Make x86's BT instruction matching more thorough, and add some
dagcombines that help it match in several more cases. Add
several more cases to test/CodeGen/X86/bt.ll. This doesn't
yet include matching for BT with an immediate operand, it
just covers more register+register cases.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@63266 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/test/CodeGen/X86/bt.ll b/test/CodeGen/X86/bt.ll
index 86254d3..f91130d 100644
--- a/test/CodeGen/X86/bt.ll
+++ b/test/CodeGen/X86/bt.ll
@@ -1,4 +1,4 @@
-; RUN: llvm-as < %s | llc | grep btl
+; RUN: llvm-as < %s | llc -march=x86 | grep btl | count 28
; RUN: llvm-as < %s | llc -mcpu=pentium4 | grep btl | not grep esp
; RUN: llvm-as < %s | llc -mcpu=penryn | grep btl | not grep esp
; PR3253
@@ -7,8 +7,17 @@
; pentium4, however it is currently disabled due to the register+memory
; form having different semantics than the register+register form.
-target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
-target triple = "i386-apple-darwin8"
+; Test these patterns:
+; (X & (1 << N)) != 0 --> BT(X, N).
+; ((X >>u N) & 1) != 0 --> BT(X, N).
+; as well as several variations:
+; - The second form can use an arithmetic shift.
+; - Either form can use == instead of !=.
+; - Either form can compare with an operand of the &
+; instead of with 0.
+; - The comparison can be commuted (only cases where neither
+; operand is constant are included).
+; - The and can be commuted.
define void @test2(i32 %x, i32 %n) nounwind {
entry:
@@ -25,4 +34,409 @@
ret void
}
+define void @test2b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = lshr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 1, %tmp29
+ %tmp4 = icmp eq i32 %tmp3, 0 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @atest2(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = ashr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, 1 ; <i32> [#uses=1]
+ %tmp4 = icmp eq i32 %tmp3, 0 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @atest2b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = ashr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 1, %tmp29
+ %tmp4 = icmp eq i32 %tmp3, 0 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @test3(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, %x ; <i32> [#uses=1]
+ %tmp4 = icmp eq i32 %tmp3, 0 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @test3b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %x, %tmp29
+ %tmp4 = icmp eq i32 %tmp3, 0 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @testne2(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = lshr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, 1 ; <i32> [#uses=1]
+ %tmp4 = icmp ne i32 %tmp3, 0 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @testne2b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = lshr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 1, %tmp29
+ %tmp4 = icmp ne i32 %tmp3, 0 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @atestne2(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = ashr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, 1 ; <i32> [#uses=1]
+ %tmp4 = icmp ne i32 %tmp3, 0 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @atestne2b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = ashr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 1, %tmp29
+ %tmp4 = icmp ne i32 %tmp3, 0 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @testne3(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, %x ; <i32> [#uses=1]
+ %tmp4 = icmp ne i32 %tmp3, 0 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @testne3b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %x, %tmp29
+ %tmp4 = icmp ne i32 %tmp3, 0 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @query2(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = lshr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, 1 ; <i32> [#uses=1]
+ %tmp4 = icmp eq i32 %tmp3, 1 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @query2b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = lshr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 1, %tmp29
+ %tmp4 = icmp eq i32 %tmp3, 1 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @aquery2(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = ashr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, 1 ; <i32> [#uses=1]
+ %tmp4 = icmp eq i32 %tmp3, 1 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @aquery2b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = ashr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 1, %tmp29
+ %tmp4 = icmp eq i32 %tmp3, 1 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @query3(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, %x ; <i32> [#uses=1]
+ %tmp4 = icmp eq i32 %tmp3, %tmp29 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @query3b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %x, %tmp29
+ %tmp4 = icmp eq i32 %tmp3, %tmp29 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @query3x(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, %x ; <i32> [#uses=1]
+ %tmp4 = icmp eq i32 %tmp29, %tmp3 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @query3bx(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %x, %tmp29
+ %tmp4 = icmp eq i32 %tmp29, %tmp3 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @queryne2(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = lshr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, 1 ; <i32> [#uses=1]
+ %tmp4 = icmp ne i32 %tmp3, 1 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @queryne2b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = lshr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 1, %tmp29
+ %tmp4 = icmp ne i32 %tmp3, 1 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @aqueryne2(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = ashr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, 1 ; <i32> [#uses=1]
+ %tmp4 = icmp ne i32 %tmp3, 1 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @aqueryne2b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = ashr i32 %x, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 1, %tmp29
+ %tmp4 = icmp ne i32 %tmp3, 1 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @queryne3(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, %x ; <i32> [#uses=1]
+ %tmp4 = icmp ne i32 %tmp3, %tmp29 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @queryne3b(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %x, %tmp29
+ %tmp4 = icmp ne i32 %tmp3, %tmp29 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @queryne3x(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %tmp29, %x ; <i32> [#uses=1]
+ %tmp4 = icmp ne i32 %tmp29, %tmp3 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
+define void @queryne3bx(i32 %x, i32 %n) nounwind {
+entry:
+ %tmp29 = shl i32 1, %n ; <i32> [#uses=1]
+ %tmp3 = and i32 %x, %tmp29
+ %tmp4 = icmp ne i32 %tmp29, %tmp3 ; <i1> [#uses=1]
+ br i1 %tmp4, label %bb, label %UnifiedReturnBlock
+
+bb: ; preds = %entry
+ call void @foo()
+ ret void
+
+UnifiedReturnBlock: ; preds = %entry
+ ret void
+}
+
declare void @foo()
diff --git a/test/CodeGen/X86/commute-cmov.ll b/test/CodeGen/X86/commute-cmov.ll
index 24398dc..ac0e4ef 100644
--- a/test/CodeGen/X86/commute-cmov.ll
+++ b/test/CodeGen/X86/commute-cmov.ll
@@ -1,5 +1,20 @@
-; RUN: llvm-as < %s | llc -march=x86 | grep {cmove 16(%esp)}
+; RUN: llvm-as < %s | llc -march=x86 > %t
+; RUN: grep btl %t | count 2
+; RUN: grep cmov %t | count 2
+; RUN: not grep test %t
+; RUN: not grep set %t
+; RUN: not grep j %t
+; RUN: not grep cmovne %t
+; RUN: not grep cmove %t
+define i32 @foo(i32 %x, i32 %n, i32 %w, i32 %v) nounwind readnone {
+entry:
+ %0 = lshr i32 %x, %n ; <i32> [#uses=1]
+ %1 = and i32 %0, 1 ; <i32> [#uses=1]
+ %toBool = icmp eq i32 %1, 0 ; <i1> [#uses=1]
+ %.0 = select i1 %toBool, i32 %v, i32 12 ; <i32> [#uses=1]
+ ret i32 %.0
+}
define i32 @bar(i32 %x, i32 %n, i32 %w, i32 %v) nounwind readnone {
entry:
%0 = lshr i32 %x, %n ; <i32> [#uses=1]