| ; 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) { |
| ; CHECK-LABEL: define i64 @select_icmp_const( |
| ; CHECK-SAME: ptr [[A:%.*]], i64 [[N:%.*]]) { |
| ; CHECK-NEXT: [[ITER_CHECK:.*]]: |
| ; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], 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 i64 [[N]], 4 |
| ; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[VEC_EPILOG_PH:.*]], label %[[VECTOR_PH:.*]] |
| ; CHECK: [[VECTOR_PH]]: |
| ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], 4 |
| ; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]] |
| ; CHECK-NEXT: br label %[[VECTOR_BODY:.*]] |
| ; CHECK: [[VECTOR_BODY]]: |
| ; CHECK-NEXT: [[TMP0:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i64> [ splat (i64 -9223372036854775808), %[[VECTOR_PH]] ], [ [[TMP4:%.*]], %[[VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[TMP0]] |
| ; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i64>, ptr [[TMP1]], align 8 |
| ; CHECK-NEXT: [[TMP3:%.*]] = icmp eq <4 x i64> [[WIDE_LOAD]], splat (i64 3) |
| ; CHECK-NEXT: [[TMP4]] = select <4 x i1> [[TMP3]], <4 x i64> [[VEC_IND]], <4 x i64> [[VEC_PHI]] |
| ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[TMP0]], 4 |
| ; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], splat (i64 4) |
| ; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] |
| ; CHECK: [[MIDDLE_BLOCK]]: |
| ; CHECK-NEXT: [[TMP6:%.*]] = call i64 @llvm.vector.reduce.smax.v4i64(<4 x i64> [[TMP4]]) |
| ; CHECK-NEXT: [[RDX_SELECT_CMP:%.*]] = icmp ne i64 [[TMP6]], -9223372036854775808 |
| ; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP]], i64 [[TMP6]], i64 3 |
| ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[VEC_EPILOG_ITER_CHECK:.*]] |
| ; CHECK: [[VEC_EPILOG_ITER_CHECK]]: |
| ; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i64 [[N]], [[N_VEC]] |
| ; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[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: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] |
| ; CHECK-NEXT: [[BC_MERGE_RDX1:%.*]] = phi i64 [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 3, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] |
| ; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i64 [[BC_MERGE_RDX1]], 3 |
| ; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = select i1 [[TMP14]], i64 -9223372036854775808, i64 [[BC_MERGE_RDX1]] |
| ; CHECK-NEXT: [[N_MOD_VF2:%.*]] = urem i64 [[N]], 4 |
| ; CHECK-NEXT: [[N_VEC3:%.*]] = sub i64 [[N]], [[N_MOD_VF2]] |
| ; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[BC_MERGE_RDX]], i64 0 |
| ; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x i64> [[DOTSPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer |
| ; CHECK-NEXT: [[DOTSPLATINSERT8:%.*]] = insertelement <4 x i64> poison, i64 [[BC_RESUME_VAL]], i64 0 |
| ; CHECK-NEXT: [[DOTSPLAT9:%.*]] = shufflevector <4 x i64> [[DOTSPLATINSERT8]], <4 x i64> poison, <4 x i32> zeroinitializer |
| ; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i64> [[DOTSPLAT9]], <i64 0, i64 1, i64 2, i64 3> |
| ; CHECK-NEXT: br label %[[VEC_EPILOG_VECTOR_BODY:.*]] |
| ; CHECK: [[VEC_EPILOG_VECTOR_BODY]]: |
| ; CHECK-NEXT: [[TMP7:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT9:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[VEC_IND5:%.*]] = phi <4 x i64> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT6:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[VEC_PHI7:%.*]] = phi <4 x i64> [ [[DOTSPLAT]], %[[VEC_EPILOG_PH]] ], [ [[TMP11:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[TMP7]] |
| ; CHECK-NEXT: [[WIDE_LOAD8:%.*]] = load <4 x i64>, ptr [[TMP8]], align 8 |
| ; CHECK-NEXT: [[TMP10:%.*]] = icmp eq <4 x i64> [[WIDE_LOAD8]], splat (i64 3) |
| ; CHECK-NEXT: [[TMP11]] = select <4 x i1> [[TMP10]], <4 x i64> [[VEC_IND5]], <4 x i64> [[VEC_PHI7]] |
| ; CHECK-NEXT: [[INDEX_NEXT9]] = add nuw i64 [[TMP7]], 4 |
| ; CHECK-NEXT: [[VEC_IND_NEXT6]] = add <4 x i64> [[VEC_IND5]], splat (i64 4) |
| ; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT9]], [[N_VEC3]] |
| ; CHECK-NEXT: br i1 [[TMP12]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]] |
| ; CHECK: [[VEC_EPILOG_MIDDLE_BLOCK]]: |
| ; CHECK-NEXT: [[TMP13:%.*]] = call i64 @llvm.vector.reduce.smax.v4i64(<4 x i64> [[TMP11]]) |
| ; CHECK-NEXT: [[RDX_SELECT_CMP10:%.*]] = icmp ne i64 [[TMP13]], -9223372036854775808 |
| ; CHECK-NEXT: [[RDX_SELECT11:%.*]] = select i1 [[RDX_SELECT_CMP10]], i64 [[TMP13]], i64 3 |
| ; CHECK-NEXT: [[CMP_N12:%.*]] = icmp eq i64 [[N]], [[N_VEC3]] |
| ; CHECK-NEXT: br i1 [[CMP_N12]], label %[[EXIT]], label %[[VEC_EPILOG_SCALAR_PH]] |
| ; CHECK: [[VEC_EPILOG_SCALAR_PH]]: |
| ; CHECK-NEXT: [[BC_RESUME_VAL15:%.*]] = phi i64 [ [[N_VEC3]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[ITER_CHECK]] ] |
| ; CHECK-NEXT: [[BC_MERGE_RDX16:%.*]] = phi i64 [ [[RDX_SELECT11]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 3, %[[ITER_CHECK]] ] |
| ; CHECK-NEXT: br label %[[LOOP:.*]] |
| ; CHECK: [[LOOP]]: |
| ; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL15]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] |
| ; CHECK-NEXT: [[RDX:%.*]] = phi i64 [ [[BC_MERGE_RDX16]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ] |
| ; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]] |
| ; CHECK-NEXT: [[L:%.*]] = load i64, ptr [[GEP]], align 8 |
| ; CHECK-NEXT: [[C:%.*]] = icmp eq i64 [[L]], 3 |
| ; CHECK-NEXT: [[SEL]] = select i1 [[C]], i64 [[IV]], i64 [[RDX]] |
| ; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1 |
| ; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]] |
| ; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP4:![0-9]+]] |
| ; CHECK: [[EXIT]]: |
| ; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i64 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT11]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ] |
| ; CHECK-NEXT: ret i64 [[SEL_LCSSA]] |
| ; |
| entry: |
| br label %loop |
| |
| loop: |
| %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ] |
| %rdx = phi i64 [ 3, %entry ], [ %sel, %loop ] |
| %gep = getelementptr inbounds i64, ptr %a, i64 %iv |
| %l = load i64, ptr %gep, align 8 |
| %c = icmp eq i64 %l, 3 |
| %sel = select i1 %c, i64 %iv, i64 %rdx |
| %iv.next = add nuw nsw i64 %iv, 1 |
| %ec = icmp eq i64 %iv.next, %n |
| br i1 %ec, label %exit, label %loop |
| |
| exit: |
| ret i64 %sel |
| } |
| |
| define i64 @select_fcmp_const_fast(ptr %a, i64 %n) { |
| ; CHECK-LABEL: define i64 @select_fcmp_const_fast( |
| ; CHECK-SAME: ptr [[A:%.*]], i64 [[N:%.*]]) { |
| ; CHECK-NEXT: [[ITER_CHECK:.*]]: |
| ; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], 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 i64 [[N]], 4 |
| ; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[VEC_EPILOG_PH:.*]], label %[[VECTOR_PH:.*]] |
| ; CHECK: [[VECTOR_PH]]: |
| ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], 4 |
| ; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]] |
| ; CHECK-NEXT: br label %[[VECTOR_BODY:.*]] |
| ; CHECK: [[VECTOR_BODY]]: |
| ; CHECK-NEXT: [[TMP0:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i64> [ splat (i64 -9223372036854775808), %[[VECTOR_PH]] ], [ [[TMP4:%.*]], %[[VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP0]] |
| ; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP1]], align 4 |
| ; CHECK-NEXT: [[TMP3:%.*]] = fcmp fast ueq <4 x float> [[WIDE_LOAD]], splat (float 3.000000e+00) |
| ; CHECK-NEXT: [[TMP4]] = select <4 x i1> [[TMP3]], <4 x i64> [[VEC_IND]], <4 x i64> [[VEC_PHI]] |
| ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[TMP0]], 4 |
| ; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], splat (i64 4) |
| ; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]] |
| ; CHECK: [[MIDDLE_BLOCK]]: |
| ; CHECK-NEXT: [[TMP6:%.*]] = call i64 @llvm.vector.reduce.smax.v4i64(<4 x i64> [[TMP4]]) |
| ; CHECK-NEXT: [[RDX_SELECT_CMP:%.*]] = icmp ne i64 [[TMP6]], -9223372036854775808 |
| ; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP]], i64 [[TMP6]], i64 2 |
| ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]] |
| ; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[VEC_EPILOG_ITER_CHECK:.*]] |
| ; CHECK: [[VEC_EPILOG_ITER_CHECK]]: |
| ; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i64 [[N]], [[N_VEC]] |
| ; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[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: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] |
| ; CHECK-NEXT: [[BC_MERGE_RDX1:%.*]] = phi i64 [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 2, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] |
| ; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i64 [[BC_MERGE_RDX1]], 2 |
| ; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = select i1 [[TMP14]], i64 -9223372036854775808, i64 [[BC_MERGE_RDX1]] |
| ; CHECK-NEXT: [[N_MOD_VF2:%.*]] = urem i64 [[N]], 4 |
| ; CHECK-NEXT: [[N_VEC3:%.*]] = sub i64 [[N]], [[N_MOD_VF2]] |
| ; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[BC_MERGE_RDX]], i64 0 |
| ; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x i64> [[DOTSPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer |
| ; CHECK-NEXT: [[DOTSPLATINSERT8:%.*]] = insertelement <4 x i64> poison, i64 [[BC_RESUME_VAL]], i64 0 |
| ; CHECK-NEXT: [[DOTSPLAT9:%.*]] = shufflevector <4 x i64> [[DOTSPLATINSERT8]], <4 x i64> poison, <4 x i32> zeroinitializer |
| ; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i64> [[DOTSPLAT9]], <i64 0, i64 1, i64 2, i64 3> |
| ; CHECK-NEXT: br label %[[VEC_EPILOG_VECTOR_BODY:.*]] |
| ; CHECK: [[VEC_EPILOG_VECTOR_BODY]]: |
| ; CHECK-NEXT: [[TMP7:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT9:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[VEC_IND5:%.*]] = phi <4 x i64> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT6:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[VEC_PHI7:%.*]] = phi <4 x i64> [ [[DOTSPLAT]], %[[VEC_EPILOG_PH]] ], [ [[TMP11:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] |
| ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP7]] |
| ; CHECK-NEXT: [[WIDE_LOAD8:%.*]] = load <4 x float>, ptr [[TMP8]], align 4 |
| ; CHECK-NEXT: [[TMP10:%.*]] = fcmp fast ueq <4 x float> [[WIDE_LOAD8]], splat (float 3.000000e+00) |
| ; CHECK-NEXT: [[TMP11]] = select <4 x i1> [[TMP10]], <4 x i64> [[VEC_IND5]], <4 x i64> [[VEC_PHI7]] |
| ; CHECK-NEXT: [[INDEX_NEXT9]] = add nuw i64 [[TMP7]], 4 |
| ; CHECK-NEXT: [[VEC_IND_NEXT6]] = add <4 x i64> [[VEC_IND5]], splat (i64 4) |
| ; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT9]], [[N_VEC3]] |
| ; CHECK-NEXT: br i1 [[TMP12]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]] |
| ; CHECK: [[VEC_EPILOG_MIDDLE_BLOCK]]: |
| ; CHECK-NEXT: [[TMP13:%.*]] = call i64 @llvm.vector.reduce.smax.v4i64(<4 x i64> [[TMP11]]) |
| ; CHECK-NEXT: [[RDX_SELECT_CMP10:%.*]] = icmp ne i64 [[TMP13]], -9223372036854775808 |
| ; CHECK-NEXT: [[RDX_SELECT11:%.*]] = select i1 [[RDX_SELECT_CMP10]], i64 [[TMP13]], i64 2 |
| ; CHECK-NEXT: [[CMP_N12:%.*]] = icmp eq i64 [[N]], [[N_VEC3]] |
| ; CHECK-NEXT: br i1 [[CMP_N12]], label %[[EXIT]], label %[[VEC_EPILOG_SCALAR_PH]] |
| ; CHECK: [[VEC_EPILOG_SCALAR_PH]]: |
| ; CHECK-NEXT: [[BC_RESUME_VAL15:%.*]] = phi i64 [ [[N_VEC3]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[ITER_CHECK]] ] |
| ; CHECK-NEXT: [[BC_MERGE_RDX16:%.*]] = phi i64 [ [[RDX_SELECT11]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 2, %[[ITER_CHECK]] ] |
| ; CHECK-NEXT: br label %[[LOOP:.*]] |
| ; CHECK: [[LOOP]]: |
| ; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL15]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] |
| ; CHECK-NEXT: [[RDX:%.*]] = phi i64 [ [[BC_MERGE_RDX16]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ] |
| ; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[IV]] |
| ; CHECK-NEXT: [[L:%.*]] = load float, ptr [[GEP]], align 4 |
| ; CHECK-NEXT: [[C:%.*]] = fcmp fast ueq float [[L]], 3.000000e+00 |
| ; CHECK-NEXT: [[SEL]] = select i1 [[C]], i64 [[IV]], i64 [[RDX]] |
| ; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1 |
| ; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]] |
| ; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP7:![0-9]+]] |
| ; CHECK: [[EXIT]]: |
| ; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i64 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT11]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ] |
| ; CHECK-NEXT: ret i64 [[SEL_LCSSA]] |
| ; |
| entry: |
| br label %loop |
| |
| loop: |
| %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ] |
| %rdx = phi i64 [ 2, %entry ], [ %sel, %loop ] |
| %gep = getelementptr inbounds float, ptr %a, i64 %iv |
| %l = load float, ptr %gep, align 4 |
| %c = fcmp fast ueq float %l, 3.0 |
| %sel = select i1 %c, i64 %iv, i64 %rdx |
| %iv.next = add nuw nsw i64 %iv, 1 |
| %ec = icmp eq i64 %iv.next, %n |
| br i1 %ec, label %exit, label %loop |
| |
| exit: |
| ret i64 %sel |
| } |
| |
| 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: [[FR:%.*]] = freeze i8 [[START]] |
| ; 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: [[WIDE_LOAD:%.*]] = load <4 x i8>, ptr [[TMP5]], 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 [[FR]] |
| ; 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]] ], [ [[FR]], %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] |
| ; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i8 [[BC_MERGE_RDX]], [[FR]] |
| ; 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 [[TMP12]], i64 0 |
| ; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x i8> [[DOTSPLATINSERT]], <4 x i8> poison, <4 x i32> zeroinitializer |
| ; CHECK-NEXT: [[DOTSPLATINSERT8:%.*]] = insertelement <4 x i8> poison, i8 [[BC_RESUME_VAL]], i64 0 |
| ; CHECK-NEXT: [[DOTSPLAT9:%.*]] = shufflevector <4 x i8> [[DOTSPLATINSERT8]], <4 x i8> poison, <4 x i32> zeroinitializer |
| ; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i8> [[DOTSPLAT9]], <i8 0, i8 1, i8 2, i8 3> |
| ; 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> [ [[DOTSPLAT]], %[[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: [[WIDE_LOAD10:%.*]] = load <4 x i8>, ptr [[TMP14]], 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 [[FR]] |
| ; 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 |
| } |
