IF6:.*]], label %[[PRED_STORE_CONTINUE7:.*]] |
| ; VF2IC2: [[PRED_STORE_IF6]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE7]]: |
| ; VF2IC2: br i1 [[TMP21:%.*]], label %[[PRED_STORE_IF8:.*]], label %[[PRED_STORE_CONTINUE9:.*]] |
| ; VF2IC2: [[PRED_STORE_IF8]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE9]]: |
| ; VF2IC2: br i1 [[TMP25:%.*]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !prof [[PROF1]], !llvm.loop [[LOOP11:![0-9]+]] |
| ; VF2IC2: [[MIDDLE_BLOCK]]: |
| ; VF2IC2: br i1 [[CMP_N:%.*]], label %[[EXIT:.*]], label %[[SCALAR_PH]], !prof [[PROF6]] |
| ; VF2IC2: [[SCALAR_PH]]: |
| ; VF2IC2: [[LOOP:.*]]: |
| ; VF2IC2: br i1 [[C1:%.*]], label %[[M:.*]], label %[[LATCH:.*]], !prof [[PROF12:![0-9]+]] |
| ; VF2IC2: [[M]]: |
| ; VF2IC2: br i1 [[C2:%.*]], label %[[IF:.*]], label %[[LATCH]], !prof [[PROF6]] |
| ; VF2IC2: [[IF]]: |
| ; VF2IC2: [[LATCH]]: |
| ; VF2IC2: br i1 [[EXITCOND:%.*]], label %[[EXIT]], label %[[LOOP]], !prof [[PROF8]], !llvm.loop [[LOOP13:![0-9]+]] |
| ; VF2IC2: [[EXIT]]: |
| ; |
| entry: |
| br label %loop |
| |
| loop: |
| %iv = phi i32 [ 0, %entry ], [ %iv.next, %latch ] |
| %gep.a = getelementptr inbounds i32, ptr %a, i32 %iv |
| %v = load i32, ptr %gep.a, align 4 |
| %c1 = icmp sgt i32 %v, 0 |
| br i1 %c1, label %m, label %latch, !prof !2 |
| |
| m: |
| %gep.b = getelementptr inbounds i32, ptr %b, i32 %iv |
| %c2 = icmp sgt i32 %v, 100 |
| br i1 %c2, label %if, label %latch, !prof !3 |
| |
| if: |
| store i32 %v, ptr %gep.b, align 4 |
| br label %latch |
| |
| latch: |
| %iv.next = add nuw nsw i32 %iv, 1 |
| %exitcond = icmp eq i32 %iv.next, %n |
| br i1 %exitcond, label %exit, label %loop, !prof !0 |
| |
| exit: |
| ret void |
| } |
| |
| ; Loop without profile data. |
| define void @predicated_store_no_profile(ptr %a, i32 %n) { |
| ; VF4IC1-LABEL: define void @predicated_store_no_profile( |
| ; VF4IC1-SAME: ptr [[A:%.*]], i32 [[N:%.*]]) { |
| ; VF4IC1: [[ENTRY:.*:]] |
| ; VF4IC1: br i1 [[MIN_ITERS_CHECK:%.*]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]] |
| ; VF4IC1: [[VECTOR_PH]]: |
| ; VF4IC1: [[VECTOR_BODY:.*]]: |
| ; VF4IC1: br i1 [[TMP2:%.*]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]] |
| ; VF4IC1: [[PRED_STORE_IF]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE]]: |
| ; VF4IC1: br i1 [[TMP5:%.*]], label %[[PRED_STORE_IF1:.*]], label %[[PRED_STORE_CONTINUE2:.*]] |
| ; VF4IC1: [[PRED_STORE_IF1]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE2]]: |
| ; VF4IC1: br i1 [[TMP10:%.*]], label %[[PRED_STORE_IF3:.*]], label %[[PRED_STORE_CONTINUE4:.*]] |
| ; VF4IC1: [[PRED_STORE_IF3]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE4]]: |
| ; VF4IC1: br i1 [[TMP15:%.*]], label %[[PRED_STORE_IF5:.*]], label %[[PRED_STORE_CONTINUE6:.*]] |
| ; VF4IC1: [[PRED_STORE_IF5]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE6]]: |
| ; VF4IC1: br i1 [[TMP20:%.*]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]] |
| ; VF4IC1: [[MIDDLE_BLOCK]]: |
| ; VF4IC1: br i1 [[CMP_N:%.*]], label %[[EXIT:.*]], label %[[SCALAR_PH]] |
| ; VF4IC1: [[SCALAR_PH]]: |
| ; VF4IC1: [[LOOP:.*]]: |
| ; VF4IC1: br i1 [[CMP:%.*]], label %[[IF_THEN:.*]], label %[[LATCH:.*]] |
| ; VF4IC1: [[IF_THEN]]: |
| ; VF4IC1: [[LATCH]]: |
| ; VF4IC1: br i1 [[EXITCOND:%.*]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP15:![0-9]+]] |
| ; VF4IC1: [[EXIT]]: |
| ; |
| ; VF2IC2-LABEL: define void @predicated_store_no_profile( |
| ; VF2IC2-SAME: ptr [[A:%.*]], i32 [[N:%.*]]) { |
| ; VF2IC2: [[ENTRY:.*:]] |
| ; VF2IC2: br i1 [[MIN_ITERS_CHECK:%.*]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]] |
| ; VF2IC2: [[VECTOR_PH]]: |
| ; VF2IC2: [[VECTOR_BODY:.*]]: |
| ; VF2IC2: br i1 [[TMP4:%.*]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]] |
| ; VF2IC2: [[PRED_STORE_IF]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE]]: |
| ; VF2IC2: br i1 [[TMP7:%.*]], label %[[PRED_STORE_IF2:.*]], label %[[PRED_STORE_CONTINUE3:.*]] |
| ; VF2IC2: [[PRED_STORE_IF2]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE3]]: |
| ; VF2IC2: br i1 [[TMP12:%.*]], label %[[PRED_STORE_IF4:.*]], label %[[PRED_STORE_CONTINUE5:.*]] |
| ; VF2IC2: [[PRED_STORE_IF4]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE5]]: |
| ; VF2IC2: br i1 [[TMP17:%.*]], label %[[PRED_STORE_IF6:.*]], label %[[PRED_STORE_CONTINUE7:.*]] |
| ; VF2IC2: [[PRED_STORE_IF6]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE7]]: |
| ; VF2IC2: br i1 [[TMP22:%.*]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]] |
| ; VF2IC2: [[MIDDLE_BLOCK]]: |
| ; VF2IC2: br i1 [[CMP_N:%.*]], label %[[EXIT:.*]], label %[[SCALAR_PH]] |
| ; VF2IC2: [[SCALAR_PH]]: |
| ; VF2IC2: [[LOOP:.*]]: |
| ; VF2IC2: br i1 [[CMP:%.*]], label %[[IF_THEN:.*]], label %[[LATCH:.*]] |
| ; VF2IC2: [[IF_THEN]]: |
| ; VF2IC2: [[LATCH]]: |
| ; VF2IC2: br i1 [[EXITCOND:%.*]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP15:![0-9]+]] |
| ; VF2IC2: [[EXIT]]: |
| ; |
| entry: |
| br label %loop |
| |
| loop: |
| %iv = phi i32 [ 0, %entry ], [ %iv.next, %latch ] |
| %gep = getelementptr inbounds i32, ptr %a, i32 %iv |
| %val = load i32, ptr %gep, align 4 |
| %cmp = icmp sgt i32 %val, 0 |
| br i1 %cmp, label %if.then, label %latch |
| |
| if.then: |
| %add = add i32 %val, 1 |
| store i32 %add, ptr %gep, align 4 |
| br label %latch |
| |
| latch: |
| %iv.next = add nuw nsw i32 %iv, 1 |
| %exitcond = icmp eq i32 %iv.next, %n |
| br i1 %exitcond, label %exit, label %loop |
| |
| exit: |
| ret void |
| } |
| |
| ; Profile data for the loop latch, but not internal loop blocks. |
| define void @predicated_store_unprofiled_predicate(ptr %a, i32 %n) { |
| ; VF4IC1-LABEL: define void @predicated_store_unprofiled_predicate( |
| ; VF4IC1-SAME: ptr [[A:%.*]], i32 [[N:%.*]]) { |
| ; VF4IC1: [[ENTRY:.*:]] |
| ; VF4IC1: br i1 [[MIN_ITERS_CHECK:%.*]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]], !prof [[PROF0]] |
| ; VF4IC1: [[VECTOR_PH]]: |
| ; VF4IC1: [[VECTOR_BODY:.*]]: |
| ; VF4IC1: br i1 [[TMP2:%.*]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]] |
| ; VF4IC1: [[PRED_STORE_IF]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE]]: |
| ; VF4IC1: br i1 [[TMP5:%.*]], label %[[PRED_STORE_IF1:.*]], label %[[PRED_STORE_CONTINUE2:.*]] |
| ; VF4IC1: [[PRED_STORE_IF1]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE2]]: |
| ; VF4IC1: br i1 [[TMP10:%.*]], label %[[PRED_STORE_IF3:.*]], label %[[PRED_STORE_CONTINUE4:.*]] |
| ; VF4IC1: [[PRED_STORE_IF3]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE4]]: |
| ; VF4IC1: br i1 [[TMP15:%.*]], label %[[PRED_STORE_IF5:.*]], label %[[PRED_STORE_CONTINUE6:.*]] |
| ; VF4IC1: [[PRED_STORE_IF5]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE6]]: |
| ; VF4IC1: br i1 [[TMP20:%.*]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !prof [[PROF1]], !llvm.loop [[LOOP16:![0-9]+]] |
| ; VF4IC1: [[MIDDLE_BLOCK]]: |
| ; VF4IC1: br i1 [[CMP_N:%.*]], label %[[EXIT:.*]], label %[[SCALAR_PH]], !prof [[PROF6]] |
| ; VF4IC1: [[SCALAR_PH]]: |
| ; VF4IC1: [[LOOP:.*]]: |
| ; VF4IC1: br i1 [[CMP:%.*]], label %[[IF_THEN:.*]], label %[[LATCH:.*]] |
| ; VF4IC1: [[IF_THEN]]: |
| ; VF4IC1: [[LATCH]]: |
| ; VF4IC1: br i1 [[EXITCOND:%.*]], label %[[EXIT]], label %[[LOOP]], !prof [[PROF8]], !llvm.loop [[LOOP17:![0-9]+]] |
| ; VF4IC1: [[EXIT]]: |
| ; |
| ; VF2IC2-LABEL: define void @predicated_store_unprofiled_predicate( |
| ; VF2IC2-SAME: ptr [[A:%.*]], i32 [[N:%.*]]) { |
| ; VF2IC2: [[ENTRY:.*:]] |
| ; VF2IC2: br i1 [[MIN_ITERS_CHECK:%.*]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]], !prof [[PROF0]] |
| ; VF2IC2: [[VECTOR_PH]]: |
| ; VF2IC2: [[VECTOR_BODY:.*]]: |
| ; VF2IC2: br i1 [[TMP4:%.*]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]] |
| ; VF2IC2: [[PRED_STORE_IF]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE]]: |
| ; VF2IC2: br i1 [[TMP7:%.*]], label %[[PRED_STORE_IF2:.*]], label %[[PRED_STORE_CONTINUE3:.*]] |
| ; VF2IC2: [[PRED_STORE_IF2]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE3]]: |
| ; VF2IC2: br i1 [[TMP12:%.*]], label %[[PRED_STORE_IF4:.*]], label %[[PRED_STORE_CONTINUE5:.*]] |
| ; VF2IC2: [[PRED_STORE_IF4]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE5]]: |
| ; VF2IC2: br i1 [[TMP17:%.*]], label %[[PRED_STORE_IF6:.*]], label %[[PRED_STORE_CONTINUE7:.*]] |
| ; VF2IC2: [[PRED_STORE_IF6]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE7]]: |
| ; VF2IC2: br i1 [[TMP22:%.*]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !prof [[PROF1]], !llvm.loop [[LOOP16:![0-9]+]] |
| ; VF2IC2: [[MIDDLE_BLOCK]]: |
| ; VF2IC2: br i1 [[CMP_N:%.*]], label %[[EXIT:.*]], label %[[SCALAR_PH]], !prof [[PROF6]] |
| ; VF2IC2: [[SCALAR_PH]]: |
| ; VF2IC2: [[LOOP:.*]]: |
| ; VF2IC2: br i1 [[CMP:%.*]], label %[[IF_THEN:.*]], label %[[LATCH:.*]] |
| ; VF2IC2: [[IF_THEN]]: |
| ; VF2IC2: [[LATCH]]: |
| ; VF2IC2: br i1 [[EXITCOND:%.*]], label %[[EXIT]], label %[[LOOP]], !prof [[PROF8]], !llvm.loop [[LOOP17:![0-9]+]] |
| ; VF2IC2: [[EXIT]]: |
| ; |
| entry: |
| br label %loop |
| |
| loop: |
| %iv = phi i32 [ 0, %entry ], [ %iv.next, %latch ] |
| %gep = getelementptr inbounds i32, ptr %a, i32 %iv |
| %val = load i32, ptr %gep, align 4 |
| %cmp = icmp sgt i32 %val, 0 |
| br i1 %cmp, label %if.then, label %latch |
| |
| if.then: |
| %add = add i32 %val, 1 |
| store i32 %add, ptr %gep, align 4 |
| br label %latch |
| |
| latch: |
| %iv.next = add nuw nsw i32 %iv, 1 |
| %exitcond = icmp eq i32 %iv.next, %n |
| br i1 %exitcond, label %exit, label %loop, !prof !0 |
| |
| exit: |
| ret void |
| } |
| |
| define void @predicated_store_almost_always_taken(ptr %a, i32 %n) { |
| ; VF4IC1-LABEL: define void @predicated_store_almost_always_taken( |
| ; VF4IC1-SAME: ptr [[A:%.*]], i32 [[N:%.*]]) { |
| ; VF4IC1: [[ENTRY:.*:]] |
| ; VF4IC1: br i1 [[MIN_ITERS_CHECK:%.*]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]], !prof [[PROF0]] |
| ; VF4IC1: [[VECTOR_PH]]: |
| ; VF4IC1: [[VECTOR_BODY:.*]]: |
| ; VF4IC1: br i1 [[TMP3:%.*]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]] |
| ; VF4IC1: [[PRED_STORE_IF]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE]]: |
| ; VF4IC1: br i1 [[TMP5:%.*]], label %[[PRED_STORE_IF1:.*]], label %[[PRED_STORE_CONTINUE2:.*]] |
| ; VF4IC1: [[PRED_STORE_IF1]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE2]]: |
| ; VF4IC1: br i1 [[TMP9:%.*]], label %[[PRED_STORE_IF3:.*]], label %[[PRED_STORE_CONTINUE4:.*]] |
| ; VF4IC1: [[PRED_STORE_IF3]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE4]]: |
| ; VF4IC1: br i1 [[TMP13:%.*]], label %[[PRED_STORE_IF5:.*]], label %[[PRED_STORE_CONTINUE6:.*]] |
| ; VF4IC1: [[PRED_STORE_IF5]]: |
| ; VF4IC1: [[PRED_STORE_CONTINUE6]]: |
| ; VF4IC1: br i1 [[TMP17:%.*]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !prof [[PROF1]], !llvm.loop [[LOOP18:![0-9]+]] |
| ; VF4IC1: [[MIDDLE_BLOCK]]: |
| ; VF4IC1: br i1 [[CMP_N:%.*]], label %[[EXIT:.*]], label %[[SCALAR_PH]], !prof [[PROF6]] |
| ; VF4IC1: [[SCALAR_PH]]: |
| ; VF4IC1: [[LOOP:.*]]: |
| ; VF4IC1: br i1 [[CMP:%.*]], label %[[IF_THEN:.*]], label %[[LATCH:.*]], !prof [[PROF19:![0-9]+]] |
| ; VF4IC1: [[IF_THEN]]: |
| ; VF4IC1: [[LATCH]]: |
| ; VF4IC1: br i1 [[EXITCOND:%.*]], label %[[EXIT]], label %[[LOOP]], !prof [[PROF8]], !llvm.loop [[LOOP20:![0-9]+]] |
| ; VF4IC1: [[EXIT]]: |
| ; |
| ; VF2IC2-LABEL: define void @predicated_store_almost_always_taken( |
| ; VF2IC2-SAME: ptr [[A:%.*]], i32 [[N:%.*]]) { |
| ; VF2IC2: [[ENTRY:.*:]] |
| ; VF2IC2: br i1 [[MIN_ITERS_CHECK:%.*]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]], !prof [[PROF0]] |
| ; VF2IC2: [[VECTOR_PH]]: |
| ; VF2IC2: [[VECTOR_BODY:.*]]: |
| ; VF2IC2: br i1 [[TMP4:%.*]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]] |
| ; VF2IC2: [[PRED_STORE_IF]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE]]: |
| ; VF2IC2: br i1 [[TMP7:%.*]], label %[[PRED_STORE_IF2:.*]], label %[[PRED_STORE_CONTINUE3:.*]] |
| ; VF2IC2: [[PRED_STORE_IF2]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE3]]: |
| ; VF2IC2: br i1 [[TMP12:%.*]], label %[[PRED_STORE_IF4:.*]], label %[[PRED_STORE_CONTINUE5:.*]] |
| ; VF2IC2: [[PRED_STORE_IF4]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE5]]: |
| ; VF2IC2: br i1 [[TMP17:%.*]], label %[[PRED_STORE_IF6:.*]], label %[[PRED_STORE_CONTINUE7:.*]] |
| ; VF2IC2: [[PRED_STORE_IF6]]: |
| ; VF2IC2: [[PRED_STORE_CONTINUE7]]: |
| ; VF2IC2: br i1 [[TMP22:%.*]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !prof [[PROF1]], !llvm.loop [[LOOP18:![0-9]+]] |
| ; VF2IC2: [[MIDDLE_BLOCK]]: |
| ; VF2IC2: br i1 [[CMP_N:%.*]], label %[[EXIT:.*]], label %[[SCALAR_PH]], !prof [[PROF6]] |
| ; VF2IC2: [[SCALAR_PH]]: |
| ; VF2IC2: [[LOOP:.*]]: |
| ; VF2IC2: br i1 [[CMP:%.*]], label %[[IF_THEN:.*]], label %[[LATCH:.*]], !prof [[PROF19:![0-9]+]] |
| ; VF2IC2: [[IF_THEN]]: |
| ; VF2IC2: [[LATCH]]: |
| ; VF2IC2: br i1 [[EXITCOND:%.*]], label %[[EXIT]], label %[[LOOP]], !prof [[PROF8]], !llvm.loop [[LOOP20:![0-9]+]] |
| ; VF2IC2: [[EXIT]]: |
| ; |
| entry: |
| br label %loop |
| |
| loop: |
| %iv = phi i32 [ 0, %entry ], [ %iv.next, %latch ] |
| %gep = getelementptr inbounds i32, ptr %a, i32 %iv |
| %val = load i32, ptr %gep, align 4 |
| %cmp = icmp sgt i32 %val, 0 |
| br i1 %cmp, label %if.then, label %latch, !prof !4 |
| |
| if.then: |
| %add = add i32 %val, 1 |
| store i32 %add, ptr %gep, align 4 |
| br label %latch |
| |
| latch: |
| %iv.next = add nuw nsw i32 %iv, 1 |
| %exitcond = icmp eq i32 %iv.next, %n |
| br i1 %exitcond, label %exit, label %loop, !prof !0 |
| |
| exit: |
| ret void |
| } |
| |
| !0 = !{!"branch_weights", i32 1, i32 1000} |
| !1 = !{!"branch_weights", i32 1, i32 7} |
| !2 = !{!"branch_weights", i32 1, i32 1} |
| !3 = !{!"branch_weights", i32 1, i32 3} |
| !4 = !{!"branch_weights", i32 1000, i32 1} |
| ;. |
| ; VF4IC1: [[PROF0]] = !{!"branch_weights", i32 1, i32 127} |
| ; VF4IC1: [[PROF1]] = !{!"branch_weights", i32 1, i32 249} |
| ; VF4IC1: [[LOOP2]] = distinct !{[[LOOP2]], [[META3:![0-9]+]], [[META4:![0-9]+]], [[META5:![0-9]+]]} |
| ; VF4IC1: [[META3]] = !{!"llvm.loop.isvectorized", i32 1} |
| ; VF4IC1: [[META4]] = !{!"llvm.loop.unroll.runtime.disable"} |
| ; VF4IC1: [[META5]] = !{!"llvm.loop.estimated_trip_count", i32 250} |
| ; VF4IC1: [[PROF6]] = !{!"branch_weights", i32 1, i32 3} |
| ; VF4IC1: [[PROF7]] = !{!"branch_weights", i32 1, i32 7} |
| ; VF4IC1: [[PROF8]] = !{!"branch_weights", i32 1, i32 0} |
| ; VF4IC1: [[LOOP9]] = distinct !{[[LOOP9]], [[META4]], [[META3]], [[META10:![0-9]+]]} |
| ; VF4IC1: [[META10]] = !{!"llvm.loop.estimated_trip_count", i32 1} |
| ; VF4IC1: [[LOOP11]] = distinct !{[[LOOP11]], [[META3]], [[META4]], [[META5]]} |
| ; VF4IC1: [[PROF12]] = !{!"branch_weights", i32 1, i32 1} |
| ; VF4IC1: [[LOOP13]] = distinct !{[[LOOP13]], [[META3]], [[META10]]} |
| ; VF4IC1: [[LOOP14]] = distinct !{[[LOOP14]], [[META3]], [[META4]]} |
| ; VF4IC1: [[LOOP15]] = distinct !{[[LOOP15]], [[META4]], [[META3]]} |
| ; VF4IC1: [[LOOP16]] = distinct !{[[LOOP16]], [[META3]], [[META4]], [[META5]]} |
| ; VF4IC1: [[LOOP17]] = distinct !{[[LOOP17]], [[META4]], [[META3]], [[META10]]} |
| ; VF4IC1: [[LOOP18]] = distinct !{[[LOOP18]], [[META3]], [[META4]], [[META5]]} |
| ; VF4IC1: [[PROF19]] = !{!"branch_weights", i32 1000, i32 1} |
| ; VF4IC1: [[LOOP20]] = distinct !{[[LOOP20]], [[META4]], [[META3]], [[META10]]} |
| ;. |
| ; VF2IC2: [[PROF0]] = !{!"branch_weights", i32 1, i32 127} |
| ; VF2IC2: [[PROF1]] = !{!"branch_weights", i32 1, i32 249} |
| ; VF2IC2: [[LOOP2]] = distinct !{[[LOOP2]], [[META3:![0-9]+]], [[META4:![0-9]+]], [[META5:![0-9]+]]} |
| ; VF2IC2: [[META3]] = !{!"llvm.loop.isvectorized", i32 1} |
| ; VF2IC2: [[META4]] = !{!"llvm.loop.unroll.runtime.disable"} |
| ; VF2IC2: [[META5]] = !{!"llvm.loop.estimated_trip_count", i32 250} |
| ; VF2IC2: [[PROF6]] = !{!"branch_weights", i32 1, i32 3} |
| ; VF2IC2: [[PROF7]] = !{!"branch_weights", i32 1, i32 7} |
| ; VF2IC2: [[PROF8]] = !{!"branch_weights", i32 1, i32 0} |
| ; VF2IC2: [[LOOP9]] = distinct !{[[LOOP9]], [[META4]], [[META3]], [[META10:![0-9]+]]} |
| ; VF2IC2: [[META10]] = !{!"llvm.loop.estimated_trip_count", i32 1} |
| ; VF2IC2: [[LOOP11]] = distinct !{[[LOOP11]], [[META3]], [[META4]], [[META5]]} |
| ; VF2IC2: [[PROF12]] = !{!"branch_weights", i32 1, i32 1} |
| ; VF2IC2: [[LOOP13]] = distinct !{[[LOOP13]], [[META3]], [[META10]]} |
| ; VF2IC2: [[LOOP14]] = distinct !{[[LOOP14]], [[META3]], [[META4]]} |
| ; VF2IC2: [[LOOP15]] = distinct !{[[LOOP15]], [[META4]], [[META3]]} |
| ; VF2IC2: [[LOOP16]] = distinct !{[[LOOP16]], [[META3]], [[META4]], [[META5]]} |
| ; VF2IC2: [[LOOP17]] = distinct !{[[LOOP17]], [[META4]], [[META3]], [[META10]]} |
| ; VF2IC2: [[LOOP18]] = distinct !{[[LOOP18]], [[META3]], [[META4]], [[META5]]} |
| ; VF2IC2: [[PROF19]] = !{!"branch_weights", i32 1000, i32 1} |
| ; VF2IC2: [[LOOP20]] = distinct !{[[LOOP20]], [[META4]], [[META3]], [[META10]]} |
| ;. |
