From: Zi Xuan Wu Date: Mon, 26 Aug 2019 05:06:30 +0000 (+0000) Subject: [NFC][Regalloc] Add testcases for D66576 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=1d098622eca0db46490e2ccd05ae2bf087fb7656;p=llvm [NFC][Regalloc] Add testcases for D66576 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369877 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/test/CodeGen/AArch64/csr-split.ll b/test/CodeGen/AArch64/csr-split.ll new file mode 100644 index 00000000000..1bee7f05ace --- /dev/null +++ b/test/CodeGen/AArch64/csr-split.ll @@ -0,0 +1,224 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc -verify-machineinstrs -mtriple=aarch64-unknown-linux < %s | FileCheck %s +; RUN: llc -verify-machineinstrs -mtriple=arm64-apple-ios < %s | FileCheck %s --check-prefix=CHECK-APPLE + +; Check CSR split can work properly for tests below. + +@a = common dso_local local_unnamed_addr global i32 0, align 4 + +define dso_local signext i32 @test1(i32* %b) local_unnamed_addr { +; CHECK-LABEL: test1: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill +; CHECK-NEXT: .cfi_def_cfa_offset 16 +; CHECK-NEXT: .cfi_offset w19, -8 +; CHECK-NEXT: .cfi_offset w30, -16 +; CHECK-NEXT: adrp x8, a +; CHECK-NEXT: ldrsw x8, [x8, :lo12:a] +; CHECK-NEXT: cmp x8, x0 +; CHECK-NEXT: b.eq .LBB0_2 +; CHECK-NEXT: // %bb.1: // %if.end +; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload +; CHECK-NEXT: ret +; CHECK-NEXT: .LBB0_2: // %if.then +; CHECK-NEXT: mov x19, x0 +; CHECK-NEXT: bl callVoid +; CHECK-NEXT: mov x0, x19 +; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload +; CHECK-NEXT: b callNonVoid +; +; CHECK-APPLE-LABEL: test1: +; CHECK-APPLE: ; %bb.0: ; %entry +; CHECK-APPLE-NEXT: stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill +; CHECK-APPLE-NEXT: stp x29, x30, [sp, #16] ; 16-byte Folded Spill +; CHECK-APPLE-NEXT: .cfi_def_cfa_offset 32 +; CHECK-APPLE-NEXT: .cfi_offset w30, -8 +; CHECK-APPLE-NEXT: .cfi_offset w29, -16 +; CHECK-APPLE-NEXT: .cfi_offset w19, -24 +; CHECK-APPLE-NEXT: .cfi_offset w20, -32 +; CHECK-APPLE-NEXT: Lloh0: +; CHECK-APPLE-NEXT: adrp x8, _a@PAGE +; CHECK-APPLE-NEXT: Lloh1: +; CHECK-APPLE-NEXT: ldrsw x8, [x8, _a@PAGEOFF] +; CHECK-APPLE-NEXT: cmp x8, x0 +; CHECK-APPLE-NEXT: b.eq LBB0_2 +; CHECK-APPLE-NEXT: ; %bb.1: ; %if.end +; CHECK-APPLE-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload +; CHECK-APPLE-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload +; CHECK-APPLE-NEXT: ret +; CHECK-APPLE-NEXT: LBB0_2: ; %if.then +; CHECK-APPLE-NEXT: mov x19, x0 +; CHECK-APPLE-NEXT: bl _callVoid +; CHECK-APPLE-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload +; CHECK-APPLE-NEXT: mov x0, x19 +; CHECK-APPLE-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload +; CHECK-APPLE-NEXT: b _callNonVoid +; CHECK-APPLE-NEXT: .loh AdrpLdr Lloh0, Lloh1 +entry: + %0 = load i32, i32* @a, align 4, !tbaa !2 + %conv = sext i32 %0 to i64 + %1 = inttoptr i64 %conv to i32* + %cmp = icmp eq i32* %1, %b + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + %call = tail call signext i32 bitcast (i32 (...)* @callVoid to i32 ()*)() + %call2 = tail call signext i32 @callNonVoid(i32* %b) + br label %if.end + +if.end: ; preds = %if.then, %entry + %retval.0 = phi i32 [ %call2, %if.then ], [ undef, %entry ] + ret i32 %retval.0 +} + +declare signext i32 @callVoid(...) local_unnamed_addr + +declare signext i32 @callNonVoid(i32*) local_unnamed_addr + +define dso_local signext i32 @test2(i32* %p1) local_unnamed_addr { +; CHECK-LABEL: test2: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: stp x30, x19, [sp, #-16]! // 16-byte Folded Spill +; CHECK-NEXT: .cfi_def_cfa_offset 16 +; CHECK-NEXT: .cfi_offset w19, -8 +; CHECK-NEXT: .cfi_offset w30, -16 +; CHECK-NEXT: cbz x0, .LBB1_2 +; CHECK-NEXT: // %bb.1: // %if.end +; CHECK-NEXT: adrp x8, a +; CHECK-NEXT: ldrsw x8, [x8, :lo12:a] +; CHECK-NEXT: mov x19, x0 +; CHECK-NEXT: cmp x8, x0 +; CHECK-NEXT: b.eq .LBB1_3 +; CHECK-NEXT: .LBB1_2: // %return +; CHECK-NEXT: mov w0, wzr +; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload +; CHECK-NEXT: ret +; CHECK-NEXT: .LBB1_3: // %if.then2 +; CHECK-NEXT: bl callVoid +; CHECK-NEXT: mov x0, x19 +; CHECK-NEXT: ldp x30, x19, [sp], #16 // 16-byte Folded Reload +; CHECK-NEXT: b callNonVoid +; +; CHECK-APPLE-LABEL: test2: +; CHECK-APPLE: ; %bb.0: ; %entry +; CHECK-APPLE-NEXT: stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill +; CHECK-APPLE-NEXT: stp x29, x30, [sp, #16] ; 16-byte Folded Spill +; CHECK-APPLE-NEXT: .cfi_def_cfa_offset 32 +; CHECK-APPLE-NEXT: .cfi_offset w30, -8 +; CHECK-APPLE-NEXT: .cfi_offset w29, -16 +; CHECK-APPLE-NEXT: .cfi_offset w19, -24 +; CHECK-APPLE-NEXT: .cfi_offset w20, -32 +; CHECK-APPLE-NEXT: cbz x0, LBB1_2 +; CHECK-APPLE-NEXT: ; %bb.1: ; %if.end +; CHECK-APPLE-NEXT: Lloh2: +; CHECK-APPLE-NEXT: adrp x8, _a@PAGE +; CHECK-APPLE-NEXT: Lloh3: +; CHECK-APPLE-NEXT: ldrsw x8, [x8, _a@PAGEOFF] +; CHECK-APPLE-NEXT: mov x19, x0 +; CHECK-APPLE-NEXT: cmp x8, x0 +; CHECK-APPLE-NEXT: b.eq LBB1_3 +; CHECK-APPLE-NEXT: LBB1_2: ; %return +; CHECK-APPLE-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload +; CHECK-APPLE-NEXT: mov w0, wzr +; CHECK-APPLE-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload +; CHECK-APPLE-NEXT: ret +; CHECK-APPLE-NEXT: LBB1_3: ; %if.then2 +; CHECK-APPLE-NEXT: bl _callVoid +; CHECK-APPLE-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload +; CHECK-APPLE-NEXT: mov x0, x19 +; CHECK-APPLE-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload +; CHECK-APPLE-NEXT: b _callNonVoid +; CHECK-APPLE-NEXT: .loh AdrpLdr Lloh2, Lloh3 +entry: + %tobool = icmp eq i32* %p1, null + br i1 %tobool, label %return, label %if.end + +if.end: ; preds = %entry + %0 = load i32, i32* @a, align 4, !tbaa !2 + %conv = sext i32 %0 to i64 + %1 = inttoptr i64 %conv to i32* + %cmp = icmp eq i32* %1, %p1 + br i1 %cmp, label %if.then2, label %return + +if.then2: ; preds = %if.end + %call = tail call signext i32 bitcast (i32 (...)* @callVoid to i32 ()*)() + %call3 = tail call signext i32 @callNonVoid(i32* nonnull %p1) + br label %return + +return: ; preds = %if.end, %entry, %if.then2 + %retval.0 = phi i32 [ %call3, %if.then2 ], [ 0, %entry ], [ 0, %if.end ] + ret i32 %retval.0 +} + + +define dso_local i8* @test3(i8** nocapture %p1, i8 zeroext %p2) local_unnamed_addr { +; CHECK-LABEL: test3: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill +; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill +; CHECK-NEXT: .cfi_def_cfa_offset 32 +; CHECK-NEXT: .cfi_offset w19, -8 +; CHECK-NEXT: .cfi_offset w20, -16 +; CHECK-NEXT: .cfi_offset w30, -32 +; CHECK-NEXT: ldr x19, [x0] +; CHECK-NEXT: cbz x19, .LBB2_2 +; CHECK-NEXT: // %bb.1: // %land.rhs +; CHECK-NEXT: mov x20, x0 +; CHECK-NEXT: mov x0, x19 +; CHECK-NEXT: bl bar +; CHECK-NEXT: str x0, [x20] +; CHECK-NEXT: .LBB2_2: // %land.end +; CHECK-NEXT: mov x0, x19 +; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload +; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload +; CHECK-NEXT: ret +; +; CHECK-APPLE-LABEL: test3: +; CHECK-APPLE: ; %bb.0: ; %entry +; CHECK-APPLE-NEXT: stp x20, x19, [sp, #-32]! ; 16-byte Folded Spill +; CHECK-APPLE-NEXT: stp x29, x30, [sp, #16] ; 16-byte Folded Spill +; CHECK-APPLE-NEXT: .cfi_def_cfa_offset 32 +; CHECK-APPLE-NEXT: .cfi_offset w30, -8 +; CHECK-APPLE-NEXT: .cfi_offset w29, -16 +; CHECK-APPLE-NEXT: .cfi_offset w19, -24 +; CHECK-APPLE-NEXT: .cfi_offset w20, -32 +; CHECK-APPLE-NEXT: ldr x19, [x0] +; CHECK-APPLE-NEXT: cbz x19, LBB2_2 +; CHECK-APPLE-NEXT: ; %bb.1: ; %land.rhs +; CHECK-APPLE-NEXT: mov x20, x0 +; CHECK-APPLE-NEXT: mov x0, x19 +; CHECK-APPLE-NEXT: bl _bar +; CHECK-APPLE-NEXT: str x0, [x20] +; CHECK-APPLE-NEXT: LBB2_2: ; %land.end +; CHECK-APPLE-NEXT: ldp x29, x30, [sp, #16] ; 16-byte Folded Reload +; CHECK-APPLE-NEXT: mov x0, x19 +; CHECK-APPLE-NEXT: ldp x20, x19, [sp], #32 ; 16-byte Folded Reload +; CHECK-APPLE-NEXT: ret +entry: + %0 = load i8*, i8** %p1, align 8, !tbaa !6 + %tobool = icmp eq i8* %0, null + br i1 %tobool, label %land.end, label %land.rhs + +land.rhs: ; preds = %entry + %call = tail call i8* @bar(i8* nonnull %0, i8 zeroext %p2) + store i8* %call, i8** %p1, align 8, !tbaa !6 + br label %land.end + +land.end: ; preds = %entry, %land.rhs + ret i8* %0 +} + +declare i8* @bar(i8*, i8 zeroext) local_unnamed_addr + + +!llvm.module.flags = !{!0} +!llvm.ident = !{!1} + +!0 = !{i32 1, !"wchar_size", i32 4} +!1 = !{!"clang version 10.0.0 (trunk 367381) (llvm/trunk 367388)"} +!2 = !{!3, !3, i64 0} +!3 = !{!"int", !4, i64 0} +!4 = !{!"omnipotent char", !5, i64 0} +!5 = !{!"Simple C/C++ TBAA"} +!6 = !{!7, !7, i64 0} +!7 = !{!"any pointer", !4, i64 0} diff --git a/test/CodeGen/ARM/csr-split.ll b/test/CodeGen/ARM/csr-split.ll new file mode 100644 index 00000000000..f9246cb6df2 --- /dev/null +++ b/test/CodeGen/ARM/csr-split.ll @@ -0,0 +1,137 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc -verify-machineinstrs -mtriple=arm-unknown-linux < %s | FileCheck %s + +; Check CSR split can work properly for tests below. + +@a = common dso_local local_unnamed_addr global i32 0, align 4 + +define dso_local signext i32 @test1(i32* %b) local_unnamed_addr { +; CHECK-LABEL: test1: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: push {r4, lr} +; CHECK-NEXT: mov r4, r0 +; CHECK-NEXT: ldr r0, .LCPI0_0 +; CHECK-NEXT: ldr r0, [r0] +; CHECK-NEXT: cmp r0, r4 +; CHECK-NEXT: popne {r4, lr} +; CHECK-NEXT: movne pc, lr +; CHECK-NEXT: bl callVoid +; CHECK-NEXT: mov r0, r4 +; CHECK-NEXT: pop {r4, lr} +; CHECK-NEXT: b callNonVoid +; CHECK-NEXT: .p2align 2 +; CHECK-NEXT: @ %bb.1: +; CHECK-NEXT: .LCPI0_0: +; CHECK-NEXT: .long a +entry: + %0 = load i32, i32* @a, align 4, !tbaa !2 + %conv = sext i32 %0 to i64 + %1 = inttoptr i64 %conv to i32* + %cmp = icmp eq i32* %1, %b + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + %call = tail call signext i32 bitcast (i32 (...)* @callVoid to i32 ()*)() + %call2 = tail call signext i32 @callNonVoid(i32* %b) + br label %if.end + +if.end: ; preds = %if.then, %entry + %retval.0 = phi i32 [ %call2, %if.then ], [ undef, %entry ] + ret i32 %retval.0 +} + +declare signext i32 @callVoid(...) local_unnamed_addr + +declare signext i32 @callNonVoid(i32*) local_unnamed_addr + +define dso_local signext i32 @test2(i32* %p1) local_unnamed_addr { +; CHECK-LABEL: test2: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: push {r4, lr} +; CHECK-NEXT: cmp r0, #0 +; CHECK-NEXT: beq .LBB1_2 +; CHECK-NEXT: @ %bb.1: @ %if.end +; CHECK-NEXT: mov r4, r0 +; CHECK-NEXT: ldr r0, .LCPI1_0 +; CHECK-NEXT: ldr r0, [r0] +; CHECK-NEXT: cmp r0, r4 +; CHECK-NEXT: beq .LBB1_3 +; CHECK-NEXT: .LBB1_2: @ %return +; CHECK-NEXT: mov r0, #0 +; CHECK-NEXT: pop {r4, lr} +; CHECK-NEXT: mov pc, lr +; CHECK-NEXT: .LBB1_3: @ %if.then2 +; CHECK-NEXT: bl callVoid +; CHECK-NEXT: mov r0, r4 +; CHECK-NEXT: pop {r4, lr} +; CHECK-NEXT: b callNonVoid +; CHECK-NEXT: .p2align 2 +; CHECK-NEXT: @ %bb.4: +; CHECK-NEXT: .LCPI1_0: +; CHECK-NEXT: .long a +entry: + %tobool = icmp eq i32* %p1, null + br i1 %tobool, label %return, label %if.end + +if.end: ; preds = %entry + %0 = load i32, i32* @a, align 4, !tbaa !2 + %conv = sext i32 %0 to i64 + %1 = inttoptr i64 %conv to i32* + %cmp = icmp eq i32* %1, %p1 + br i1 %cmp, label %if.then2, label %return + +if.then2: ; preds = %if.end + %call = tail call signext i32 bitcast (i32 (...)* @callVoid to i32 ()*)() + %call3 = tail call signext i32 @callNonVoid(i32* nonnull %p1) + br label %return + +return: ; preds = %if.end, %entry, %if.then2 + %retval.0 = phi i32 [ %call3, %if.then2 ], [ 0, %entry ], [ 0, %if.end ] + ret i32 %retval.0 +} + + +define dso_local i8* @test3(i8** nocapture %p1, i8 zeroext %p2) local_unnamed_addr { +; CHECK-LABEL: test3: +; CHECK: @ %bb.0: @ %entry +; CHECK-NEXT: push {r4, r5, r11, lr} +; CHECK-NEXT: ldr r4, [r0] +; CHECK-NEXT: cmp r4, #0 +; CHECK-NEXT: beq .LBB2_2 +; CHECK-NEXT: @ %bb.1: @ %land.rhs +; CHECK-NEXT: mov r5, r0 +; CHECK-NEXT: mov r0, r4 +; CHECK-NEXT: bl bar +; CHECK-NEXT: str r0, [r5] +; CHECK-NEXT: .LBB2_2: @ %land.end +; CHECK-NEXT: mov r0, r4 +; CHECK-NEXT: pop {r4, r5, r11, lr} +; CHECK-NEXT: mov pc, lr +entry: + %0 = load i8*, i8** %p1, align 8, !tbaa !6 + %tobool = icmp eq i8* %0, null + br i1 %tobool, label %land.end, label %land.rhs + +land.rhs: ; preds = %entry + %call = tail call i8* @bar(i8* nonnull %0, i8 zeroext %p2) + store i8* %call, i8** %p1, align 8, !tbaa !6 + br label %land.end + +land.end: ; preds = %entry, %land.rhs + ret i8* %0 +} + +declare i8* @bar(i8*, i8 zeroext) local_unnamed_addr + + +!llvm.module.flags = !{!0} +!llvm.ident = !{!1} + +!0 = !{i32 1, !"wchar_size", i32 4} +!1 = !{!"clang version 10.0.0 (trunk 367381) (llvm/trunk 367388)"} +!2 = !{!3, !3, i64 0} +!3 = !{!"int", !4, i64 0} +!4 = !{!"omnipotent char", !5, i64 0} +!5 = !{!"Simple C/C++ TBAA"} +!6 = !{!7, !7, i64 0} +!7 = !{!"any pointer", !4, i64 0} diff --git a/test/CodeGen/PowerPC/csr-split.ll b/test/CodeGen/PowerPC/csr-split.ll new file mode 100644 index 00000000000..4e7db535089 --- /dev/null +++ b/test/CodeGen/PowerPC/csr-split.ll @@ -0,0 +1,263 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc -verify-machineinstrs -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names \ +; RUN: -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr9 < %s | FileCheck %s --check-prefix=CHECK-PWR9 +; RUN: llc -verify-machineinstrs -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names \ +; RUN: -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 < %s | FileCheck %s + +; Check CSR split can work properly for tests below. + +@a = common dso_local local_unnamed_addr global i32 0, align 4 + +define dso_local signext i32 @test1(i32* %b) local_unnamed_addr { +; CHECK-PWR9-LABEL: test1: +; CHECK-PWR9: # %bb.0: # %entry +; CHECK-PWR9-NEXT: mflr r0 +; CHECK-PWR9-NEXT: .cfi_def_cfa_offset 48 +; CHECK-PWR9-NEXT: .cfi_offset lr, 16 +; CHECK-PWR9-NEXT: .cfi_offset r30, -16 +; CHECK-PWR9-NEXT: std r30, -16(r1) # 8-byte Folded Spill +; CHECK-PWR9-NEXT: std r0, 16(r1) +; CHECK-PWR9-NEXT: stdu r1, -48(r1) +; CHECK-PWR9-NEXT: mr r30, r3 +; CHECK-PWR9-NEXT: addis r3, r2, a@toc@ha +; CHECK-PWR9-NEXT: lwa r3, a@toc@l(r3) +; CHECK-PWR9-NEXT: cmpld r3, r30 +; CHECK-PWR9-NEXT: # implicit-def: $r3 +; CHECK-PWR9-NEXT: bne cr0, .LBB0_2 +; CHECK-PWR9-NEXT: # %bb.1: # %if.then +; CHECK-PWR9-NEXT: bl callVoid +; CHECK-PWR9-NEXT: nop +; CHECK-PWR9-NEXT: mr r3, r30 +; CHECK-PWR9-NEXT: bl callNonVoid +; CHECK-PWR9-NEXT: nop +; CHECK-PWR9-NEXT: .LBB0_2: # %if.end +; CHECK-PWR9-NEXT: extsw r3, r3 +; CHECK-PWR9-NEXT: addi r1, r1, 48 +; CHECK-PWR9-NEXT: ld r0, 16(r1) +; CHECK-PWR9-NEXT: mtlr r0 +; CHECK-PWR9-NEXT: ld r30, -16(r1) # 8-byte Folded Reload +; CHECK-PWR9-NEXT: blr +; +; CHECK-LABEL: test1: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: mflr r0 +; CHECK-NEXT: std r0, 16(r1) +; CHECK-NEXT: stdu r1, -128(r1) +; CHECK-NEXT: .cfi_def_cfa_offset 128 +; CHECK-NEXT: .cfi_offset lr, 16 +; CHECK-NEXT: .cfi_offset r30, -16 +; CHECK-NEXT: addis r4, r2, a@toc@ha +; CHECK-NEXT: std r30, 112(r1) # 8-byte Folded Spill +; CHECK-NEXT: mr r30, r3 +; CHECK-NEXT: lwa r4, a@toc@l(r4) +; CHECK-NEXT: cmpld r4, r3 +; CHECK-NEXT: # implicit-def: $r3 +; CHECK-NEXT: bne cr0, .LBB0_2 +; CHECK-NEXT: # %bb.1: # %if.then +; CHECK-NEXT: bl callVoid +; CHECK-NEXT: nop +; CHECK-NEXT: mr r3, r30 +; CHECK-NEXT: bl callNonVoid +; CHECK-NEXT: nop +; CHECK-NEXT: .LBB0_2: # %if.end +; CHECK-NEXT: ld r30, 112(r1) # 8-byte Folded Reload +; CHECK-NEXT: extsw r3, r3 +; CHECK-NEXT: addi r1, r1, 128 +; CHECK-NEXT: ld r0, 16(r1) +; CHECK-NEXT: mtlr r0 +; CHECK-NEXT: blr +entry: + %0 = load i32, i32* @a, align 4, !tbaa !2 + %conv = sext i32 %0 to i64 + %1 = inttoptr i64 %conv to i32* + %cmp = icmp eq i32* %1, %b + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + %call = tail call signext i32 bitcast (i32 (...)* @callVoid to i32 ()*)() + %call2 = tail call signext i32 @callNonVoid(i32* %b) + br label %if.end + +if.end: ; preds = %if.then, %entry + %retval.0 = phi i32 [ %call2, %if.then ], [ undef, %entry ] + ret i32 %retval.0 +} + +declare signext i32 @callVoid(...) local_unnamed_addr + +declare signext i32 @callNonVoid(i32*) local_unnamed_addr + +define dso_local signext i32 @test2(i32* %p1) local_unnamed_addr { +; CHECK-PWR9-LABEL: test2: +; CHECK-PWR9: # %bb.0: # %entry +; CHECK-PWR9-NEXT: mflr r0 +; CHECK-PWR9-NEXT: .cfi_def_cfa_offset 48 +; CHECK-PWR9-NEXT: .cfi_offset lr, 16 +; CHECK-PWR9-NEXT: .cfi_offset r30, -16 +; CHECK-PWR9-NEXT: std r30, -16(r1) # 8-byte Folded Spill +; CHECK-PWR9-NEXT: std r0, 16(r1) +; CHECK-PWR9-NEXT: stdu r1, -48(r1) +; CHECK-PWR9-NEXT: mr r30, r3 +; CHECK-PWR9-NEXT: li r3, 0 +; CHECK-PWR9-NEXT: cmpldi r30, 0 +; CHECK-PWR9-NEXT: beq cr0, .LBB1_3 +; CHECK-PWR9-NEXT: # %bb.1: # %if.end +; CHECK-PWR9-NEXT: addis r4, r2, a@toc@ha +; CHECK-PWR9-NEXT: lwa r4, a@toc@l(r4) +; CHECK-PWR9-NEXT: cmpld r4, r30 +; CHECK-PWR9-NEXT: bne cr0, .LBB1_3 +; CHECK-PWR9-NEXT: # %bb.2: # %if.then2 +; CHECK-PWR9-NEXT: bl callVoid +; CHECK-PWR9-NEXT: nop +; CHECK-PWR9-NEXT: mr r3, r30 +; CHECK-PWR9-NEXT: bl callNonVoid +; CHECK-PWR9-NEXT: nop +; CHECK-PWR9-NEXT: .LBB1_3: # %return +; CHECK-PWR9-NEXT: extsw r3, r3 +; CHECK-PWR9-NEXT: addi r1, r1, 48 +; CHECK-PWR9-NEXT: ld r0, 16(r1) +; CHECK-PWR9-NEXT: mtlr r0 +; CHECK-PWR9-NEXT: ld r30, -16(r1) # 8-byte Folded Reload +; CHECK-PWR9-NEXT: blr +; +; CHECK-LABEL: test2: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: mflr r0 +; CHECK-NEXT: std r0, 16(r1) +; CHECK-NEXT: stdu r1, -128(r1) +; CHECK-NEXT: .cfi_def_cfa_offset 128 +; CHECK-NEXT: .cfi_offset lr, 16 +; CHECK-NEXT: .cfi_offset r30, -16 +; CHECK-NEXT: std r30, 112(r1) # 8-byte Folded Spill +; CHECK-NEXT: mr r30, r3 +; CHECK-NEXT: cmpldi r3, 0 +; CHECK-NEXT: li r3, 0 +; CHECK-NEXT: beq cr0, .LBB1_3 +; CHECK-NEXT: # %bb.1: # %if.end +; CHECK-NEXT: addis r4, r2, a@toc@ha +; CHECK-NEXT: lwa r4, a@toc@l(r4) +; CHECK-NEXT: cmpld r4, r30 +; CHECK-NEXT: bne cr0, .LBB1_3 +; CHECK-NEXT: # %bb.2: # %if.then2 +; CHECK-NEXT: bl callVoid +; CHECK-NEXT: nop +; CHECK-NEXT: mr r3, r30 +; CHECK-NEXT: bl callNonVoid +; CHECK-NEXT: nop +; CHECK-NEXT: .LBB1_3: # %return +; CHECK-NEXT: ld r30, 112(r1) # 8-byte Folded Reload +; CHECK-NEXT: extsw r3, r3 +; CHECK-NEXT: addi r1, r1, 128 +; CHECK-NEXT: ld r0, 16(r1) +; CHECK-NEXT: mtlr r0 +; CHECK-NEXT: blr +entry: + %tobool = icmp eq i32* %p1, null + br i1 %tobool, label %return, label %if.end + +if.end: ; preds = %entry + %0 = load i32, i32* @a, align 4, !tbaa !2 + %conv = sext i32 %0 to i64 + %1 = inttoptr i64 %conv to i32* + %cmp = icmp eq i32* %1, %p1 + br i1 %cmp, label %if.then2, label %return + +if.then2: ; preds = %if.end + %call = tail call signext i32 bitcast (i32 (...)* @callVoid to i32 ()*)() + %call3 = tail call signext i32 @callNonVoid(i32* nonnull %p1) + br label %return + +return: ; preds = %if.end, %entry, %if.then2 + %retval.0 = phi i32 [ %call3, %if.then2 ], [ 0, %entry ], [ 0, %if.end ] + ret i32 %retval.0 +} + + +define dso_local i8* @test3(i8** nocapture %p1, i8 zeroext %p2) local_unnamed_addr { +; CHECK-PWR9-LABEL: test3: +; CHECK-PWR9: # %bb.0: # %entry +; CHECK-PWR9-NEXT: mflr r0 +; CHECK-PWR9-NEXT: .cfi_def_cfa_offset 64 +; CHECK-PWR9-NEXT: .cfi_offset lr, 16 +; CHECK-PWR9-NEXT: .cfi_offset r29, -24 +; CHECK-PWR9-NEXT: .cfi_offset r30, -16 +; CHECK-PWR9-NEXT: std r29, -24(r1) # 8-byte Folded Spill +; CHECK-PWR9-NEXT: std r30, -16(r1) # 8-byte Folded Spill +; CHECK-PWR9-NEXT: std r0, 16(r1) +; CHECK-PWR9-NEXT: stdu r1, -64(r1) +; CHECK-PWR9-NEXT: ld r30, 0(r3) +; CHECK-PWR9-NEXT: cmpldi r30, 0 +; CHECK-PWR9-NEXT: beq cr0, .LBB2_2 +; CHECK-PWR9-NEXT: # %bb.1: # %land.rhs +; CHECK-PWR9-NEXT: mr r29, r3 +; CHECK-PWR9-NEXT: clrldi r4, r4, 32 +; CHECK-PWR9-NEXT: mr r3, r30 +; CHECK-PWR9-NEXT: bl bar +; CHECK-PWR9-NEXT: nop +; CHECK-PWR9-NEXT: std r3, 0(r29) +; CHECK-PWR9-NEXT: .LBB2_2: # %land.end +; CHECK-PWR9-NEXT: mr r3, r30 +; CHECK-PWR9-NEXT: addi r1, r1, 64 +; CHECK-PWR9-NEXT: ld r0, 16(r1) +; CHECK-PWR9-NEXT: mtlr r0 +; CHECK-PWR9-NEXT: ld r30, -16(r1) # 8-byte Folded Reload +; CHECK-PWR9-NEXT: ld r29, -24(r1) # 8-byte Folded Reload +; CHECK-PWR9-NEXT: blr +; +; CHECK-LABEL: test3: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: mflr r0 +; CHECK-NEXT: std r0, 16(r1) +; CHECK-NEXT: stdu r1, -144(r1) +; CHECK-NEXT: .cfi_def_cfa_offset 144 +; CHECK-NEXT: .cfi_offset lr, 16 +; CHECK-NEXT: .cfi_offset r29, -24 +; CHECK-NEXT: .cfi_offset r30, -16 +; CHECK-NEXT: std r30, 128(r1) # 8-byte Folded Spill +; CHECK-NEXT: ld r30, 0(r3) +; CHECK-NEXT: std r29, 120(r1) # 8-byte Folded Spill +; CHECK-NEXT: cmpldi r30, 0 +; CHECK-NEXT: beq cr0, .LBB2_2 +; CHECK-NEXT: # %bb.1: # %land.rhs +; CHECK-NEXT: mr r29, r3 +; CHECK-NEXT: clrldi r4, r4, 32 +; CHECK-NEXT: mr r3, r30 +; CHECK-NEXT: bl bar +; CHECK-NEXT: nop +; CHECK-NEXT: std r3, 0(r29) +; CHECK-NEXT: .LBB2_2: # %land.end +; CHECK-NEXT: mr r3, r30 +; CHECK-NEXT: ld r30, 128(r1) # 8-byte Folded Reload +; CHECK-NEXT: ld r29, 120(r1) # 8-byte Folded Reload +; CHECK-NEXT: addi r1, r1, 144 +; CHECK-NEXT: ld r0, 16(r1) +; CHECK-NEXT: mtlr r0 +; CHECK-NEXT: blr +entry: + %0 = load i8*, i8** %p1, align 8, !tbaa !6 + %tobool = icmp eq i8* %0, null + br i1 %tobool, label %land.end, label %land.rhs + +land.rhs: ; preds = %entry + %call = tail call i8* @bar(i8* nonnull %0, i8 zeroext %p2) + store i8* %call, i8** %p1, align 8, !tbaa !6 + br label %land.end + +land.end: ; preds = %entry, %land.rhs + ret i8* %0 +} + +declare i8* @bar(i8*, i8 zeroext) local_unnamed_addr + + +!llvm.module.flags = !{!0} +!llvm.ident = !{!1} + +!0 = !{i32 1, !"wchar_size", i32 4} +!1 = !{!"clang version 10.0.0 (trunk 367381) (llvm/trunk 367388)"} +!2 = !{!3, !3, i64 0} +!3 = !{!"int", !4, i64 0} +!4 = !{!"omnipotent char", !5, i64 0} +!5 = !{!"Simple C/C++ TBAA"} +!6 = !{!7, !7, i64 0} +!7 = !{!"any pointer", !4, i64 0} diff --git a/test/CodeGen/X86/csr-split.ll b/test/CodeGen/X86/csr-split.ll new file mode 100644 index 00000000000..9bd480338aa --- /dev/null +++ b/test/CodeGen/X86/csr-split.ll @@ -0,0 +1,230 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc -verify-machineinstrs -mtriple=x86_64-unknown-linux < %s | FileCheck %s +; RUN: llc -verify-machineinstrs -mtriple=i386-unknown-linux < %s | FileCheck %s --check-prefix=CHECK-32BIT + +; Check CSR split can work properly for tests below. + +@a = common dso_local local_unnamed_addr global i32 0, align 4 + +define dso_local signext i32 @test1(i32* %b) local_unnamed_addr { +; CHECK-LABEL: test1: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: pushq %rbx +; CHECK-NEXT: .cfi_def_cfa_offset 16 +; CHECK-NEXT: .cfi_offset %rbx, -16 +; CHECK-NEXT: movslq {{.*}}(%rip), %rax +; CHECK-NEXT: cmpq %rdi, %rax +; CHECK-NEXT: je .LBB0_2 +; CHECK-NEXT: # %bb.1: # %if.end +; CHECK-NEXT: popq %rbx +; CHECK-NEXT: .cfi_def_cfa_offset 8 +; CHECK-NEXT: retq +; CHECK-NEXT: .LBB0_2: # %if.then +; CHECK-NEXT: .cfi_def_cfa_offset 16 +; CHECK-NEXT: movq %rdi, %rbx +; CHECK-NEXT: callq callVoid +; CHECK-NEXT: movq %rbx, %rdi +; CHECK-NEXT: popq %rbx +; CHECK-NEXT: .cfi_def_cfa_offset 8 +; CHECK-NEXT: jmp callNonVoid # TAILCALL +; +; CHECK-32BIT-LABEL: test1: +; CHECK-32BIT: # %bb.0: # %entry +; CHECK-32BIT-NEXT: subl $12, %esp +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 16 +; CHECK-32BIT-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-32BIT-NEXT: cmpl %eax, a +; CHECK-32BIT-NEXT: je .LBB0_2 +; CHECK-32BIT-NEXT: # %bb.1: # %if.end +; CHECK-32BIT-NEXT: addl $12, %esp +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 4 +; CHECK-32BIT-NEXT: retl +; CHECK-32BIT-NEXT: .LBB0_2: # %if.then +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 16 +; CHECK-32BIT-NEXT: calll callVoid +; CHECK-32BIT-NEXT: addl $12, %esp +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 4 +; CHECK-32BIT-NEXT: jmp callNonVoid # TAILCALL +entry: + %0 = load i32, i32* @a, align 4, !tbaa !2 + %conv = sext i32 %0 to i64 + %1 = inttoptr i64 %conv to i32* + %cmp = icmp eq i32* %1, %b + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + %call = tail call signext i32 bitcast (i32 (...)* @callVoid to i32 ()*)() + %call2 = tail call signext i32 @callNonVoid(i32* %b) + br label %if.end + +if.end: ; preds = %if.then, %entry + %retval.0 = phi i32 [ %call2, %if.then ], [ undef, %entry ] + ret i32 %retval.0 +} + +declare signext i32 @callVoid(...) local_unnamed_addr + +declare signext i32 @callNonVoid(i32*) local_unnamed_addr + +define dso_local signext i32 @test2(i32* %p1) local_unnamed_addr { +; CHECK-LABEL: test2: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: pushq %rbx +; CHECK-NEXT: .cfi_def_cfa_offset 16 +; CHECK-NEXT: .cfi_offset %rbx, -16 +; CHECK-NEXT: testq %rdi, %rdi +; CHECK-NEXT: je .LBB1_2 +; CHECK-NEXT: # %bb.1: # %if.end +; CHECK-NEXT: movq %rdi, %rbx +; CHECK-NEXT: movslq {{.*}}(%rip), %rax +; CHECK-NEXT: cmpq %rdi, %rax +; CHECK-NEXT: je .LBB1_3 +; CHECK-NEXT: .LBB1_2: # %return +; CHECK-NEXT: xorl %eax, %eax +; CHECK-NEXT: popq %rbx +; CHECK-NEXT: .cfi_def_cfa_offset 8 +; CHECK-NEXT: retq +; CHECK-NEXT: .LBB1_3: # %if.then2 +; CHECK-NEXT: .cfi_def_cfa_offset 16 +; CHECK-NEXT: callq callVoid +; CHECK-NEXT: movq %rbx, %rdi +; CHECK-NEXT: popq %rbx +; CHECK-NEXT: .cfi_def_cfa_offset 8 +; CHECK-NEXT: jmp callNonVoid # TAILCALL +; +; CHECK-32BIT-LABEL: test2: +; CHECK-32BIT: # %bb.0: # %entry +; CHECK-32BIT-NEXT: subl $12, %esp +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 16 +; CHECK-32BIT-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-32BIT-NEXT: testl %eax, %eax +; CHECK-32BIT-NEXT: je .LBB1_2 +; CHECK-32BIT-NEXT: # %bb.1: # %if.end +; CHECK-32BIT-NEXT: cmpl %eax, a +; CHECK-32BIT-NEXT: je .LBB1_3 +; CHECK-32BIT-NEXT: .LBB1_2: # %return +; CHECK-32BIT-NEXT: xorl %eax, %eax +; CHECK-32BIT-NEXT: addl $12, %esp +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 4 +; CHECK-32BIT-NEXT: retl +; CHECK-32BIT-NEXT: .LBB1_3: # %if.then2 +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 16 +; CHECK-32BIT-NEXT: calll callVoid +; CHECK-32BIT-NEXT: addl $12, %esp +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 4 +; CHECK-32BIT-NEXT: jmp callNonVoid # TAILCALL +entry: + %tobool = icmp eq i32* %p1, null + br i1 %tobool, label %return, label %if.end + +if.end: ; preds = %entry + %0 = load i32, i32* @a, align 4, !tbaa !2 + %conv = sext i32 %0 to i64 + %1 = inttoptr i64 %conv to i32* + %cmp = icmp eq i32* %1, %p1 + br i1 %cmp, label %if.then2, label %return + +if.then2: ; preds = %if.end + %call = tail call signext i32 bitcast (i32 (...)* @callVoid to i32 ()*)() + %call3 = tail call signext i32 @callNonVoid(i32* nonnull %p1) + br label %return + +return: ; preds = %if.end, %entry, %if.then2 + %retval.0 = phi i32 [ %call3, %if.then2 ], [ 0, %entry ], [ 0, %if.end ] + ret i32 %retval.0 +} + + +define dso_local i8* @test3(i8** nocapture %p1, i8 zeroext %p2) local_unnamed_addr { +; CHECK-LABEL: test3: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: pushq %r14 +; CHECK-NEXT: .cfi_def_cfa_offset 16 +; CHECK-NEXT: pushq %rbx +; CHECK-NEXT: .cfi_def_cfa_offset 24 +; CHECK-NEXT: pushq %rax +; CHECK-NEXT: .cfi_def_cfa_offset 32 +; CHECK-NEXT: .cfi_offset %rbx, -24 +; CHECK-NEXT: .cfi_offset %r14, -16 +; CHECK-NEXT: movq (%rdi), %rbx +; CHECK-NEXT: testq %rbx, %rbx +; CHECK-NEXT: je .LBB2_2 +; CHECK-NEXT: # %bb.1: # %land.rhs +; CHECK-NEXT: movq %rdi, %r14 +; CHECK-NEXT: movzbl %sil, %esi +; CHECK-NEXT: movq %rbx, %rdi +; CHECK-NEXT: callq bar +; CHECK-NEXT: movq %rax, (%r14) +; CHECK-NEXT: .LBB2_2: # %land.end +; CHECK-NEXT: movq %rbx, %rax +; CHECK-NEXT: addq $8, %rsp +; CHECK-NEXT: .cfi_def_cfa_offset 24 +; CHECK-NEXT: popq %rbx +; CHECK-NEXT: .cfi_def_cfa_offset 16 +; CHECK-NEXT: popq %r14 +; CHECK-NEXT: .cfi_def_cfa_offset 8 +; CHECK-NEXT: retq +; +; CHECK-32BIT-LABEL: test3: +; CHECK-32BIT: # %bb.0: # %entry +; CHECK-32BIT-NEXT: pushl %edi +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 8 +; CHECK-32BIT-NEXT: pushl %esi +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 12 +; CHECK-32BIT-NEXT: pushl %eax +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 16 +; CHECK-32BIT-NEXT: .cfi_offset %esi, -12 +; CHECK-32BIT-NEXT: .cfi_offset %edi, -8 +; CHECK-32BIT-NEXT: movl {{[0-9]+}}(%esp), %edi +; CHECK-32BIT-NEXT: movl (%edi), %esi +; CHECK-32BIT-NEXT: testl %esi, %esi +; CHECK-32BIT-NEXT: je .LBB2_2 +; CHECK-32BIT-NEXT: # %bb.1: # %land.rhs +; CHECK-32BIT-NEXT: subl $8, %esp +; CHECK-32BIT-NEXT: .cfi_adjust_cfa_offset 8 +; CHECK-32BIT-NEXT: movzbl {{[0-9]+}}(%esp), %eax +; CHECK-32BIT-NEXT: pushl %eax +; CHECK-32BIT-NEXT: .cfi_adjust_cfa_offset 4 +; CHECK-32BIT-NEXT: pushl %esi +; CHECK-32BIT-NEXT: .cfi_adjust_cfa_offset 4 +; CHECK-32BIT-NEXT: calll bar +; CHECK-32BIT-NEXT: addl $16, %esp +; CHECK-32BIT-NEXT: .cfi_adjust_cfa_offset -16 +; CHECK-32BIT-NEXT: movl %eax, (%edi) +; CHECK-32BIT-NEXT: .LBB2_2: # %land.end +; CHECK-32BIT-NEXT: movl %esi, %eax +; CHECK-32BIT-NEXT: addl $4, %esp +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 12 +; CHECK-32BIT-NEXT: popl %esi +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 8 +; CHECK-32BIT-NEXT: popl %edi +; CHECK-32BIT-NEXT: .cfi_def_cfa_offset 4 +; CHECK-32BIT-NEXT: retl +entry: + %0 = load i8*, i8** %p1, align 8, !tbaa !6 + %tobool = icmp eq i8* %0, null + br i1 %tobool, label %land.end, label %land.rhs + +land.rhs: ; preds = %entry + %call = tail call i8* @bar(i8* nonnull %0, i8 zeroext %p2) + store i8* %call, i8** %p1, align 8, !tbaa !6 + br label %land.end + +land.end: ; preds = %entry, %land.rhs + ret i8* %0 +} + +declare i8* @bar(i8*, i8 zeroext) local_unnamed_addr + + +!llvm.module.flags = !{!0} +!llvm.ident = !{!1} + +!0 = !{i32 1, !"wchar_size", i32 4} +!1 = !{!"clang version 10.0.0 (trunk 367381) (llvm/trunk 367388)"} +!2 = !{!3, !3, i64 0} +!3 = !{!"int", !4, i64 0} +!4 = !{!"omnipotent char", !5, i64 0} +!5 = !{!"Simple C/C++ TBAA"} +!6 = !{!7, !7, i64 0} +!7 = !{!"any pointer", !4, i64 0}