1 files changed, 146 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-precise-allocate-to-module-struct.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-precise-allocate-to-module-struct.ll
new file mode 100644
index 0000000..0de7f8f
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-precise-allocate-to-module-struct.ll
@@ -0,0 +1,146 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --check-globals
+; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds --amdgpu-lower-module-lds-strategy=module < %s | FileCheck %s
+
+; Regression test for issue 160181
+; One variable is chosen to be assigned at zero. Here, that's @both
+; Then other variables should be allocated at fixed offsets from that provided
+; they are allocated by all the other kernels that presently allocate the
+; variable at address zero.
+; The failure mode was in that second check - variables could be added to
+; the module scope zero address struct even when some of the kernels allocating
+; that struct do not need the additional variable.
+
+; With current llvm, all three of these integers are put in the module scope struct, when
+; neither kern_one or kern_two access all three.
+
+@both = addrspace(3) global i32 poison
+@both_second = addrspace(3) global i16 poison ; a second field in the module struct
+@one = addrspace(3) global i32 poison
+@two = addrspace(3) global i32 poison
+
+
+;.
+; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t poison, align 4, !absolute_symbol [[META0:![0-9]+]]
+; CHECK: @llvm.compiler.used = appending addrspace(1) global [1 x ptr] [ptr addrspacecast (ptr addrspace(3) @llvm.amdgcn.module.lds to ptr)], section "llvm.metadata"
+;.
+define void @func_one() {
+; CHECK-LABEL: define {{[^@]+}}@func_one() {
+; CHECK-NEXT:    [[VAL0:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !noalias [[META1:![0-9]+]]
+; CHECK-NEXT:    store i32 [[VAL0]], ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_MODULE_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.module.lds, i32 0, i32 1), align 4, !noalias [[META18:![0-9]+]]
+; CHECK-NEXT:    store i16 10, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_MODULE_LDS_T]], ptr addrspace(3) @llvm.amdgcn.module.lds, i32 0, i32 3), align 4, !noalias [[META23:![0-9]+]]
+; CHECK-NEXT:    ret void
+;
+  %val0 = load i32, ptr addrspace(3) @both
+  store i32 %val0, ptr addrspace(3) @one
+  store i16 10, ptr addrspace(3) @both_second
+  ret void
+}
+
+define amdgpu_kernel void @kern_one() {
+; CHECK-LABEL: define {{[^@]+}}@kern_one
+; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ], !noalias [[META24:![0-9]+]]
+; CHECK-NEXT:    call void @func_one()
+; CHECK-NEXT:    ret void
+;
+entry:
+  call void @func_one()
+  ret void
+}
+
+define void @func_two() {
+; CHECK-LABEL: define {{[^@]+}}@func_two() {
+; CHECK-NEXT:    [[VAL0:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !noalias [[META1]]
+; CHECK-NEXT:    store i32 [[VAL0]], ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_MODULE_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.module.lds, i32 0, i32 2), align 4, !noalias [[META25:![0-9]+]]
+; CHECK-NEXT:    store i16 20, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_MODULE_LDS_T]], ptr addrspace(3) @llvm.amdgcn.module.lds, i32 0, i32 3), align 4, !noalias [[META23]]
+; CHECK-NEXT:    ret void
+;
+  %val0 = load i32, ptr addrspace(3) @both
+  store i32 %val0, ptr addrspace(3) @two
+  store i16 20, ptr addrspace(3) @both_second
+  ret void
+}
+
+define amdgpu_kernel void @kern_two() {
+; CHECK-LABEL: define {{[^@]+}}@kern_two
+; CHECK-SAME: () #[[ATTR0]] {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ], !alias.scope [[META26:![0-9]+]], !noalias [[META27:![0-9]+]]
+; CHECK-NEXT:    call void @func_two()
+; CHECK-NEXT:    ret void
+;
+entry:
+  call void @func_two()
+  ret void
+}
+
+; Unrelated to the bug at hand, but if a variable is only
+; reachable from a single kernel, it gets allocated to a fixed
+; address independent of the module scope struct. This kernel
+; means the key variables miss that optimisation while @both
+; remains the best candidate for address zero allocation.
+define void @func_block_direct_allocation() {
+; CHECK-LABEL: define {{[^@]+}}@func_block_direct_allocation() {
+; CHECK-NEXT:    [[VAL1:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_MODULE_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.module.lds, i32 0, i32 1), align 4, !noalias [[META18]]
+; CHECK-NEXT:    [[VAL2:%.*]] = load i32, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_MODULE_LDS_T]], ptr addrspace(3) @llvm.amdgcn.module.lds, i32 0, i32 2), align 4, !noalias [[META25]]
+; CHECK-NEXT:    [[SUM:%.*]] = add i32 [[VAL1]], [[VAL2]]
+; CHECK-NEXT:    store i32 [[SUM]], ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !noalias [[META1]]
+; CHECK-NEXT:    store i16 30, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_MODULE_LDS_T]], ptr addrspace(3) @llvm.amdgcn.module.lds, i32 0, i32 3), align 4, !noalias [[META23]]
+; CHECK-NEXT:    ret void
+;
+  %val1 = load i32, ptr addrspace(3) @one
+  %val2 = load i32, ptr addrspace(3) @two
+  %sum = add i32 %val1, %val2
+  store i32 %sum, ptr addrspace(3) @both
+  store i16 30, ptr addrspace(3) @both_second
+  ret void
+}
+
+define amdgpu_kernel void @kern_block_direct_allocation() {
+; CHECK-LABEL: define {{[^@]+}}@kern_block_direct_allocation
+; CHECK-SAME: () #[[ATTR0]] {
+; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
+; CHECK-NEXT:    call void @func_block_direct_allocation()
+; CHECK-NEXT:    call void @func_one()
+; CHECK-NEXT:    call void @func_two()
+; CHECK-NEXT:    ret void
+;
+  call void @func_block_direct_allocation()
+  call void @func_one()
+  call void @func_two()
+  ret void
+}
+;.
+; CHECK: attributes #[[ATTR0]] = { "amdgpu-lds-size"="16" }
+; CHECK: attributes #[[ATTR1:[0-9]+]] = { nocallback nofree nosync nounwind willreturn memory(none) }
+;.
+; CHECK: [[META0]] = !{i32 0, i32 1}
+; CHECK: [[META1]] = !{[[META2:![0-9]+]], [[META4:![0-9]+]], [[META5:![0-9]+]], [[META6:![0-9]+]], [[META8:![0-9]+]], [[META9:![0-9]+]], [[META10:![0-9]+]], [[META12:![0-9]+]], [[META13:![0-9]+]], [[META14:![0-9]+]], [[META16:![0-9]+]], [[META17:![0-9]+]]}
+; CHECK: [[META2]] = distinct !{[[META2]], [[META3:![0-9]+]]}
+; CHECK: [[META3]] = distinct !{[[META3]]}
+; CHECK: [[META4]] = distinct !{[[META4]], [[META3]]}
+; CHECK: [[META5]] = distinct !{[[META5]], [[META3]]}
+; CHECK: [[META6]] = distinct !{[[META6]], [[META7:![0-9]+]]}
+; CHECK: [[META7]] = distinct !{[[META7]]}
+; CHECK: [[META8]] = distinct !{[[META8]], [[META7]]}
+; CHECK: [[META9]] = distinct !{[[META9]], [[META7]]}
+; CHECK: [[META10]] = distinct !{[[META10]], [[META11:![0-9]+]]}
+; CHECK: [[META11]] = distinct !{[[META11]]}
+; CHECK: [[META12]] = distinct !{[[META12]], [[META11]]}
+; CHECK: [[META13]] = distinct !{[[META13]], [[META11]]}
+; CHECK: [[META14]] = distinct !{[[META14]], [[META15:![0-9]+]]}
+; CHECK: [[META15]] = distinct !{[[META15]]}
+; CHECK: [[META16]] = distinct !{[[META16]], [[META15]]}
+; CHECK: [[META17]] = distinct !{[[META17]], [[META15]]}
+; CHECK: [[META18]] = !{[[META19:![0-9]+]], [[META2]], [[META5]], [[META20:![0-9]+]], [[META6]], [[META9]], [[META21:![0-9]+]], [[META10]], [[META13]], [[META22:![0-9]+]], [[META14]], [[META17]]}
+; CHECK: [[META19]] = distinct !{[[META19]], [[META3]]}
+; CHECK: [[META20]] = distinct !{[[META20]], [[META7]]}
+; CHECK: [[META21]] = distinct !{[[META21]], [[META11]]}
+; CHECK: [[META22]] = distinct !{[[META22]], [[META15]]}
+; CHECK: [[META23]] = !{[[META19]], [[META4]], [[META5]], [[META20]], [[META8]], [[META9]], [[META21]], [[META12]], [[META13]], [[META22]], [[META16]], [[META17]]}
+; CHECK: [[META24]] = !{[[META10]], [[META12]], [[META13]], [[META14]], [[META16]], [[META17]]}
+; CHECK: [[META25]] = !{[[META19]], [[META2]], [[META4]], [[META20]], [[META6]], [[META8]], [[META21]], [[META10]], [[META12]], [[META22]], [[META14]], [[META16]]}
+; CHECK: [[META26]] = !{[[META22]]}
+; CHECK: [[META27]] = !{[[META14]], [[META16]], [[META17]]}
+;.