[PATCH] D134741: [amdgpu] Error, instead of miscompile, anonymous kernels using lds

[Jon Chesterfield via Phabricator via llvm-commits]

JonChesterfield updated this revision to Diff 463566.
JonChesterfield added a comment.

- redirect stderr


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D134741/new/

https://reviews.llvm.org/D134741

Files:
  llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
  llvm/test/CodeGen/AMDGPU/lds-reject-anonymous-kernels.ll
  llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll


Index: llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll
+++ llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll
@@ -10,16 +10,16 @@
 ; CHECK: %llvm.amdgcn.module.lds.t = type { [8 x i8], [1 x i8] }
 ; CHECK: %llvm.amdgcn.kernel.k0.lds.t = type { [16 x i8], [4 x i8], [2 x i8] }
 ; CHECK: %llvm.amdgcn.kernel.k1.lds.t = type { [16 x i8], [4 x i8], [2 x i8] }
-; CHECK: %llvm.amdgcn.kernel..lds.t = type { [2 x i8] }
-; CHECK: %llvm.amdgcn.kernel..lds.t.0 = type { [4 x i8] }
+; CHECK: %llvm.amdgcn.kernel.k2.lds.t = type { [2 x i8] }
+; CHECK: %llvm.amdgcn.kernel.k3.lds.t = type { [4 x i8] }
 
 ;.
 ; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t undef, align 8
 ; CHECK: @llvm.compiler.used = appending global [1 x i8*] [i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.module.lds.t, %llvm.amdgcn.module.lds.t addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0, i32 0) to i8*)], section "llvm.metadata"
 ; CHECK: @llvm.amdgcn.kernel.k0.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k0.lds.t undef, align 16
 ; CHECK: @llvm.amdgcn.kernel.k1.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k1.lds.t undef, align 16
-; CHECK: @llvm.amdgcn.kernel..lds = internal addrspace(3) global %llvm.amdgcn.kernel..lds.t undef, align 2
-; CHECK: @llvm.amdgcn.kernel..lds.1 = internal addrspace(3) global %llvm.amdgcn.kernel..lds.t.0 undef, align 4
+; CHECK: @llvm.amdgcn.kernel.k2.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k2.lds.t undef, align 2
+; CHECK: @llvm.amdgcn.kernel.k3.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k3.lds.t undef, align 4
 ;.
 define amdgpu_kernel void @k0() #0 {
 ; CHECK-LABEL: @k0(
@@ -70,9 +70,9 @@
   ret void
 }
 
-define amdgpu_kernel void @0() #0 {
-; CHECK-LABEL: @0(
-; CHECK-NEXT:    %lds.size.2.align.2.bc = bitcast [2 x i8] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel..lds.t, %llvm.amdgcn.kernel..lds.t addrspace(3)* @llvm.amdgcn.kernel..lds, i32 0, i32 0) to i8 addrspace(3)*
+define amdgpu_kernel void @k2() #0 {
+; CHECK-LABEL: @k2(
+; CHECK-NEXT:    %lds.size.2.align.2.bc = bitcast [2 x i8] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k2.lds.t, %llvm.amdgcn.kernel.k2.lds.t addrspace(3)* @llvm.amdgcn.kernel.k2.lds, i32 0, i32 0) to i8 addrspace(3)*
 ; CHECK-NEXT:    store i8 2, i8 addrspace(3)* %lds.size.2.align.2.bc, align 2
 ; CHECK-NEXT:    ret void
 ;
@@ -82,9 +82,9 @@
   ret void
 }
 
-define amdgpu_kernel void @1() #0 {
-; CHECK-LABEL: @1(
-; CHECK-NEXT:    %lds.size.4.align.4.bc = bitcast [4 x i8] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel..lds.t.0, %llvm.amdgcn.kernel..lds.t.0 addrspace(3)* @llvm.amdgcn.kernel..lds.1, i32 0, i32 0) to i8 addrspace(3)*
+define amdgpu_kernel void @k3() #0 {
+; CHECK-LABEL: @k3(
+; CHECK-NEXT:    %lds.size.4.align.4.bc = bitcast [4 x i8] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k3.lds.t, %llvm.amdgcn.kernel.k3.lds.t addrspace(3)* @llvm.amdgcn.kernel.k3.lds, i32 0, i32 0) to i8 addrspace(3)*
 ; CHECK-NEXT:    store i8 4, i8 addrspace(3)* %lds.size.4.align.4.bc, align 4
 ; CHECK-NEXT:    ret void
 ;
Index: llvm/test/CodeGen/AMDGPU/lds-reject-anonymous-kernels.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/lds-reject-anonymous-kernels.ll
@@ -0,0 +1,12 @@
+; RUN: not --crash opt -S -mtriple=amdgcn-- -amdgpu-lower-module-lds < %s 2>&1 | FileCheck %s
+; RUN: not --crash opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s 2>&1 | FileCheck %s
+
+ at var1 = addrspace(3) global i32 undef, align 8
+
+; CHECK: LLVM ERROR: Anonymous kernels cannot use LDS variables
+define amdgpu_kernel void @0() {
+  %val0 = load i32, i32 addrspace(3)* @var1
+  %val1 = add i32 %val0, 4
+  store i32 %val1, i32 addrspace(3)* @var1
+  ret void
+}
Index: llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
@@ -293,6 +293,16 @@
           AMDGPU::findLDSVariablesToLower(M, &F);
 
       if (!KernelUsedVariables.empty()) {
+        // The association between kernel function and LDS struct is done by
+        // symbol name, which only works if the function in question has a name
+        // This is not expected to be a problem in practice as kernels are
+        // called by name making anonymous ones (which are named by the backend)
+        // difficult to use. This does mean that llvm test cases need
+        // to name the kernels.
+        if (!F.hasName()) {
+          report_fatal_error("Anonymous kernels cannot use LDS variables");
+        }
+
         std::string VarName =
             (Twine("llvm.amdgcn.kernel.") + F.getName() + ".lds").str();
         GlobalVariable *SGV;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D134741.463566.patch
Type: text/x-patch
Size: 5024 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220928/6458cb89/attachment.bin>