summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/PowerPC
diff options
context:
space:
mode:
authorHal Finkel <hfinkel@anl.gov>2012-08-28 02:10:27 +0000
committerHal Finkel <hfinkel@anl.gov>2012-08-28 02:10:27 +0000
commit5ab378037f2fde6694ef926b26d3df7ea6b8334d (patch)
tree4371442d19d761286b37b66c6d8476c702cf7ce1 /llvm/test/CodeGen/PowerPC
parente39526a789754d8459eed63757cd6782dd2db834 (diff)
downloadbcm5719-llvm-5ab378037f2fde6694ef926b26d3df7ea6b8334d.tar.gz
bcm5719-llvm-5ab378037f2fde6694ef926b26d3df7ea6b8334d.zip
Eliminate redundant CR moves on PPC32.
The 32-bit ABI requires CR bit 6 to be set if the call has fp arguments and unset if it doesn't. The solution up to now was to insert a MachineNode to set/unset the CR bit, which produces a CR vreg. This vreg was then copied into CR bit 6. When the register allocator saw a bunch of these in the same function, it allocated the set/unset CR bit in some random CR register (1 extra instruction) and then emitted CR moves before every vararg function call, rather than just setting and unsetting CR bit 6 directly before every vararg function call. This patch instead inserts a PPCcrset/PPCcrunset instruction which are then matched by a dedicated instruction pattern. Patch by Tobias von Koch. llvm-svn: 162725
Diffstat (limited to 'llvm/test/CodeGen/PowerPC')
-rw-r--r--llvm/test/CodeGen/PowerPC/cr1eq-no-extra-moves.ll26
1 files changed, 26 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/PowerPC/cr1eq-no-extra-moves.ll b/llvm/test/CodeGen/PowerPC/cr1eq-no-extra-moves.ll
new file mode 100644
index 00000000000..afa1ea8e75a
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/cr1eq-no-extra-moves.ll
@@ -0,0 +1,26 @@
+; RUN: llc < %s | FileCheck %s
+target datalayout = "E-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v128:128:128-n32"
+target triple = "powerpc-unknown-linux"
+
+@.str = private unnamed_addr constant [3 x i8] c"%i\00", align 1
+
+define void @test(i32 %count) nounwind {
+entry:
+; CHECK: crxor 6, 6, 6
+ %call = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([3 x i8]* @.str, i32 0, i32 0), i32 1) nounwind
+ %cmp2 = icmp sgt i32 %count, 0
+ br i1 %cmp2, label %for.body, label %for.end
+
+for.body: ; preds = %entry, %for.body
+ %i.03 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
+; CHECK: crxor 6, 6, 6
+ %call1 = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([3 x i8]* @.str, i32 0, i32 0), i32 1) nounwind
+ %inc = add nsw i32 %i.03, 1
+ %exitcond = icmp eq i32 %inc, %count
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body, %entry
+ ret void
+}
+
+declare i32 @printf(i8* nocapture, ...) nounwind
OpenPOWER on IntegriCloud