AMDGPU: Add pass to detect used kernel features

[oota-llvm.git] / test / CodeGen / X86 / or-branch.ll

diff --git a/test/CodeGen/X86/or-branch.ll b/test/CodeGen/X86/or-branch.ll
index 5ad7fa14b358c18c4d8004b42990da68339595f7..4899a0fc7e88490bcb3186016e8ad992a402032f 100644 (file)
--- a/test/CodeGen/X86/or-branch.ll
+++ b/test/CodeGen/X86/or-branch.ll
@@ -1,19 +1,54 @@
-; RUN: llvm-as < %s | llc -march=x86 | not grep set
+; RUN: llc < %s -mtriple=i386-unknown-unknown -jump-is-expensive=0 | FileCheck %s --check-prefix=JUMP2 --check-prefix=CHECK
+; RUN: llc < %s -mtriple=i386-unknown-unknown -jump-is-expensive=1 | FileCheck %s --check-prefix=JUMP1 --check-prefix=CHECK
 
-void %foo(int %X, int %Y, int %Z) {
+define void @foo(i32 %X, i32 %Y, i32 %Z) nounwind {
+; JUMP2-LABEL: foo:
+; JUMP2-DAG:     jl
+; JUMP2-DAG:     je
+;
+; JUMP1-LABEL: foo:
+; JUMP1-DAG:     sete
+; JUMP1-DAG:     setl
+; JUMP1:         orb
+; JUMP1:         jne
 entry:
-       %tmp = tail call int (...)* %bar( )             ; <int> [#uses=0]
-       %tmp = seteq int %X, 0          ; <bool> [#uses=1]
-       %tmp3 = setlt int %Y, 5         ; <bool> [#uses=1]
-       %tmp4 = or bool %tmp3, %tmp             ; <bool> [#uses=1]
-       br bool %tmp4, label %cond_true, label %UnifiedReturnBlock
-
-cond_true:             ; preds = %entry
-       %tmp5 = tail call int (...)* %bar( )            ; <int> [#uses=0]
-       ret void
-
-UnifiedReturnBlock:            ; preds = %entry
-       ret void
+  %tmp1 = icmp eq i32 %X, 0
+  %tmp3 = icmp slt i32 %Y, 5
+  %tmp4 = or i1 %tmp3, %tmp1
+  br i1 %tmp4, label %cond_true, label %UnifiedReturnBlock
+
+cond_true:
+  %tmp5 = tail call i32 (...) @bar( )
+  ret void
+
+UnifiedReturnBlock:
+  ret void
+}
+
+; If the branch is unpredictable, don't add another branch
+; regardless of whether they are expensive or not.
+
+define void @unpredictable(i32 %X, i32 %Y, i32 %Z) nounwind {
+; CHECK-LABEL: unpredictable:
+; CHECK-DAG:     sete
+; CHECK-DAG:     setl
+; CHECK:         orb
+; CHECK:         jne
+entry:
+  %tmp1 = icmp eq i32 %X, 0
+  %tmp3 = icmp slt i32 %Y, 5
+  %tmp4 = or i1 %tmp3, %tmp1
+  br i1 %tmp4, label %cond_true, label %UnifiedReturnBlock, !unpredictable !0
+
+cond_true:
+  %tmp5 = tail call i32 (...) @bar( )
+  ret void
+
+UnifiedReturnBlock:
+  ret void
 }
 
-declare int %bar(...)
+declare i32 @bar(...)
+
+!0 = !{}
+