[llvm] 4df3b60 - Add pre-commit tests for [D102215](https://reviews.llvm.org/D102215).
Michael Liao via llvm-commits
llvm-commits at lists.llvm.org
Tue May 25 11:43:01 PDT 2021
Author: Michael Liao
Date: 2021-05-25T14:42:25-04:00
New Revision: 4df3b60199ef80dfbd84c8cee8c8afd511443330
URL: https://github.com/llvm/llvm-project/commit/4df3b60199ef80dfbd84c8cee8c8afd511443330
DIFF: https://github.com/llvm/llvm-project/commit/4df3b60199ef80dfbd84c8cee8c8afd511443330.diff
LOG: Add pre-commit tests for [D102215](https://reviews.llvm.org/D102215).
Added:
llvm/test/CodeGen/AArch64/memcpy-scoped-aa.ll
llvm/test/CodeGen/AMDGPU/memcpy-scoped-aa.ll
llvm/test/CodeGen/X86/memcpy-scoped-aa.ll
Modified:
Removed:
################################################################################
diff --git a/llvm/test/CodeGen/AArch64/memcpy-scoped-aa.ll b/llvm/test/CodeGen/AArch64/memcpy-scoped-aa.ll
new file mode 100644
index 0000000000000..f684391a46a2e
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/memcpy-scoped-aa.ll
@@ -0,0 +1,125 @@
+; RUN: llc -mtriple=aarch64-linux-gnu -o - %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -stop-after=finalize-isel -o - %s | FileCheck --check-prefix=MIR %s
+
+; MIR-DAG: ![[DOMAIN:[0-9]+]] = distinct !{!{{[0-9]+}}, !"bax"}
+; MIR-DAG: ![[SCOPE0:[0-9]+]] = distinct !{!{{[0-9]+}}, ![[DOMAIN]], !"bax: %p"}
+; MIR-DAG: ![[SCOPE1:[0-9]+]] = distinct !{!{{[0-9]+}}, ![[DOMAIN]], !"bax: %q"}
+; MIR-DAG: ![[SET0:[0-9]+]] = !{![[SCOPE0]]}
+; MIR-DAG: ![[SET1:[0-9]+]] = !{![[SCOPE1]]}
+
+; MIR-LABEL: name: test_memcpy
+; MIR: %2:fpr128 = LDRQui %0, 1 :: (load 16 from %ir.p1, align 4)
+; MIR-NEXT: STRQui killed %2, %0, 0 :: (store 16 into %ir.p0, align 4)
+define i32 @test_memcpy(i32* nocapture %p, i32* nocapture readonly %q) {
+; CHECK-LABEL: test_memcpy:
+; CHECK: ldr [[PVAL:q[0-9]+]], [x0, #16]
+; CHECK: str [[PVAL]], [x0]
+; CHECK: ldp [[Q0:w[0-9]+]], [[Q1:w[0-9]+]], [x1]
+; CHECK: add w0, [[Q0]], [[Q1]]
+; CHECK: ret
+ %p0 = bitcast i32* %p to i8*
+ %add.ptr = getelementptr inbounds i32, i32* %p, i64 4
+ %p1 = bitcast i32* %add.ptr to i8*
+ tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* noundef nonnull align 4 dereferenceable(16) %p0, i8* noundef nonnull align 4 dereferenceable(16) %p1, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32* %q, i64 1
+ %v1 = load i32, i32* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+; MIR-LABEL: name: test_memcpy_inline
+; MIR: %2:fpr128 = LDRQui %0, 1 :: (load 16 from %ir.p1, align 4)
+; MIR-NEXT: STRQui killed %2, %0, 0 :: (store 16 into %ir.p0, align 4)
+define i32 @test_memcpy_inline(i32* nocapture %p, i32* nocapture readonly %q) {
+; CHECK-LABEL: test_memcpy_inline:
+; CHECK: ldr [[PVAL:q[0-9]+]], [x0, #16]
+; CHECK: str [[PVAL]], [x0]
+; CHECK: ldp [[Q0:w[0-9]+]], [[Q1:w[0-9]+]], [x1]
+; CHECK: add w0, [[Q0]], [[Q1]]
+; CHECK: ret
+ %p0 = bitcast i32* %p to i8*
+ %add.ptr = getelementptr inbounds i32, i32* %p, i64 4
+ %p1 = bitcast i32* %add.ptr to i8*
+ tail call void @llvm.memcpy.inline.p0i8.p0i8.i64(i8* noundef nonnull align 4 dereferenceable(16) %p0, i8* noundef nonnull align 4 dereferenceable(16) %p1, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32* %q, i64 1
+ %v1 = load i32, i32* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+; MIR-LABEL: name: test_memmove
+; MIR: %2:fpr128 = LDRQui %0, 1 :: (load 16 from %ir.p1, align 4)
+; MIR-NEXT: STRQui killed %2, %0, 0 :: (store 16 into %ir.p0, align 4)
+define i32 @test_memmove(i32* nocapture %p, i32* nocapture readonly %q) {
+; CHECK-LABEL: test_memmove:
+; CHECK: ldr [[PVAL:q[0-9]+]], [x0, #16]
+; CHECK: str [[PVAL]], [x0]
+; CHECK: ldp [[Q0:w[0-9]+]], [[Q1:w[0-9]+]], [x1]
+; CHECK: add w0, [[Q0]], [[Q1]]
+; CHECK: ret
+ %p0 = bitcast i32* %p to i8*
+ %add.ptr = getelementptr inbounds i32, i32* %p, i64 4
+ %p1 = bitcast i32* %add.ptr to i8*
+ tail call void @llvm.memmove.p0i8.p0i8.i64(i8* noundef nonnull align 4 dereferenceable(16) %p0, i8* noundef nonnull align 4 dereferenceable(16) %p1, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32* %q, i64 1
+ %v1 = load i32, i32* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+; MIR-LABEL: name: test_memset
+; MIR: %2:gpr64 = MOVi64imm -6148914691236517206
+; MIR-NEXT: STRXui %2, %0, 1 :: (store 8 into %ir.p0 + 8, align 4)
+; MIR-NEXT: STRXui %2, %0, 0 :: (store 8 into %ir.p0, align 4)
+define i32 @test_memset(i32* nocapture %p, i32* nocapture readonly %q) {
+; CHECK-LABEL: test_memset:
+; CHECK: mov [[PVAL:x[0-9]+]], #-6148914691236517206
+; CHECK: stp [[PVAL]], [[PVAL]], [x0]
+; CHECK: ldp [[Q0:w[0-9]+]], [[Q1:w[0-9]+]], [x1]
+; CHECK: add w0, [[Q0]], [[Q1]]
+; CHECK: ret
+ %p0 = bitcast i32* %p to i8*
+ tail call void @llvm.memset.p0i8.i64(i8* noundef nonnull align 4 dereferenceable(16) %p0, i8 170, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32* %q, i64 1
+ %v1 = load i32, i32* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+; MIR-LABEL: name: test_mempcpy
+; MIR: %2:fpr128 = LDRQui %0, 1 :: (load 16 from %ir.p1, align 1)
+; MIR-NEXT: STRQui killed %2, %0, 0 :: (store 16 into %ir.p0, align 1)
+define i32 @test_mempcpy(i32* nocapture %p, i32* nocapture readonly %q) {
+; CHECK-LABEL: test_mempcpy:
+; CHECK: ldr [[PVAL:q[0-9]+]], [x0, #16]
+; CHECK: str [[PVAL]], [x0]
+; CHECK: ldp [[Q0:w[0-9]+]], [[Q1:w[0-9]+]], [x1]
+; CHECK: add w0, [[Q0]], [[Q1]]
+; CHECK: ret
+ %p0 = bitcast i32* %p to i8*
+ %add.ptr = getelementptr inbounds i32, i32* %p, i64 4
+ %p1 = bitcast i32* %add.ptr to i8*
+ %call = tail call i8* @mempcpy(i8* noundef nonnull align 4 dereferenceable(16) %p0, i8* noundef nonnull align 4 dereferenceable(16) %p1, i64 16), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32* %q, i64 1
+ %v1 = load i32, i32* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* noalias nocapture writeonly, i8* noalias nocapture readonly, i64, i1 immarg)
+declare void @llvm.memcpy.inline.p0i8.p0i8.i64(i8* noalias nocapture writeonly, i8* noalias nocapture readonly, i64, i1 immarg)
+declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1 immarg)
+declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1 immarg)
+
+declare i8* @mempcpy(i8*, i8*, i64)
+
+!0 = distinct !{!0, !"bax"}
+!1 = distinct !{!1, !0, !"bax: %p"}
+!2 = !{!1}
+!3 = distinct !{!3, !0, !"bax: %q"}
+!4 = !{!3}
diff --git a/llvm/test/CodeGen/AMDGPU/memcpy-scoped-aa.ll b/llvm/test/CodeGen/AMDGPU/memcpy-scoped-aa.ll
new file mode 100644
index 0000000000000..8398cfaa54358
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/memcpy-scoped-aa.ll
@@ -0,0 +1,108 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -o - %s | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -stop-after=finalize-isel -o - %s | FileCheck --check-prefix=MIR %s
+
+; Ensure that the scoped AA is attached on loads/stores lowered from mem ops.
+
+; Re-evaluate the slot numbers of scopes as that numbering could be changed run-by-run.
+
+; MIR-DAG: ![[DOMAIN:[0-9]+]] = distinct !{!{{[0-9]+}}, !"bax"}
+; MIR-DAG: ![[SCOPE0:[0-9]+]] = distinct !{!{{[0-9]+}}, ![[DOMAIN]], !"bax: %p"}
+; MIR-DAG: ![[SCOPE1:[0-9]+]] = distinct !{!{{[0-9]+}}, ![[DOMAIN]], !"bax: %q"}
+; MIR-DAG: ![[SET0:[0-9]+]] = !{![[SCOPE0]]}
+; MIR-DAG: ![[SET1:[0-9]+]] = !{![[SCOPE1]]}
+
+; MIR-LABEL: name: test_memcpy
+; MIR: %8:vreg_128 = GLOBAL_LOAD_DWORDX4 %9, 16, 0, implicit $exec :: (load 16 from %ir.p1, align 4, addrspace 1)
+; MIR: GLOBAL_STORE_DWORDX4 %10, killed %8, 0, 0, implicit $exec :: (store 16 into %ir.p0, align 4, addrspace 1)
+define i32 @test_memcpy(i32 addrspace(1)* nocapture %p, i32 addrspace(1)* nocapture readonly %q) {
+; Check loads of %q are scheduled ahead of that store of the memcpy on %p.
+; CHECK-LABEL: test_memcpy:
+; CHECK: global_load_dwordx4 [[PVAL:v\[[0-9]+:[0-9]+\]]], v[0:1], off offset:16
+; CHECK: global_store_dwordx4 v[0:1], [[PVAL]], off
+; CHECK: global_load_dwordx2 v{{\[}}[[Q0:[0-9]+]]:[[Q1:[0-9]+]]{{\]}}, v[2:3], off
+; CHECK: v_add_nc_u32_e32 v{{[0-9]+}}, v[[Q0]], v[[Q1]]
+; CHECK: s_setpc_b64 s[30:31]
+ %p0 = bitcast i32 addrspace(1)* %p to i8 addrspace(1)*
+ %add.ptr = getelementptr inbounds i32, i32 addrspace(1)* %p, i64 4
+ %p1 = bitcast i32 addrspace(1)* %add.ptr to i8 addrspace(1)*
+ tail call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* noundef nonnull align 4 dereferenceable(16) %p0, i8 addrspace(1)* noundef nonnull align 4 dereferenceable(16) %p1, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32 addrspace(1)* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32 addrspace(1)* %q, i64 1
+ %v1 = load i32, i32 addrspace(1)* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+; MIR-LABEL: name: test_memcpy_inline
+; MIR: %8:vreg_128 = GLOBAL_LOAD_DWORDX4 %9, 16, 0, implicit $exec :: (load 16 from %ir.p1, align 4, addrspace 1)
+; MIR: GLOBAL_STORE_DWORDX4 %10, killed %8, 0, 0, implicit $exec :: (store 16 into %ir.p0, align 4, addrspace 1)
+define i32 @test_memcpy_inline(i32 addrspace(1)* nocapture %p, i32 addrspace(1)* nocapture readonly %q) {
+; Check loads of %q are scheduled ahead of that store of the memcpy on %p.
+; CHECK-LABEL: test_memcpy_inline:
+; CHECK: global_load_dwordx4 [[PVAL:v\[[0-9]+:[0-9]+\]]], v[0:1], off offset:16
+; CHECK: global_store_dwordx4 v[0:1], [[PVAL]], off
+; CHECK: global_load_dwordx2 v{{\[}}[[Q0:[0-9]+]]:[[Q1:[0-9]+]]{{\]}}, v[2:3], off
+; CHECK: v_add_nc_u32_e32 v{{[0-9]+}}, v[[Q0]], v[[Q1]]
+; CHECK: s_setpc_b64 s[30:31]
+ %p0 = bitcast i32 addrspace(1)* %p to i8 addrspace(1)*
+ %add.ptr = getelementptr inbounds i32, i32 addrspace(1)* %p, i64 4
+ %p1 = bitcast i32 addrspace(1)* %add.ptr to i8 addrspace(1)*
+ tail call void @llvm.memcpy.inline.p1i8.p1i8.i64(i8 addrspace(1)* noundef nonnull align 4 dereferenceable(16) %p0, i8 addrspace(1)* noundef nonnull align 4 dereferenceable(16) %p1, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32 addrspace(1)* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32 addrspace(1)* %q, i64 1
+ %v1 = load i32, i32 addrspace(1)* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+; MIR-LABEL: name: test_memmove
+; MIR: %8:vreg_128 = GLOBAL_LOAD_DWORDX4 %9, 16, 0, implicit $exec :: (load 16 from %ir.p1, align 4, addrspace 1)
+; MIR: GLOBAL_STORE_DWORDX4 %10, killed %8, 0, 0, implicit $exec :: (store 16 into %ir.p0, align 4, addrspace 1)
+define i32 @test_memmove(i32 addrspace(1)* nocapture %p, i32 addrspace(1)* nocapture readonly %q) {
+; Check loads of %q are scheduled ahead of that store of the memmove on %p.
+; CHECK-LABEL: test_memmove:
+; CHECK: global_load_dwordx4 [[PVAL:v\[[0-9]+:[0-9]+\]]], v[0:1], off offset:16
+; CHECK: global_store_dwordx4 v[0:1], [[PVAL]]
+; CHECK: global_load_dwordx2 v{{\[}}[[Q0:[0-9]+]]:[[Q1:[0-9]+]]{{\]}}, v[2:3], off
+; CHECK: v_add_nc_u32_e32 v{{[0-9]+}}, v[[Q0]], v[[Q1]]
+; CHECK: s_setpc_b64 s[30:31]
+ %p0 = bitcast i32 addrspace(1)* %p to i8 addrspace(1)*
+ %add.ptr = getelementptr inbounds i32, i32 addrspace(1)* %p, i64 4
+ %p1 = bitcast i32 addrspace(1)* %add.ptr to i8 addrspace(1)*
+ tail call void @llvm.memmove.p1i8.p1i8.i64(i8 addrspace(1)* noundef nonnull align 4 dereferenceable(16) %p0, i8 addrspace(1)* noundef nonnull align 4 dereferenceable(16) %p1, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32 addrspace(1)* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32 addrspace(1)* %q, i64 1
+ %v1 = load i32, i32 addrspace(1)* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+; MIR-LABEL: name: test_memset
+; MIR: GLOBAL_STORE_DWORDX4 killed %10, killed %11, 0, 0, implicit $exec :: (store 16 into %ir.p0, align 4, addrspace 1)
+define i32 @test_memset(i32 addrspace(1)* nocapture %p, i32 addrspace(1)* nocapture readonly %q) {
+; Check loads of %q are scheduled ahead of that store of the memset on %p.
+; CHECK-LABEL: test_memset:
+; CHECK: v_mov_b32_e32 v[[PVAL:[0-9]+]], 0xaaaaaaaa
+; CHECK: global_store_dwordx4 v[0:1], v{{\[}}[[PVAL]]{{:[0-9]+\]}}, off
+; CHECK: global_load_dwordx2 v{{\[}}[[Q0:[0-9]+]]:[[Q1:[0-9]+]]{{\]}}, v[2:3], off
+; CHECK: v_add_nc_u32_e32 v{{[0-9]+}}, v[[Q0]], v[[Q1]]
+; CHECK: s_setpc_b64 s[30:31]
+ %p0 = bitcast i32 addrspace(1)* %p to i8 addrspace(1)*
+ tail call void @llvm.memset.p1i8.i64(i8 addrspace(1)* noundef nonnull align 4 dereferenceable(16) %p0, i8 170, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32 addrspace(1)* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32 addrspace(1)* %q, i64 1
+ %v1 = load i32, i32 addrspace(1)* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+declare void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* noalias nocapture writeonly, i8 addrspace(1)* noalias nocapture readonly, i64, i1 immarg)
+declare void @llvm.memcpy.inline.p1i8.p1i8.i64(i8 addrspace(1)* noalias nocapture writeonly, i8 addrspace(1)* noalias nocapture readonly, i64, i1 immarg)
+declare void @llvm.memmove.p1i8.p1i8.i64(i8 addrspace(1)* nocapture writeonly, i8 addrspace(1)* nocapture readonly, i64, i1 immarg)
+declare void @llvm.memset.p1i8.i64(i8 addrspace(1)* nocapture writeonly, i8, i64, i1 immarg)
+
+!0 = distinct !{!0, !"bax"}
+!1 = distinct !{!1, !0, !"bax: %p"}
+!2 = !{!1}
+!3 = distinct !{!3, !0, !"bax: %q"}
+!4 = !{!3}
diff --git a/llvm/test/CodeGen/X86/memcpy-scoped-aa.ll b/llvm/test/CodeGen/X86/memcpy-scoped-aa.ll
new file mode 100644
index 0000000000000..bd65caeade71e
--- /dev/null
+++ b/llvm/test/CodeGen/X86/memcpy-scoped-aa.ll
@@ -0,0 +1,106 @@
+; RUN: llc -mtriple=x86_64-linux-gnu -stop-after=finalize-isel -o - %s | FileCheck --check-prefix=MIR %s
+
+; Ensure that the scoped AA is attached on loads/stores lowered from mem ops.
+
+; Re-evaluate the slot numbers of scopes as that numbering could be changed run-by-run.
+
+; MIR-DAG: ![[DOMAIN:[0-9]+]] = distinct !{!{{[0-9]+}}, !"bax"}
+; MIR-DAG: ![[SCOPE0:[0-9]+]] = distinct !{!{{[0-9]+}}, ![[DOMAIN]], !"bax: %p"}
+; MIR-DAG: ![[SCOPE1:[0-9]+]] = distinct !{!{{[0-9]+}}, ![[DOMAIN]], !"bax: %q"}
+; MIR-DAG: ![[SET0:[0-9]+]] = !{![[SCOPE0]]}
+; MIR-DAG: ![[SET1:[0-9]+]] = !{![[SCOPE1]]}
+
+; MIR-LABEL: name: test_memcpy
+; MIR: %2:gr64 = MOV64rm %0, 1, $noreg, 16, $noreg :: (load 8 from %ir.p1, align 4)
+; MIR-NEXT: %3:gr64 = MOV64rm %0, 1, $noreg, 24, $noreg :: (load 8 from %ir.p1 + 8, align 4)
+; MIR-NEXT: MOV64mr %0, 1, $noreg, 8, $noreg, killed %3 :: (store 8 into %ir.p0 + 8, align 4)
+; MIR-NEXT: MOV64mr %0, 1, $noreg, 0, $noreg, killed %2 :: (store 8 into %ir.p0, align 4)
+define i32 @test_memcpy(i32* nocapture %p, i32* nocapture readonly %q) {
+ %p0 = bitcast i32* %p to i8*
+ %add.ptr = getelementptr inbounds i32, i32* %p, i64 4
+ %p1 = bitcast i32* %add.ptr to i8*
+ tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* noundef nonnull align 4 dereferenceable(16) %p0, i8* noundef nonnull align 4 dereferenceable(16) %p1, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32* %q, i64 1
+ %v1 = load i32, i32* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+; MIR-LABEL: name: test_memcpy_inline
+; MIR: %2:gr64 = MOV64rm %0, 1, $noreg, 16, $noreg :: (load 8 from %ir.p1, align 4)
+; MIR-NEXT: %3:gr64 = MOV64rm %0, 1, $noreg, 24, $noreg :: (load 8 from %ir.p1 + 8, align 4)
+; MIR-NEXT: MOV64mr %0, 1, $noreg, 8, $noreg, killed %3 :: (store 8 into %ir.p0 + 8, align 4)
+; MIR-NEXT: MOV64mr %0, 1, $noreg, 0, $noreg, killed %2 :: (store 8 into %ir.p0, align 4)
+define i32 @test_memcpy_inline(i32* nocapture %p, i32* nocapture readonly %q) {
+ %p0 = bitcast i32* %p to i8*
+ %add.ptr = getelementptr inbounds i32, i32* %p, i64 4
+ %p1 = bitcast i32* %add.ptr to i8*
+ tail call void @llvm.memcpy.inline.p0i8.p0i8.i64(i8* noundef nonnull align 4 dereferenceable(16) %p0, i8* noundef nonnull align 4 dereferenceable(16) %p1, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32* %q, i64 1
+ %v1 = load i32, i32* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+; MIR-LABEL: name: test_memmove
+; MIR: %2:gr64 = MOV64rm %0, 1, $noreg, 16, $noreg :: (load 8 from %ir.p1, align 4)
+; MIR-NEXT: %3:gr64 = MOV64rm %0, 1, $noreg, 24, $noreg :: (load 8 from %ir.p1 + 8, align 4)
+; MIR-NEXT: MOV64mr %0, 1, $noreg, 0, $noreg, killed %2 :: (store 8 into %ir.p0, align 4)
+; MIR-NEXT: MOV64mr %0, 1, $noreg, 8, $noreg, killed %3 :: (store 8 into %ir.p0 + 8, align 4)
+define i32 @test_memmove(i32* nocapture %p, i32* nocapture readonly %q) {
+ %p0 = bitcast i32* %p to i8*
+ %add.ptr = getelementptr inbounds i32, i32* %p, i64 4
+ %p1 = bitcast i32* %add.ptr to i8*
+ tail call void @llvm.memmove.p0i8.p0i8.i64(i8* noundef nonnull align 4 dereferenceable(16) %p0, i8* noundef nonnull align 4 dereferenceable(16) %p1, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32* %q, i64 1
+ %v1 = load i32, i32* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+; MIR-LABEL: name: test_memset
+; MIR: %2:gr64 = MOV64ri -6148914691236517206
+; MIR-NEXT: MOV64mr %0, 1, $noreg, 8, $noreg, %2 :: (store 8 into %ir.p0 + 8, align 4)
+; MIR-NEXT: MOV64mr %0, 1, $noreg, 0, $noreg, %2 :: (store 8 into %ir.p0, align 4)
+define i32 @test_memset(i32* nocapture %p, i32* nocapture readonly %q) {
+ %p0 = bitcast i32* %p to i8*
+ tail call void @llvm.memset.p0i8.i64(i8* noundef nonnull align 4 dereferenceable(16) %p0, i8 170, i64 16, i1 false), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32* %q, i64 1
+ %v1 = load i32, i32* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+; MIR-LABEL: name: test_mempcpy
+; MIR: %2:gr64 = MOV64rm %0, 1, $noreg, 16, $noreg :: (load 8 from %ir.p1, align 1)
+; MIR-NEXT: %3:gr64 = MOV64rm %0, 1, $noreg, 24, $noreg :: (load 8 from %ir.p1 + 8, align 1)
+; MIR-NEXT: MOV64mr %0, 1, $noreg, 8, $noreg, killed %3 :: (store 8 into %ir.p0 + 8, align 1)
+; MIR-NEXT: MOV64mr %0, 1, $noreg, 0, $noreg, killed %2 :: (store 8 into %ir.p0, align 1)
+define i32 @test_mempcpy(i32* nocapture %p, i32* nocapture readonly %q) {
+ %p0 = bitcast i32* %p to i8*
+ %add.ptr = getelementptr inbounds i32, i32* %p, i64 4
+ %p1 = bitcast i32* %add.ptr to i8*
+ %call = tail call i8* @mempcpy(i8* noundef nonnull align 4 dereferenceable(16) %p0, i8* noundef nonnull align 4 dereferenceable(16) %p1, i64 16), !alias.scope !2, !noalias !4
+ %v0 = load i32, i32* %q, align 4, !alias.scope !4, !noalias !2
+ %q1 = getelementptr inbounds i32, i32* %q, i64 1
+ %v1 = load i32, i32* %q1, align 4, !alias.scope !4, !noalias !2
+ %add = add i32 %v0, %v1
+ ret i32 %add
+}
+
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* noalias nocapture writeonly, i8* noalias nocapture readonly, i64, i1 immarg)
+declare void @llvm.memcpy.inline.p0i8.p0i8.i64(i8* noalias nocapture writeonly, i8* noalias nocapture readonly, i64, i1 immarg)
+declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1 immarg)
+declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1 immarg)
+
+declare i8* @mempcpy(i8*, i8*, i64)
+
+!0 = distinct !{!0, !"bax"}
+!1 = distinct !{!1, !0, !"bax: %p"}
+!2 = !{!1}
+!3 = distinct !{!3, !0, !"bax: %q"}
+!4 = !{!3}
More information about the llvm-commits
mailing list