[CodeGenPrepare] Teach when it is profitable to speculate calls to @llvm.cttz/ctlz.

If the control flow is modelling an if-statement where the only instruction in
the 'then' basic block (excluding the terminator) is a call to cttz/ctlz,
CodeGenPrepare can try to speculate the cttz/ctlz call and simplify the control
flow graph.

Example:
\code
entry:
  %cmp = icmp eq i64 %val, 0
  br i1 %cmp, label %end.bb, label %then.bb

then.bb:
  %c = tail call i64 @llvm.cttz.i64(i64 %val, i1 true)
  br label %end.bb

end.bb:
  %cond = phi i64 [ %c, %then.bb ], [ 64, %entry]
\code

In this example, basic block %then.bb is taken if value %val is not zero.
Also, the phi node in %end.bb would propagate the size-of in bits of %val
only if %val is equal to zero.

With this patch, CodeGenPrepare will try to hoist the call to cttz from %then.bb
into basic block %entry only if cttz is cheap to speculate for the target.

Added two new hooks in TargetLowering.h to let targets customize the behavior
(i.e. decide whether it is cheap or not to speculate calls to cttz/ctlz). The
two new methods are 'isCheapToSpeculateCtlz' and 'isCheapToSpeculateCttz'.
By default, both methods return 'false'.
On X86, method 'isCheapToSpeculateCtlz' returns true only if the target has
LZCNT. Method 'isCheapToSpeculateCttz' only returns true if the target has BMI.

Differential Revision: http://reviews.llvm.org/D6728

llvm-svn: 224899

1 files changed, 250 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/cttz-ctlz.ll b/llvm/test/CodeGen/X86/cttz-ctlz.ll
new file mode 100644
index 00000000000..88dcf650a21
--- /dev/null
+++ b/llvm/test/CodeGen/X86/cttz-ctlz.ll
@@ -0,0 +1,250 @@
+; RUN: opt -S -codegenprepare -mtriple=x86_64-unknown-unknown -mattr=+bmi < %s | FileCheck %s --check-prefix=ALL --check-prefix=BMI
+; RUN: opt -S -codegenprepare -mtriple=x86_64-unknown-unknown -mattr=+lzcnt < %s | FileCheck %s --check-prefix=ALL --check-prefix=LZCNT
+; RUN: opt -S -codegenprepare -mtriple=x86_64-unknown-unknown < %s | FileCheck %s --check-prefix=ALL --check-prefix=GENERIC
+
+
+define i64 @test1(i64 %A) {
+; ALL-LABEL: @test1(
+; LZCNT: [[CTLZ:%[A-Za-z0-9]+]] = call i64 @llvm.ctlz.i64(i64 %A, i1 false)
+; LZCNT-NEXT: ret i64 [[CTLZ]]
+; BMI: icmp eq i64 %A, 0
+; BMI: call i64 @llvm.ctlz.i64(i64 %A, i1 true)
+; GENERIC: icmp eq i64 %A, 0
+; GENERIC: call i64 @llvm.ctlz.i64(i64 %A, i1 true)
+entry:
+  %tobool = icmp eq i64 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i64 @llvm.ctlz.i64(i64 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i64 [ %0, %cond.true ], [ 64, %entry ]
+  ret i64 %cond
+}
+
+
+define i32 @test2(i32 %A) {
+; ALL-LABEL: @test2(
+; LZCNT: [[CTLZ:%[A-Za-z0-9]+]] = call i32 @llvm.ctlz.i32(i32 %A, i1 false)
+; LZCNT-NEXT: ret i32 [[CTLZ]]
+; BMI: icmp eq i32 %A, 0
+; BMI: call i32 @llvm.ctlz.i32(i32 %A, i1 true)
+; GENERIC: icmp eq i32 %A, 0
+; GENERIC: call i32 @llvm.ctlz.i32(i32 %A, i1 true)
+entry:
+  %tobool = icmp eq i32 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i32 @llvm.ctlz.i32(i32 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i32 [ %0, %cond.true ], [ 32, %entry ]
+  ret i32 %cond
+}
+
+
+define signext i16 @test3(i16 signext %A) {
+; ALL-LABEL: @test3(
+; LZCNT: [[CTLZ:%[A-Za-z0-9]+]] = call i16 @llvm.ctlz.i16(i16 %A, i1 false)
+; LZCNT-NEXT: ret i16 [[CTLZ]]
+; BMI: icmp eq i16 %A, 0
+; BMI: call i16 @llvm.ctlz.i16(i16 %A, i1 true)
+; GENERIC: icmp eq i16 %A, 0
+; GENERIC: call i16 @llvm.ctlz.i16(i16 %A, i1 true)
+entry:
+  %tobool = icmp eq i16 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i16 @llvm.ctlz.i16(i16 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i16 [ %0, %cond.true ], [ 16, %entry ]
+  ret i16 %cond
+}
+
+
+define i64 @test1b(i64 %A) {
+; ALL-LABEL: @test1b(
+; LZCNT: icmp eq i64 %A, 0
+; LZCNT: call i64 @llvm.cttz.i64(i64 %A, i1 true)
+; BMI: [[CTTZ:%[A-Za-z0-9]+]] = call i64 @llvm.cttz.i64(i64 %A, i1 false)
+; BMI-NEXT: ret i64 [[CTTZ]]
+; GENERIC: icmp eq i64 %A, 0
+; GENERIC: call i64 @llvm.cttz.i64(i64 %A, i1 true)
+entry:
+  %tobool = icmp eq i64 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i64 @llvm.cttz.i64(i64 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i64 [ %0, %cond.true ], [ 64, %entry ]
+  ret i64 %cond
+}
+
+
+define i32 @test2b(i32 %A) {
+; ALL-LABEL: @test2b(
+; LZCNT: icmp eq i32 %A, 0
+; LZCNT: call i32 @llvm.cttz.i32(i32 %A, i1 true)
+; BMI: [[CTTZ:%[A-Za-z0-9]+]] = call i32 @llvm.cttz.i32(i32 %A, i1 false)
+; BMI-NEXT: ret i32 [[CTTZ]]
+; GENERIC: icmp eq i32 %A, 0
+; GENERIC: call i32 @llvm.cttz.i32(i32 %A, i1 true)
+entry:
+  %tobool = icmp eq i32 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i32 @llvm.cttz.i32(i32 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i32 [ %0, %cond.true ], [ 32, %entry ]
+  ret i32 %cond
+}
+
+
+define signext i16 @test3b(i16 signext %A) {
+; ALL-LABEL: @test3b(
+; LZCNT: icmp eq i16 %A, 0
+; LZCNT: call i16 @llvm.cttz.i16(i16 %A, i1 true)
+; BMI: [[CTTZ:%[A-Za-z0-9]+]] = call i16 @llvm.cttz.i16(i16 %A, i1 false)
+; BMI-NEXT: ret i16 [[CTTZ]]
+; GENERIC: icmp eq i16 %A, 0
+; GENERIC: call i16 @llvm.cttz.i16(i16 %A, i1 true)
+entry:
+  %tobool = icmp eq i16 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i16 @llvm.cttz.i16(i16 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i16 [ %0, %cond.true ], [ 16, %entry ]
+  ret i16 %cond
+}
+
+
+define i64 @test1c(i64 %A) {
+; ALL-LABEL: @test1c(
+; ALL: icmp eq i64 %A, 0
+; ALL: call i64 @llvm.ctlz.i64(i64 %A, i1 true)
+entry:
+  %tobool = icmp eq i64 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i64 @llvm.ctlz.i64(i64 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i64 [ %0, %cond.true ], [ 63, %entry ]
+  ret i64 %cond
+}
+
+define i32 @test2c(i32 %A) {
+; ALL-LABEL: @test2c(
+; ALL: icmp eq i32 %A, 0
+; ALL: call i32 @llvm.ctlz.i32(i32 %A, i1 true)
+entry:
+  %tobool = icmp eq i32 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i32 @llvm.ctlz.i32(i32 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i32 [ %0, %cond.true ], [ 31, %entry ]
+  ret i32 %cond
+}
+
+
+define signext i16 @test3c(i16 signext %A) {
+; ALL-LABEL: @test3c(
+; ALL: icmp eq i16 %A, 0
+; ALL: call i16 @llvm.ctlz.i16(i16 %A, i1 true)
+entry:
+  %tobool = icmp eq i16 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i16 @llvm.ctlz.i16(i16 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i16 [ %0, %cond.true ], [ 15, %entry ]
+  ret i16 %cond
+}
+
+
+define i64 @test1d(i64 %A) {
+; ALL-LABEL: @test1d(
+; ALL: icmp eq i64 %A, 0
+; ALL: call i64 @llvm.cttz.i64(i64 %A, i1 true)
+entry:
+  %tobool = icmp eq i64 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i64 @llvm.cttz.i64(i64 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i64 [ %0, %cond.true ], [ 63, %entry ]
+  ret i64 %cond
+}
+
+
+define i32 @test2d(i32 %A) {
+; ALL-LABEL: @test2d(
+; ALL: icmp eq i32 %A, 0
+; ALL: call i32 @llvm.cttz.i32(i32 %A, i1 true)
+entry:
+  %tobool = icmp eq i32 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i32 @llvm.cttz.i32(i32 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i32 [ %0, %cond.true ], [ 31, %entry ]
+  ret i32 %cond
+}
+
+
+define signext i16 @test3d(i16 signext %A) {
+; ALL-LABEL: @test3d(
+; ALL: icmp eq i16 %A, 0
+; ALL: call i16 @llvm.cttz.i16(i16 %A, i1 true)
+entry:
+  %tobool = icmp eq i16 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i16 @llvm.cttz.i16(i16 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i16 [ %0, %cond.true ], [ 15, %entry ]
+  ret i16 %cond
+}
+
+
+declare i64 @llvm.ctlz.i64(i64, i1)
+declare i32 @llvm.ctlz.i32(i32, i1)
+declare i16 @llvm.ctlz.i16(i16, i1)
+declare i64 @llvm.cttz.i64(i64, i1)
+declare i32 @llvm.cttz.i32(i32, i1)
+declare i16 @llvm.cttz.i16(i16, i1)