[LV] Add epilogue vectorization tests for FindLastIV reductions. Add missing test coverage for #126836.
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll b/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll new file mode 100644 index 0000000..2540496 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll
@@ -0,0 +1,122 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5 +; RUN: opt -passes=loop-vectorize -mtriple=arm64-apple-macosx -S %s | FileCheck %s + +define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) { +; CHECK-LABEL: define i8 @select_icmp_var_start( +; CHECK-SAME: ptr [[A:%.*]], i8 [[N:%.*]], i8 [[START:%.*]]) { +; CHECK-NEXT: [[ITER_CHECK:.*]]: +; CHECK-NEXT: [[TMP0:%.*]] = add i8 [[N]], -1 +; CHECK-NEXT: [[TMP1:%.*]] = zext i8 [[TMP0]] to i32 +; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 1 +; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP2]], 8 +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH:.*]], label %[[VECTOR_MAIN_LOOP_ITER_CHECK:.*]] +; CHECK: [[VECTOR_MAIN_LOOP_ITER_CHECK]]: +; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i32 [[TMP2]], 32 +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[VEC_EPILOG_PH:.*]], label %[[VECTOR_PH:.*]] +; CHECK: [[VECTOR_PH]]: +; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP2]], 32 +; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF]] +; CHECK-NEXT: [[TMP3:%.*]] = trunc i32 [[N_VEC]] to i8 +; CHECK-NEXT: br label %[[VECTOR_BODY:.*]] +; CHECK: [[VECTOR_BODY]]: +; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_IND:%.*]] = phi <16 x i8> [ <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <16 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP10:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <16 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP11:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[STEP_ADD:%.*]] = add <16 x i8> [[VEC_IND]], splat (i8 16) +; CHECK-NEXT: [[INDEX4:%.*]] = trunc i32 [[INDEX]] to i8 +; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[INDEX4]] +; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 0 +; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 16 +; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[TMP9]], align 8 +; CHECK-NEXT: [[WIDE_LOAD3:%.*]] = load <16 x i8>, ptr [[TMP7]], align 8 +; CHECK-NEXT: [[TMP17:%.*]] = icmp eq <16 x i8> [[WIDE_LOAD]], splat (i8 3) +; CHECK-NEXT: [[TMP23:%.*]] = icmp eq <16 x i8> [[WIDE_LOAD3]], splat (i8 3) +; CHECK-NEXT: [[TMP10]] = select <16 x i1> [[TMP17]], <16 x i8> [[VEC_IND]], <16 x i8> [[VEC_PHI]] +; CHECK-NEXT: [[TMP11]] = select <16 x i1> [[TMP23]], <16 x i8> [[STEP_ADD]], <16 x i8> [[VEC_PHI2]] +; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 32 +; CHECK-NEXT: [[VEC_IND_NEXT]] = add <16 x i8> [[STEP_ADD]], splat (i8 16) +; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]] +; CHECK-NEXT: br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] +; CHECK: [[MIDDLE_BLOCK]]: +; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call <16 x i8> @llvm.smax.v16i8(<16 x i8> [[TMP10]], <16 x i8> [[TMP11]]) +; CHECK-NEXT: [[TMP13:%.*]] = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> [[RDX_MINMAX]]) +; CHECK-NEXT: [[RDX_SELECT_CMP12:%.*]] = icmp ne i8 [[TMP13]], -128 +; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP12]], i8 [[TMP13]], i8 [[START]] +; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC]] +; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[VEC_EPILOG_ITER_CHECK:.*]] +; CHECK: [[VEC_EPILOG_ITER_CHECK]]: +; CHECK-NEXT: [[IND_END:%.*]] = trunc i32 [[N_VEC]] to i8 +; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i32 [[TMP2]], [[N_VEC]] +; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i32 [[N_VEC_REMAINING]], 8 +; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]] +; CHECK: [[VEC_EPILOG_PH]]: +; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP3]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i8 [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i8 [[BC_MERGE_RDX]], [[START]] +; CHECK-NEXT: [[TMP15:%.*]] = select i1 [[TMP14]], i8 -128, i8 [[BC_MERGE_RDX]] +; CHECK-NEXT: [[N_MOD_VF4:%.*]] = urem i32 [[TMP2]], 8 +; CHECK-NEXT: [[N_VEC5:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF4]] +; CHECK-NEXT: [[TMP16:%.*]] = trunc i32 [[N_VEC5]] to i8 +; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <8 x i8> poison, i8 [[BC_RESUME_VAL]], i64 0 +; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <8 x i8> [[DOTSPLATINSERT]], <8 x i8> poison, <8 x i32> zeroinitializer +; CHECK-NEXT: [[INDUCTION:%.*]] = add <8 x i8> [[DOTSPLAT]], <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7> +; CHECK-NEXT: [[DOTSPLATINSERT10:%.*]] = insertelement <8 x i8> poison, i8 [[TMP15]], i64 0 +; CHECK-NEXT: [[DOTSPLAT11:%.*]] = shufflevector <8 x i8> [[DOTSPLATINSERT10]], <8 x i8> poison, <8 x i32> zeroinitializer +; CHECK-NEXT: br label %[[VEC_EPILOG_VECTOR_BODY:.*]] +; CHECK: [[VEC_EPILOG_VECTOR_BODY]]: +; CHECK-NEXT: [[INDEX6:%.*]] = phi i32 [ [[VEC_EPILOG_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT13:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_IND7:%.*]] = phi <8 x i8> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT8:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI9:%.*]] = phi <8 x i8> [ [[DOTSPLAT11]], %[[VEC_EPILOG_PH]] ], [ [[TMP20:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[IV:%.*]] = trunc i32 [[INDEX6]] to i8 +; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[IV]] +; CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds i8, ptr [[GEP]], i32 0 +; CHECK-NEXT: [[WIDE_LOAD12:%.*]] = load <8 x i8>, ptr [[TMP18]], align 8 +; CHECK-NEXT: [[TMP19:%.*]] = icmp eq <8 x i8> [[WIDE_LOAD12]], splat (i8 3) +; CHECK-NEXT: [[TMP20]] = select <8 x i1> [[TMP19]], <8 x i8> [[VEC_IND7]], <8 x i8> [[VEC_PHI9]] +; CHECK-NEXT: [[INDEX_NEXT13]] = add nuw i32 [[INDEX6]], 8 +; CHECK-NEXT: [[VEC_IND_NEXT8]] = add <8 x i8> [[VEC_IND7]], splat (i8 8) +; CHECK-NEXT: [[TMP21:%.*]] = icmp eq i32 [[INDEX_NEXT13]], [[N_VEC5]] +; CHECK-NEXT: br i1 [[TMP21]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]] +; CHECK: [[VEC_EPILOG_MIDDLE_BLOCK]]: +; CHECK-NEXT: [[TMP22:%.*]] = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> [[TMP20]]) +; CHECK-NEXT: [[RDX_SELECT_CMP14:%.*]] = icmp ne i8 [[TMP22]], -128 +; CHECK-NEXT: [[RDX_SELECT15:%.*]] = select i1 [[RDX_SELECT_CMP14]], i8 [[TMP22]], i8 [[START]] +; CHECK-NEXT: [[CMP_N16:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC5]] +; CHECK-NEXT: br i1 [[CMP_N16]], label %[[EXIT]], label %[[VEC_EPILOG_SCALAR_PH]] +; CHECK: [[VEC_EPILOG_SCALAR_PH]]: +; CHECK-NEXT: [[BC_RESUME_VAL17:%.*]] = phi i8 [ [[TMP16]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[ITER_CHECK]] ] +; CHECK-NEXT: [[BC_MERGE_RDX18:%.*]] = phi i8 [ [[RDX_SELECT15]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], %[[ITER_CHECK]] ] +; CHECK-NEXT: br label %[[LOOP:.*]] +; CHECK: [[LOOP]]: +; CHECK-NEXT: [[IV1:%.*]] = phi i8 [ [[BC_RESUME_VAL17]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX18]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[GEP1:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[IV1]] +; CHECK-NEXT: [[L:%.*]] = load i8, ptr [[GEP1]], align 8 +; CHECK-NEXT: [[C:%.*]] = icmp eq i8 [[L]], 3 +; CHECK-NEXT: [[SEL]] = select i1 [[C]], i8 [[IV1]], i8 [[RDX]] +; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i8 [[IV1]], 1 +; CHECK-NEXT: [[EC:%.*]] = icmp eq i8 [[IV_NEXT]], [[N]] +; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP4:![0-9]+]] +; CHECK: [[EXIT]]: +; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT15]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ] +; CHECK-NEXT: ret i8 [[SEL_LCSSA]] +; +entry: + br label %loop + +loop: + %iv = phi i8 [ 0, %entry ], [ %iv.next, %loop ] + %rdx = phi i8 [ %start, %entry ], [ %sel, %loop ] + %gep = getelementptr inbounds i8, ptr %a, i8 %iv + %l = load i8, ptr %gep, align 8 + %c = icmp eq i8 %l, 3 + %sel = select i1 %c, i8 %iv, i8 %rdx + %iv.next = add nuw nsw i8 %iv, 1 + %ec = icmp eq i8 %iv.next, %n + br i1 %ec, label %exit, label %loop + +exit: + ret i8 %sel +}
diff --git a/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll b/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll index c007d6b..ee154ea 100644 --- a/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll +++ b/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll
@@ -1,4 +1,4 @@ -; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5 +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5 ; RUN: opt -passes=loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -epilogue-vectorization-force-VF=4 -S < %s | FileCheck %s define i64 @select_icmp_const(ptr %a, i64 %n) { @@ -208,13 +208,116 @@ exit: ret i64 %sel } -;. -; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]} -; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1} -; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"} -; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META1]], [[META2]]} -; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META2]], [[META1]]} -; CHECK: [[LOOP5]] = distinct !{[[LOOP5]], [[META1]], [[META2]]} -; CHECK: [[LOOP6]] = distinct !{[[LOOP6]], [[META1]], [[META2]]} -; CHECK: [[LOOP7]] = distinct !{[[LOOP7]], [[META2]], [[META1]]} -;. + +define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) { +; CHECK-LABEL: define i8 @select_icmp_var_start( +; CHECK-SAME: ptr [[A:%.*]], i8 [[N:%.*]], i8 [[START:%.*]]) { +; CHECK-NEXT: [[ITER_CHECK:.*]]: +; CHECK-NEXT: [[TMP0:%.*]] = add i8 [[N]], -1 +; CHECK-NEXT: [[TMP1:%.*]] = zext i8 [[TMP0]] to i32 +; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 1 +; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP2]], 4 +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH:.*]], label %[[VECTOR_MAIN_LOOP_ITER_CHECK:.*]] +; CHECK: [[VECTOR_MAIN_LOOP_ITER_CHECK]]: +; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i32 [[TMP2]], 4 +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[VEC_EPILOG_PH:.*]], label %[[VECTOR_PH:.*]] +; CHECK: [[VECTOR_PH]]: +; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP2]], 4 +; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF]] +; CHECK-NEXT: [[TMP3:%.*]] = trunc i32 [[N_VEC]] to i8 +; CHECK-NEXT: br label %[[VECTOR_BODY:.*]] +; CHECK: [[VECTOR_BODY]]: +; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i8> [ <i8 0, i8 1, i8 2, i8 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP8:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[TMP4:%.*]] = trunc i32 [[INDEX]] to i8 +; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[TMP4]] +; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i8, ptr [[TMP5]], i32 0 +; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, ptr [[TMP6]], align 8 +; CHECK-NEXT: [[TMP7:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD]], splat (i8 3) +; CHECK-NEXT: [[TMP8]] = select <4 x i1> [[TMP7]], <4 x i8> [[VEC_IND]], <4 x i8> [[VEC_PHI]] +; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4 +; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i8> [[VEC_IND]], splat (i8 4) +; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]] +; CHECK-NEXT: br i1 [[TMP9]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]] +; CHECK: [[MIDDLE_BLOCK]]: +; CHECK-NEXT: [[TMP10:%.*]] = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> [[TMP8]]) +; CHECK-NEXT: [[RDX_SELECT_CMP:%.*]] = icmp ne i8 [[TMP10]], -128 +; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP]], i8 [[TMP10]], i8 [[START]] +; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC]] +; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[VEC_EPILOG_ITER_CHECK:.*]] +; CHECK: [[VEC_EPILOG_ITER_CHECK]]: +; CHECK-NEXT: [[IND_END:%.*]] = trunc i32 [[N_VEC]] to i8 +; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i32 [[TMP2]], [[N_VEC]] +; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i32 [[N_VEC_REMAINING]], 4 +; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]] +; CHECK: [[VEC_EPILOG_PH]]: +; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP3]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i8 [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i8 [[BC_MERGE_RDX]], [[START]] +; CHECK-NEXT: [[TMP12:%.*]] = select i1 [[TMP11]], i8 -128, i8 [[BC_MERGE_RDX]] +; CHECK-NEXT: [[N_MOD_VF2:%.*]] = urem i32 [[TMP2]], 4 +; CHECK-NEXT: [[N_VEC3:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF2]] +; CHECK-NEXT: [[TMP13:%.*]] = trunc i32 [[N_VEC3]] to i8 +; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x i8> poison, i8 [[BC_RESUME_VAL]], i64 0 +; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x i8> [[DOTSPLATINSERT]], <4 x i8> poison, <4 x i32> zeroinitializer +; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i8> [[DOTSPLAT]], <i8 0, i8 1, i8 2, i8 3> +; CHECK-NEXT: [[DOTSPLATINSERT8:%.*]] = insertelement <4 x i8> poison, i8 [[TMP12]], i64 0 +; CHECK-NEXT: [[DOTSPLAT9:%.*]] = shufflevector <4 x i8> [[DOTSPLATINSERT8]], <4 x i8> poison, <4 x i32> zeroinitializer +; CHECK-NEXT: br label %[[VEC_EPILOG_VECTOR_BODY:.*]] +; CHECK: [[VEC_EPILOG_VECTOR_BODY]]: +; CHECK-NEXT: [[INDEX4:%.*]] = phi i32 [ [[VEC_EPILOG_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT11:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_IND5:%.*]] = phi <4 x i8> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT6:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI7:%.*]] = phi <4 x i8> [ [[DOTSPLAT9]], %[[VEC_EPILOG_PH]] ], [ [[TMP17:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[OFFSET_IDX:%.*]] = trunc i32 [[INDEX4]] to i8 +; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[OFFSET_IDX]] +; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds i8, ptr [[TMP14]], i32 0 +; CHECK-NEXT: [[WIDE_LOAD10:%.*]] = load <4 x i8>, ptr [[TMP15]], align 8 +; CHECK-NEXT: [[TMP16:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD10]], splat (i8 3) +; CHECK-NEXT: [[TMP17]] = select <4 x i1> [[TMP16]], <4 x i8> [[VEC_IND5]], <4 x i8> [[VEC_PHI7]] +; CHECK-NEXT: [[INDEX_NEXT11]] = add nuw i32 [[INDEX4]], 4 +; CHECK-NEXT: [[VEC_IND_NEXT6]] = add <4 x i8> [[VEC_IND5]], splat (i8 4) +; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i32 [[INDEX_NEXT11]], [[N_VEC3]] +; CHECK-NEXT: br i1 [[TMP18]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]] +; CHECK: [[VEC_EPILOG_MIDDLE_BLOCK]]: +; CHECK-NEXT: [[TMP19:%.*]] = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> [[TMP17]]) +; CHECK-NEXT: [[RDX_SELECT_CMP12:%.*]] = icmp ne i8 [[TMP19]], -128 +; CHECK-NEXT: [[RDX_SELECT13:%.*]] = select i1 [[RDX_SELECT_CMP12]], i8 [[TMP19]], i8 [[START]] +; CHECK-NEXT: [[CMP_N14:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC3]] +; CHECK-NEXT: br i1 [[CMP_N14]], label %[[EXIT]], label %[[VEC_EPILOG_SCALAR_PH]] +; CHECK: [[VEC_EPILOG_SCALAR_PH]]: +; CHECK-NEXT: [[BC_RESUME_VAL15:%.*]] = phi i8 [ [[TMP13]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[ITER_CHECK]] ] +; CHECK-NEXT: [[BC_MERGE_RDX16:%.*]] = phi i8 [ [[RDX_SELECT13]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], %[[ITER_CHECK]] ] +; CHECK-NEXT: br label %[[LOOP:.*]] +; CHECK: [[LOOP]]: +; CHECK-NEXT: [[IV:%.*]] = phi i8 [ [[BC_RESUME_VAL15]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX16]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[IV]] +; CHECK-NEXT: [[L:%.*]] = load i8, ptr [[GEP]], align 8 +; CHECK-NEXT: [[C:%.*]] = icmp eq i8 [[L]], 3 +; CHECK-NEXT: [[SEL]] = select i1 [[C]], i8 [[IV]], i8 [[RDX]] +; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i8 [[IV]], 1 +; CHECK-NEXT: [[EC:%.*]] = icmp eq i8 [[IV_NEXT]], [[N]] +; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP10:![0-9]+]] +; CHECK: [[EXIT]]: +; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT13]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ] +; CHECK-NEXT: ret i8 [[SEL_LCSSA]] +; +entry: + br label %loop + +loop: + %iv = phi i8 [ 0, %entry ], [ %iv.next, %loop ] + %rdx = phi i8 [ %start, %entry ], [ %sel, %loop ] + %gep = getelementptr inbounds i8, ptr %a, i8 %iv + %l = load i8, ptr %gep, align 8 + %c = icmp eq i8 %l, 3 + %sel = select i1 %c, i8 %iv, i8 %rdx + %iv.next = add nuw nsw i8 %iv, 1 + %ec = icmp eq i8 %iv.next, %n + br i1 %ec, label %exit, label %loop + +exit: + ret i8 %sel +}