summaryrefslogtreecommitdiff
path: root/test/CodeGen/X86/atom-pad-short-functions.ll
diff options
context:
space:
mode:
authorPreston Gurd <preston.gurd@intel.com>2013-01-08 18:27:24 +0000
committerPreston Gurd <preston.gurd@intel.com>2013-01-08 18:27:24 +0000
commitc7b902e7fe3498503efbfd98cabb1b1c67cadda6 (patch)
tree7b93b61349d55c8f4a07b0d4392c070c9816d9ab /test/CodeGen/X86/atom-pad-short-functions.ll
parent2a92c10dcb1672750d51412534a6136552f415b0 (diff)
downloadllvm-c7b902e7fe3498503efbfd98cabb1b1c67cadda6.tar.gz
llvm-c7b902e7fe3498503efbfd98cabb1b1c67cadda6.tar.bz2
llvm-c7b902e7fe3498503efbfd98cabb1b1c67cadda6.tar.xz
Pad Short Functions for Intel Atom
The current Intel Atom microarchitecture has a feature whereby when a function returns early then it is slightly faster to execute a sequence of NOP instructions to wait until the return address is ready, as opposed to simply stalling on the ret instruction until the return address is ready. When compiling for X86 Atom only, this patch will run a pass, called "X86PadShortFunction" which will add NOP instructions where less than four cycles elapse between function entry and return. It includes tests. This patch has been updated to address Nadav's review comments - Optimize only at >= O1 and don't do optimization if -Os is set - Stores MachineBasicBlock* instead of BBNum - Uses DenseMap instead of std::map - Fixes placement of braces Patch by Andy Zhang. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171879 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/X86/atom-pad-short-functions.ll')
-rw-r--r--test/CodeGen/X86/atom-pad-short-functions.ll78
1 files changed, 78 insertions, 0 deletions
diff --git a/test/CodeGen/X86/atom-pad-short-functions.ll b/test/CodeGen/X86/atom-pad-short-functions.ll
new file mode 100644
index 0000000000..54af17d4c4
--- /dev/null
+++ b/test/CodeGen/X86/atom-pad-short-functions.ll
@@ -0,0 +1,78 @@
+; RUN: llc < %s -O1 -mcpu=atom -mtriple=i686-linux | FileCheck %s
+
+declare void @external_function(...)
+
+define i32 @test_return_val(i32 %a) nounwind {
+; CHECK: test_return_val
+; CHECK: movl
+; CHECK: nop
+; CHECK: nop
+; CHECK: nop
+; CHECK: nop
+; CHECK: nop
+; CHECK: nop
+; CHECK: ret
+ ret i32 %a
+}
+
+define i32 @test_optsize(i32 %a) nounwind optsize {
+; CHECK: test_optsize
+; CHECK: movl
+; CHECK-NEXT: ret
+ ret i32 %a
+}
+
+define i32 @test_add(i32 %a, i32 %b) nounwind {
+; CHECK: test_add
+; CHECK: addl
+; CHECK: nop
+; CHECK: nop
+; CHECK: nop
+; CHECK: nop
+; CHECK: ret
+ %result = add i32 %a, %b
+ ret i32 %result
+}
+
+define i32 @test_multiple_ret(i32 %a, i32 %b, i1 %c) nounwind {
+; CHECK: @test_multiple_ret
+; CHECK: je
+
+; CHECK: nop
+; CHECK: nop
+; CHECK: ret
+
+; CHECK: nop
+; CHECK: nop
+; CHECK: ret
+
+ br i1 %c, label %bb1, label %bb2
+
+bb1:
+ ret i32 %a
+
+bb2:
+ ret i32 %b
+}
+
+define void @test_call_others(i32 %x) nounwind
+{
+; CHECK: test_call_others
+; CHECK: je
+ %tobool = icmp eq i32 %x, 0
+ br i1 %tobool, label %if.end, label %true.case
+
+; CHECK: jmp external_function
+true.case:
+ tail call void bitcast (void (...)* @external_function to void ()*)() nounwind
+ br label %if.end
+
+; CHECK: nop
+; CHECK: nop
+; CHECK: nop
+; CHECK: nop
+; CHECK: ret
+if.end:
+ ret void
+
+}