2 files changed, 198 insertions, 3 deletions
diff --git a/llvm/test/Transforms/InstCombine/ctlz-cttz.ll b/llvm/test/Transforms/InstCombine/ctlz-cttz.ll
new file mode 100644
index 0000000..871fb34
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/ctlz-cttz.ll
@@ -0,0 +1,145 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt < %s -S -passes=instcombine | FileCheck %s
+
+; ctpop(~i & (i - 1)) -> bitwidth - cttz(i, false)
+define i8 @ctlz_to_sub_bw_cttz(i8 %a0) {
+; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz(
+; CHECK-SAME: i8 [[A0:%.*]]) {
+; CHECK-NEXT:    [[TMP1:%.*]] = call range(i8 0, 9) i8 @llvm.cttz.i8(i8 [[A0]], i1 false)
+; CHECK-NEXT:    [[CLZ:%.*]] = sub nuw nsw i8 8, [[TMP1]]
+; CHECK-NEXT:    ret i8 [[CLZ]]
+;
+  %dec = add i8 %a0, -1
+  %not = xor i8 %a0, -1
+  %and = and i8 %dec, %not
+  %clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
+  ret i8 %clz
+}
+
+define i8 @ctlz_to_sub_bw_cttz_poison(i8 %a0) {
+; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_poison(
+; CHECK-SAME: i8 [[A0:%.*]]) {
+; CHECK-NEXT:    [[TMP1:%.*]] = call range(i8 0, 9) i8 @llvm.cttz.i8(i8 [[A0]], i1 false)
+; CHECK-NEXT:    [[CLZ:%.*]] = sub nuw nsw i8 8, [[TMP1]]
+; CHECK-NEXT:    ret i8 [[CLZ]]
+;
+  %dec = add i8 %a0, -1
+  %not = xor i8 %a0, -1
+  %and = and i8 %dec, %not
+  %clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 true)
+  ret i8 %clz
+}
+
+define i8 @ctlz_to_sub_bw_cttz_different_add(i8 %a0) {
+; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_different_add(
+; CHECK-SAME: i8 [[A0:%.*]]) {
+; CHECK-NEXT:    [[DEC:%.*]] = add i8 [[A0]], 1
+; CHECK-NEXT:    [[NOT:%.*]] = xor i8 [[A0]], -1
+; CHECK-NEXT:    [[AND:%.*]] = and i8 [[DEC]], [[NOT]]
+; CHECK-NEXT:    [[CLZ:%.*]] = tail call range(i8 0, 9) i8 @llvm.ctlz.i8(i8 [[AND]], i1 false)
+; CHECK-NEXT:    ret i8 [[CLZ]]
+;
+  %dec = add i8 %a0, 1
+  %not = xor i8 %a0, -1
+  %and = and i8 %dec, %not
+  %clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
+  ret i8 %clz
+}
+
+define i8 @ctlz_to_sub_bw_cttz_different_xor(i8 %a0) {
+; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_different_xor(
+; CHECK-SAME: i8 [[A0:%.*]]) {
+; CHECK-NEXT:    [[DEC:%.*]] = add i8 [[A0]], -1
+; CHECK-NEXT:    [[NOT:%.*]] = xor i8 [[A0]], 1
+; CHECK-NEXT:    [[AND:%.*]] = and i8 [[DEC]], [[NOT]]
+; CHECK-NEXT:    [[CLZ:%.*]] = tail call range(i8 0, 9) i8 @llvm.ctlz.i8(i8 [[AND]], i1 false)
+; CHECK-NEXT:    ret i8 [[CLZ]]
+;
+  %dec = add i8 %a0, -1
+  %not = xor i8 %a0, 1
+  %and = and i8 %dec, %not
+  %clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
+  ret i8 %clz
+}
+
+declare void @use(i8)
+
+define i8 @ctlz_to_sub_bw_cttz_multi_use_dec(i8 %a0) {
+; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_multi_use_dec(
+; CHECK-SAME: i8 [[A0:%.*]]) {
+; CHECK-NEXT:    [[DEC:%.*]] = add i8 [[A0]], -1
+; CHECK-NEXT:    call void @use(i8 [[DEC]])
+; CHECK-NEXT:    [[TMP1:%.*]] = call range(i8 0, 9) i8 @llvm.cttz.i8(i8 [[A0]], i1 false)
+; CHECK-NEXT:    [[CLZ:%.*]] = sub nuw nsw i8 8, [[TMP1]]
+; CHECK-NEXT:    ret i8 [[CLZ]]
+;
+  %dec = add i8 %a0, -1
+  call void @use(i8 %dec)
+  %not = xor i8 %a0, -1
+  %and = and i8 %dec, %not
+  %clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
+  ret i8 %clz
+}
+
+define i8 @ctlz_to_sub_bw_cttz_multi_use_not(i8 %a0) {
+; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_multi_use_not(
+; CHECK-SAME: i8 [[A0:%.*]]) {
+; CHECK-NEXT:    [[NOT:%.*]] = xor i8 [[A0]], -1
+; CHECK-NEXT:    call void @use(i8 [[NOT]])
+; CHECK-NEXT:    [[TMP1:%.*]] = call range(i8 0, 9) i8 @llvm.cttz.i8(i8 [[A0]], i1 false)
+; CHECK-NEXT:    [[CLZ:%.*]] = sub nuw nsw i8 8, [[TMP1]]
+; CHECK-NEXT:    ret i8 [[CLZ]]
+;
+  %dec = add i8 %a0, -1
+  %not = xor i8 %a0, -1
+  call void @use(i8 %not)
+  %and = and i8 %dec, %not
+  %clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
+  ret i8 %clz
+}
+
+define i8 @ctlz_to_sub_bw_cttz_multi_use_and(i8 %a0) {
+; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_multi_use_and(
+; CHECK-SAME: i8 [[A0:%.*]]) {
+; CHECK-NEXT:    [[DEC:%.*]] = add i8 [[A0]], -1
+; CHECK-NEXT:    [[NOT:%.*]] = xor i8 [[A0]], -1
+; CHECK-NEXT:    [[AND:%.*]] = and i8 [[DEC]], [[NOT]]
+; CHECK-NEXT:    call void @use(i8 [[AND]])
+; CHECK-NEXT:    [[CLZ:%.*]] = tail call range(i8 0, 9) i8 @llvm.ctlz.i8(i8 [[AND]], i1 false)
+; CHECK-NEXT:    ret i8 [[CLZ]]
+;
+  %dec = add i8 %a0, -1
+  %not = xor i8 %a0, -1
+  %and = and i8 %dec, %not
+  call void @use(i8 %and)
+  %clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
+  ret i8 %clz
+}
+
+define i8 @ctlz_to_sub_bw_cttz_commute_and(i8 %a0) {
+; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_commute_and(
+; CHECK-SAME: i8 [[A0:%.*]]) {
+; CHECK-NEXT:    [[TMP1:%.*]] = call range(i8 0, 9) i8 @llvm.cttz.i8(i8 [[A0]], i1 false)
+; CHECK-NEXT:    [[CLZ:%.*]] = sub nuw nsw i8 8, [[TMP1]]
+; CHECK-NEXT:    ret i8 [[CLZ]]
+;
+  %dec = add i8 %a0, -1
+  %not = xor i8 %a0, -1
+  %and = and i8 %not, %dec
+  %clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
+  ret i8 %clz
+}
+
+define <2 x i8> @ctlz_to_sub_bw_cttz_vec_splat(<2 x i8> %a0) {
+; CHECK-LABEL: define <2 x i8> @ctlz_to_sub_bw_cttz_vec_splat(
+; CHECK-SAME: <2 x i8> [[A0:%.*]]) {
+; CHECK-NEXT:    [[TMP1:%.*]] = call range(i8 0, 9) <2 x i8> @llvm.cttz.v2i8(<2 x i8> [[A0]], i1 false)
+; CHECK-NEXT:    [[CLZ:%.*]] = sub nuw nsw <2 x i8> splat (i8 8), [[TMP1]]
+; CHECK-NEXT:    ret <2 x i8> [[CLZ]]
+;
+  %dec = add <2 x i8> %a0, <i8 -1, i8 -1>
+  %not = xor <2 x i8> %a0, <i8 -1, i8 -1>
+  %and = and <2 x i8> %dec, %not
+  %clz = tail call <2 x i8>@llvm.ctlz.v2i8(<2 x i8> %and, i1 false)
+  ret <2 x i8> %clz
+}
diff --git a/llvm/test/Transforms/InstCombine/scmp.ll b/llvm/test/Transforms/InstCombine/scmp.ll
index c0be5b9..2ae062cd 100644
--- a/llvm/test/Transforms/InstCombine/scmp.ll
+++ b/llvm/test/Transforms/InstCombine/scmp.ll
@@ -519,9 +519,7 @@ define <3 x i2> @scmp_unary_shuffle_ops(<3 x i8> %x, <3 x i8> %y) {
 define i32 @scmp_sgt_slt(i32 %a) {
 ; CHECK-LABEL: define i32 @scmp_sgt_slt(
 ; CHECK-SAME: i32 [[A:%.*]]) {
-; CHECK-NEXT:    [[A_LOBIT:%.*]] = ashr i32 [[A]], 31
-; CHECK-NEXT:    [[CMP_INV:%.*]] = icmp slt i32 [[A]], 1
-; CHECK-NEXT:    [[RETVAL_0:%.*]] = select i1 [[CMP_INV]], i32 [[A_LOBIT]], i32 1
+; CHECK-NEXT:    [[RETVAL_0:%.*]] = call i32 @llvm.scmp.i32.i32(i32 [[A]], i32 0)
 ; CHECK-NEXT:    ret i32 [[RETVAL_0]]
 ;
   %cmp = icmp sgt i32 %a, 0
@@ -747,3 +745,55 @@ define i8 @scmp_from_select_eq_and_gt_neg3(i32 %x, i32 %y) {
   %r = select i1 %eq, i8 0, i8 %sel1
   ret i8 %r
 }
+
+define i32 @scmp_ashr(i32 %a) {
+; CHECK-LABEL: define i32 @scmp_ashr(
+; CHECK-SAME: i32 [[A:%.*]]) {
+; CHECK-NEXT:    [[RETVAL_0:%.*]] = call i32 @llvm.scmp.i32.i32(i32 [[A]], i32 0)
+; CHECK-NEXT:    ret i32 [[RETVAL_0]]
+;
+  %a.lobit = ashr i32 %a, 31
+  %cmp.inv = icmp slt i32 %a, 1
+  %retval.0 = select i1 %cmp.inv, i32 %a.lobit, i32 1
+  ret i32 %retval.0
+}
+
+; select (icmp sgt X, 0), 1, ashr X, bitwidth-1 -> scmp(X, 0)
+define i8 @scmp_ashr_sgt_pattern(i8 %a) {
+; CHECK-LABEL: define i8 @scmp_ashr_sgt_pattern(
+; CHECK-SAME: i8 [[A:%.*]]) {
+; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.scmp.i8.i8(i8 [[A]], i8 0)
+; CHECK-NEXT:    ret i8 [[R]]
+;
+  %a.lobit = ashr i8 %a, 7
+  %cmp = icmp sgt i8 %a, 0
+  %retval = select i1 %cmp, i8 1, i8 %a.lobit
+  ret i8 %retval
+}
+
+; select (icmp slt X, 1), ashr X, bitwidth-1, 1 -> scmp(X, 0)
+define i8 @scmp_ashr_slt_pattern(i8 %a) {
+; CHECK-LABEL: define i8 @scmp_ashr_slt_pattern(
+; CHECK-SAME: i8 [[A:%.*]]) {
+; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.scmp.i8.i8(i8 [[A]], i8 0)
+; CHECK-NEXT:    ret i8 [[R]]
+;
+  %a.lobit = ashr i8 %a, 7
+  %cmp = icmp slt i8 %a, 1
+  %retval = select i1 %cmp, i8 %a.lobit, i8 1
+  ret i8 %retval
+}
+
+define i8 @scmp_ashr_slt_pattern_neg(i8 %a) {
+; CHECK-LABEL: define i8 @scmp_ashr_slt_pattern_neg(
+; CHECK-SAME: i8 [[A:%.*]]) {
+; CHECK-NEXT:    [[A_LOBIT:%.*]] = ashr i8 [[A]], 4
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i8 [[A]], 1
+; CHECK-NEXT:    [[RETVAL:%.*]] = select i1 [[CMP]], i8 [[A_LOBIT]], i8 1
+; CHECK-NEXT:    ret i8 [[RETVAL]]
+;
+  %a.lobit = ashr i8 %a, 4
+  %cmp = icmp slt i8 %a, 1
+  %retval = select i1 %cmp, i8 %a.lobit, i8 1
+  ret i8 %retval
+}