AMDGPU: Add pass to detect used kernel features

[oota-llvm.git] / test / CodeGen / X86 / phys-reg-local-regalloc.ll

diff --git a/test/CodeGen/X86/phys-reg-local-regalloc.ll b/test/CodeGen/X86/phys-reg-local-regalloc.ll
index c565684685e5f68793cbc51ed6a49091364e6a5a..a0adba0f83382c510719117fe083dbc750438309 100644 (file)
--- a/test/CodeGen/X86/phys-reg-local-regalloc.ll
+++ b/test/CodeGen/X86/phys-reg-local-regalloc.ll
@@ -1,6 +1,7 @@
-; RUN: llc < %s -march=x86 -mtriple=i386-apple-darwin9 -regalloc=fast -optimize-regalloc=0 | FileCheck %s
-; RUN: llc -O0 < %s -march=x86 -mtriple=i386-apple-darwin9 -regalloc=fast | FileCheck %s
-; CHECKed instructions should be the same with or without -O0.
+; RUN: llc < %s -march=x86 -mtriple=i386-apple-darwin9 -mcpu=generic -regalloc=fast -optimize-regalloc=0 | FileCheck %s
+; RUN: llc -O0 < %s -march=x86 -mtriple=i386-apple-darwin9 -mcpu=generic -regalloc=fast | FileCheck %s
+; RUN: llc < %s -march=x86 -mtriple=i386-apple-darwin9 -mcpu=atom -regalloc=fast -optimize-regalloc=0 | FileCheck -check-prefix=ATOM %s
+; CHECKed instructions should be the same with or without -O0 except on Intel Atom due to instruction scheduling.
 
 @.str = private constant [12 x i8] c"x + y = %i\0A\00", align 1 ; <[12 x i8]*> [#uses=1]
 
@@ -15,6 +16,19 @@ entry:
 ; CHECK: movl  %ebx, 40(%esp)
 ; CHECK-NOT: movl
 ; CHECK: addl %ebx, %eax
+
+; On Intel Atom the scheduler moves a movl instruction
+; used for the printf call to follow movl 24(%esp), %eax
+; ATOM: movl 24(%esp), %eax
+; ATOM: movl
+; ATOM: movl   %eax, 36(%esp)
+; ATOM-NOT: movl
+; ATOM: movl 28(%esp), %ebx
+; ATOM-NOT: movl
+; ATOM: movl   %ebx, 40(%esp)
+; ATOM-NOT: movl
+; ATOM: addl %ebx, %eax
+
   %retval = alloca i32                            ; <i32*> [#uses=2]
   %"%ebx" = alloca i32                            ; <i32*> [#uses=1]
   %"%eax" = alloca i32                            ; <i32*> [#uses=2]
@@ -36,15 +50,15 @@ entry:
   store i32 %asmtmp2, i32* %"%eax"
   %3 = call i32 asm "", "={ax}"() nounwind        ; <i32> [#uses=1]
   call void asm sideeffect alignstack "movl $0, $1", "{eax},*m,~{dirflag},~{fpsr},~{flags},~{memory}"(i32 %3, i32* %result) nounwind
-  %4 = load i32* %result, align 4                 ; <i32> [#uses=1]
-  %5 = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([12 x i8]* @.str, i32 0, i32 0), i32 %4) nounwind ; <i32> [#uses=0]
+  %4 = load i32, i32* %result, align 4                 ; <i32> [#uses=1]
+  %5 = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 %4) nounwind ; <i32> [#uses=0]
   store i32 0, i32* %0, align 4
-  %6 = load i32* %0, align 4                      ; <i32> [#uses=1]
+  %6 = load i32, i32* %0, align 4                      ; <i32> [#uses=1]
   store i32 %6, i32* %retval, align 4
   br label %return
 
 return:                                           ; preds = %entry
-  %retval3 = load i32* %retval                    ; <i32> [#uses=1]
+  %retval3 = load i32, i32* %retval                    ; <i32> [#uses=1]
   ret i32 %retval3
 }