From 99f823f94374917174f96a7689955b8463db6816 Mon Sep 17 00:00:00 2001 From: Hal Finkel Date: Fri, 8 Jun 2012 15:38:21 +0000 Subject: Add the PPCCTRLoops pass: a PPC machine-code-level optimization pass to form CTR-based loop branching code. This pass is derived from the Hexagon HardwareLoops pass. The only significant enhancement over the Hexagon pass is that PPCCTRLoops will also attempt to delete the replaced add and compare operations if they are no longer otherwise used. Also, invalid preheader DebugLoc is not used. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158204 91177308-0d34-0410-b5e6-96231b3b80d8 --- test/CodeGen/PowerPC/ctrloops.ll | 78 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) create mode 100644 test/CodeGen/PowerPC/ctrloops.ll (limited to 'test/CodeGen/PowerPC/ctrloops.ll') diff --git a/test/CodeGen/PowerPC/ctrloops.ll b/test/CodeGen/PowerPC/ctrloops.ll new file mode 100644 index 0000000000..f7bd354ce8 --- /dev/null +++ b/test/CodeGen/PowerPC/ctrloops.ll @@ -0,0 +1,78 @@ +target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v128:128:128-n32:64" +target triple = "powerpc64-unknown-freebsd10.0" +; RUN: llc < %s -march=ppc64 | FileCheck %s + +@a = common global i32 0, align 4 + +define void @test1(i32 %c) nounwind { +entry: + br label %for.body + +for.body: ; preds = %for.body, %entry + %i.01 = phi i32 [ 0, %entry ], [ %inc, %for.body ] + %0 = load volatile i32* @a, align 4, !tbaa !0 + %add = add nsw i32 %0, %c + store volatile i32 %add, i32* @a, align 4, !tbaa !0 + %inc = add nsw i32 %i.01, 1 + %exitcond = icmp eq i32 %inc, 2048 + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body + ret void +; CHECK: @test1 +; CHECK: mtctr +; CHECK-NOT: addi +; CHECK-NOT: cmplwi +; CHECK: bdnz +} + +define void @test2(i32 %c, i32 %d) nounwind { +entry: + %cmp1 = icmp sgt i32 %d, 0 + br i1 %cmp1, label %for.body, label %for.end + +for.body: ; preds = %entry, %for.body + %i.02 = phi i32 [ %inc, %for.body ], [ 0, %entry ] + %0 = load volatile i32* @a, align 4, !tbaa !0 + %add = add nsw i32 %0, %c + store volatile i32 %add, i32* @a, align 4, !tbaa !0 + %inc = add nsw i32 %i.02, 1 + %exitcond = icmp eq i32 %inc, %d + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +; CHECK: @test2 +; CHECK: mtctr +; CHECK-NOT: addi +; CHECK-NOT: cmplwi +; CHECK: bdnz +} + +define void @test3(i32 %c, i32 %d) nounwind { +entry: + %cmp1 = icmp sgt i32 %d, 0 + br i1 %cmp1, label %for.body, label %for.end + +for.body: ; preds = %entry, %for.body + %i.02 = phi i32 [ %inc, %for.body ], [ 0, %entry ] + %mul = mul nsw i32 %i.02, %c + %0 = load volatile i32* @a, align 4, !tbaa !0 + %add = add nsw i32 %0, %mul + store volatile i32 %add, i32* @a, align 4, !tbaa !0 + %inc = add nsw i32 %i.02, 1 + %exitcond = icmp eq i32 %inc, %d + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +; CHECK: @test3 +; CHECK: mtctr +; CHECK-NOT: addi +; CHECK-NOT: cmplwi +; CHECK: bdnz +} + +!0 = metadata !{metadata !"int", metadata !1} +!1 = metadata !{metadata !"omnipotent char", metadata !2} +!2 = metadata !{metadata !"Simple C/C++ TBAA"} -- cgit v1.2.3