[InstCombine] Fold (ct{t,l}z Pow2) -> Log2(Pow2)

[goldsteinn]

• [InstCombine] Add tests for folding (ct{t,l}z Pow2); NFC
• [InstCombine] Fold (ct{t,l}z Pow2) -> Log2(Pow2)

Do so we can find Log2(Pow2) for "free" with takeLog2

https://alive2.llvm.org/ce/z/CL77fo

[llvmbot]

@llvm/pr-subscribers-llvm-transforms

Author: None (goldsteinn)

Changes

• [InstCombine] Add tests for folding (ct{t,l}z Pow2); NFC
• [InstCombine] Fold (ct{t,l}z Pow2) -> Log2(Pow2)

---

Full diff: https://github.com/llvm/llvm-project/pull/122620.diff

2 Files Affected:

• (modified) llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp (+16)
• (modified) llvm/test/Transforms/InstCombine/cttz.ll (+69)

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 7454382412369f..94240773f46a80 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -588,6 +588,22 @@ static Instruction *foldCttzCtlz(IntrinsicInst &II, InstCombinerImpl &IC) {
     }
   }
 
+  // cttz(Pow2) -> Log2(Pow2)
+  // ctlz(Pow2) -> BitWidth - 1 - Log2(Pow2)
+  if (IsTZ || II.hasOneUse()) {
+    if (auto *R = IC.tryGetLog2(Op0, match(Op1, m_One()))) {
+      if (IsTZ)
+        return IC.replaceInstUsesWith(II, R);
+      BinaryOperator *BO = BinaryOperator::CreateSub(
+          ConstantInt::get(R->getType(),
+                           R->getType()->getScalarSizeInBits() - 1),
+          R);
+      BO->setHasNoSignedWrap();
+      BO->setHasNoUnsignedWrap();
+      return BO;
+    }
+  }
+
   KnownBits Known = IC.computeKnownBits(Op0, 0, &II);
 
   // Create a mask for bits above (ctlz) or below (cttz) the first known one.
diff --git a/llvm/test/Transforms/InstCombine/cttz.ll b/llvm/test/Transforms/InstCombine/cttz.ll
index cb0bc59ae79958..5717e352c81e13 100644
--- a/llvm/test/Transforms/InstCombine/cttz.ll
+++ b/llvm/test/Transforms/InstCombine/cttz.ll
@@ -297,3 +297,72 @@ define i16 @cttz_assume(i16 %x) {
   %cttz = call i16 @llvm.cttz.i16(i16 %x, i1 false)
   ret i16 %cttz
 }
+
+
+declare void @use.i8(i8)
+define i8 @fold_ctz_log2(i8 %x) {
+; CHECK-LABEL: @fold_ctz_log2(
+; CHECK-NEXT:    [[R:%.*]] = call i8 @llvm.umin.i8(i8 [[X:%.*]], i8 5)
+; CHECK-NEXT:    ret i8 [[R]]
+;
+  %p2 = shl i8 1, %x
+  %v = call i8 @llvm.umin(i8 %p2, i8 32)
+  %r = call i8 @llvm.cttz(i8 %v, i1 false)
+  ret i8 %r
+}
+
+define i8 @fold_ctz_log2_maybe_z(i8 %x, i8 %y, i1 %c) {
+; CHECK-LABEL: @fold_ctz_log2_maybe_z(
+; CHECK-NEXT:    [[V:%.*]] = shl i8 2, [[V_V:%.*]]
+; CHECK-NEXT:    [[P2_2:%.*]] = shl i8 4, [[Y:%.*]]
+; CHECK-NEXT:    [[V1:%.*]] = select i1 [[C:%.*]], i8 [[V]], i8 [[P2_2]]
+; CHECK-NEXT:    [[R:%.*]] = call range(i8 1, 9) i8 @llvm.cttz.i8(i8 [[V1]], i1 false)
+; CHECK-NEXT:    ret i8 [[R]]
+;
+  %p2 = shl i8 2, %x
+  %p2_2 = shl i8 4, %y
+  %v = select i1 %c, i8 %p2, i8 %p2_2
+  %r = call i8 @llvm.cttz(i8 %v, i1 false)
+  ret i8 %r
+}
+
+define i8 @fold_ctz_log2_maybe_z_okay(i8 %x, i8 %y, i1 %c) {
+; CHECK-LABEL: @fold_ctz_log2_maybe_z_okay(
+; CHECK-NEXT:    [[X:%.*]] = add i8 [[X1:%.*]], 1
+; CHECK-NEXT:    [[Y:%.*]] = add i8 [[Y1:%.*]], 2
+; CHECK-NEXT:    [[V_V:%.*]] = select i1 [[C:%.*]], i8 [[X]], i8 [[Y]]
+; CHECK-NEXT:    ret i8 [[V_V]]
+;
+  %p2 = shl i8 2, %x
+  %p2_2 = shl i8 4, %y
+  %v = select i1 %c, i8 %p2, i8 %p2_2
+  %r = call i8 @llvm.cttz(i8 %v, i1 true)
+  ret i8 %r
+}
+
+define i8 @fold_clz_log2(i8 %x) {
+; CHECK-LABEL: @fold_clz_log2(
+; CHECK-NEXT:    [[TMP1:%.*]] = call i8 @llvm.umin.i8(i8 [[X:%.*]], i8 5)
+; CHECK-NEXT:    [[R:%.*]] = xor i8 [[TMP1]], 7
+; CHECK-NEXT:    ret i8 [[R]]
+;
+  %p2 = shl i8 1, %x
+  %v = call i8 @llvm.umin(i8 %p2, i8 32)
+  %r = call i8 @llvm.ctlz(i8 %v, i1 false)
+  ret i8 %r
+}
+
+define i8 @fold_clz_log2_fail_multi_use(i8 %x) {
+; CHECK-LABEL: @fold_clz_log2_fail_multi_use(
+; CHECK-NEXT:    [[P2:%.*]] = shl nuw i8 1, [[X:%.*]]
+; CHECK-NEXT:    [[V:%.*]] = call i8 @llvm.umin.i8(i8 [[P2]], i8 32)
+; CHECK-NEXT:    [[R:%.*]] = call range(i8 2, 9) i8 @llvm.ctlz.i8(i8 [[V]], i1 true)
+; CHECK-NEXT:    call void @use.i8(i8 [[R]])
+; CHECK-NEXT:    ret i8 [[R]]
+;
+  %p2 = shl i8 1, %x
+  %v = call i8 @llvm.umin(i8 %p2, i8 32)
+  %r = call i8 @llvm.ctlz(i8 %v, i1 false)
+  call void @use.i8(i8 %r)
+  ret i8 %r
+}

[dtcxzyw]

LGTM.

[nikic]

Why does the number of uses of the intrinsic matter?

[dtcxzyw]

Oops. I guess @goldsteinn means Op0->hasOneUse().

[nikic]

Add a test with non-pow2 bit width please.