[X86] ISEL (and X, <constant mask>) to BZHI when BMI2 is available.

Generating BZHI in the variable mask case, i.e. (and X, (sub (shl 1, N), 1)),
was already supported, but we were missing the constant-mask case. This patch
fixes that.

<rdar://problem/15480077>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@206738 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 306fb7e199d5003654b8a8a3a71f4f9c0aa9c7a7..d867414a98d3166f448fcc4f2ad0aa1e4a453cf8 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -18503,6 +18503,20 @@ static SDValue PerformAndCombine(SDNode *N, SelectionDAG &DAG,
       }
     } // BEXTR
 
+    // Check for BZHI with contiguous mask: (and X, 0x0..0f..f)
+    // This should be checked after BEXTR - when X is a shift, a BEXTR is
+    // preferrable.
+    if (Subtarget->hasBMI2()) {
+      if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(N1)) {
+        uint64_t Mask = C->getZExtValue();
+        if (isMask_64(Mask)) {
+          unsigned LZ = CountTrailingOnes_64(Mask);
+          return DAG.getNode(X86ISD::BZHI, DL, VT, N0,
+                             DAG.getConstant(LZ, MVT::i8));
+        }
+      }
+    }
+
     return SDValue();
   }
 

diff --git a/test/CodeGen/X86/bmi.ll b/test/CodeGen/X86/bmi.ll
index 242075a878bbf1f136ce024cea427655d4cf28b0..1dc2edb7ea4eb4c7390e2e2d47b65cb4dd26dbff 100644 (file)
--- a/test/CodeGen/X86/bmi.ll
+++ b/test/CodeGen/X86/bmi.ll
@@ -216,6 +216,24 @@ entry:
 ; CHECK: bzhiq
 }
 
+define i32 @bzhi32_constant_mask(i32 %x) #0 {
+entry:
+  %and = and i32 %x, 1073741823
+  ret i32 %and
+; CHECK-LABEL: bzhi32_constant_mask:
+; CHECK: movb    $30, %al
+; CHECK: bzhil   %eax, %edi, %eax
+}
+
+define i64 @bzhi64_constant_mask(i64 %x) #0 {
+entry:
+  %and = and i64 %x, 4611686018427387903
+  ret i64 %and
+; CHECK-LABEL: bzhi64_constant_mask:
+; CHECK: movb    $62, %al
+; CHECK: bzhiq   %rax, %rdi, %rax
+}
+
 define i32 @blsi32(i32 %x) nounwind readnone {
   %tmp = sub i32 0, %x
   %tmp2 = and i32 %x, %tmp