From 75fa6e5a23a843a70f23f19af77500561d5db47c Mon Sep 17 00:00:00 2001 From: Tilmann Scheller Date: Mon, 2 Jun 2014 12:33:33 +0000 Subject: [PATCH] [AArch64] Add some more regression tests for store pre-index update folding in the load/store optimizer. Add tests for the following transform: add x8, x8, #16 ... str X, [x8] -> str X, [x8, #16]! with X being either w0, x0, s0, d0 or q0. llvm-svn: 210021 --- llvm/test/CodeGen/AArch64/ldst-opt.ll | 105 ++++++++++++++++++++++++++++++++++ 1 file changed, 105 insertions(+) diff --git a/llvm/test/CodeGen/AArch64/ldst-opt.ll b/llvm/test/CodeGen/AArch64/ldst-opt.ll index 83e2611..71af3c1 100644 --- a/llvm/test/CodeGen/AArch64/ldst-opt.ll +++ b/llvm/test/CodeGen/AArch64/ldst-opt.ll @@ -272,6 +272,111 @@ return: ; Check the following transform: ; +; add x8, x8, #16 +; ... +; str X, [x8] +; -> +; str X, [x8, #16]! +; +; with X being either w0, x0, s0, d0 or q0. + +define void @store-pre-indexed-word2(%pre.struct.i32** %this, i1 %cond, + %pre.struct.i32* %load2, + i32 %val) nounwind { +; CHECK-LABEL: store-pre-indexed-word2 +; CHECK: str w{{[0-9]+}}, [x{{[0-9]+}}, #4]! + br i1 %cond, label %if.then, label %if.end +if.then: + %load1 = load %pre.struct.i32** %this + %gep1 = getelementptr inbounds %pre.struct.i32* %load1, i64 0, i32 1 + br label %return +if.end: + %gep2 = getelementptr inbounds %pre.struct.i32* %load2, i64 0, i32 2 + br label %return +return: + %retptr = phi i32* [ %gep1, %if.then ], [ %gep2, %if.end ] + store i32 %val, i32* %retptr + ret void +} + +define void @store-pre-indexed-doubleword2(%pre.struct.i64** %this, i1 %cond, + %pre.struct.i64* %load2, + i64 %val) nounwind { +; CHECK-LABEL: store-pre-indexed-doubleword2 +; CHECK: str x{{[0-9]+}}, [x{{[0-9]+}}, #8]! + br i1 %cond, label %if.then, label %if.end +if.then: + %load1 = load %pre.struct.i64** %this + %gep1 = getelementptr inbounds %pre.struct.i64* %load1, i64 0, i32 1 + br label %return +if.end: + %gep2 = getelementptr inbounds %pre.struct.i64* %load2, i64 0, i32 2 + br label %return +return: + %retptr = phi i64* [ %gep1, %if.then ], [ %gep2, %if.end ] + store i64 %val, i64* %retptr + ret void +} + +define void @store-pre-indexed-quadword2(%pre.struct.i128** %this, i1 %cond, + %pre.struct.i128* %load2, + <2 x i64> %val) nounwind { +; CHECK-LABEL: store-pre-indexed-quadword2 +; CHECK: str q{{[0-9]+}}, [x{{[0-9]+}}, #16]! + br i1 %cond, label %if.then, label %if.end +if.then: + %load1 = load %pre.struct.i128** %this + %gep1 = getelementptr inbounds %pre.struct.i128* %load1, i64 0, i32 1 + br label %return +if.end: + %gep2 = getelementptr inbounds %pre.struct.i128* %load2, i64 0, i32 2 + br label %return +return: + %retptr = phi <2 x i64>* [ %gep1, %if.then ], [ %gep2, %if.end ] + store <2 x i64> %val, <2 x i64>* %retptr + ret void +} + +define void @store-pre-indexed-float2(%pre.struct.float** %this, i1 %cond, + %pre.struct.float* %load2, + float %val) nounwind { +; CHECK-LABEL: store-pre-indexed-float2 +; CHECK: str s{{[0-9]+}}, [x{{[0-9]+}}, #4]! + br i1 %cond, label %if.then, label %if.end +if.then: + %load1 = load %pre.struct.float** %this + %gep1 = getelementptr inbounds %pre.struct.float* %load1, i64 0, i32 1 + br label %return +if.end: + %gep2 = getelementptr inbounds %pre.struct.float* %load2, i64 0, i32 2 + br label %return +return: + %retptr = phi float* [ %gep1, %if.then ], [ %gep2, %if.end ] + store float %val, float* %retptr + ret void +} + +define void @store-pre-indexed-double2(%pre.struct.double** %this, i1 %cond, + %pre.struct.double* %load2, + double %val) nounwind { +; CHECK-LABEL: store-pre-indexed-double2 +; CHECK: str d{{[0-9]+}}, [x{{[0-9]+}}, #8]! + br i1 %cond, label %if.then, label %if.end +if.then: + %load1 = load %pre.struct.double** %this + %gep1 = getelementptr inbounds %pre.struct.double* %load1, i64 0, i32 1 + br label %return +if.end: + %gep2 = getelementptr inbounds %pre.struct.double* %load2, i64 0, i32 2 + br label %return +return: + %retptr = phi double* [ %gep1, %if.then ], [ %gep2, %if.end ] + store double %val, double* %retptr + ret void +} + +; Check the following transform: +; ; ldr X, [x20] ; ... ; add x20, x20, #32 -- 2.7.4