[NVPTX] Add errors for incorrect CUDA addrpaces #138706
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-llvm-ir @llvm/pr-subscribers-backend-nvptx Author: Lewis Crawford (LewisCrawford) ChangesThe CUDA API only accepts kernel params in the global and generic address spaces, so display an error message when attempting to emit pointers outside those address-spaces from CUDA (but still allow them for OpenCL). Full diff: https://github.com/llvm/llvm-project/pull/138706.diff 5 Files Affected:
diff --git a/llvm/lib/Target/NVPTX/NVPTXAsmPrinter.cpp b/llvm/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
index 2f4b109e8e9e9..9e17adb6ac1ae 100644
--- a/llvm/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
+++ b/llvm/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
@@ -1399,6 +1399,8 @@ void NVPTXAsmPrinter::emitFunctionParamList(const Function *F, raw_ostream &O) {
if (PTy) {
O << "\t.param .u" << PTySizeInBits << " .ptr";
+ bool IsCUDA = static_cast<NVPTXTargetMachine &>(TM).getDrvInterface() ==
+ NVPTX::CUDA;
switch (PTy->getAddressSpace()) {
default:
break;
@@ -1406,12 +1408,18 @@ void NVPTXAsmPrinter::emitFunctionParamList(const Function *F, raw_ostream &O) {
O << " .global";
break;
case ADDRESS_SPACE_SHARED:
+ if (IsCUDA)
+ report_fatal_error(".shared ptr kernel args unsupported in CUDA.");
O << " .shared";
break;
case ADDRESS_SPACE_CONST:
+ if (IsCUDA)
+ report_fatal_error(".const ptr kernel args unsupported in CUDA.");
O << " .const";
break;
case ADDRESS_SPACE_LOCAL:
+ if (IsCUDA)
+ report_fatal_error(".local ptr kernel args unsupported in CUDA.");
O << " .local";
break;
}
diff --git a/llvm/test/CodeGen/NVPTX/kernel-param-align.ll b/llvm/test/CodeGen/NVPTX/kernel-param-align.ll
index a56b85de80143..e85ccf34bb6ac 100644
--- a/llvm/test/CodeGen/NVPTX/kernel-param-align.ll
+++ b/llvm/test/CodeGen/NVPTX/kernel-param-align.ll
@@ -1,5 +1,6 @@
-; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_60 | FileCheck %s
-; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_60 | %ptxas -arch=sm_60 - %}
+; RUN: llc < %s -mcpu=sm_60 | FileCheck %s
+; RUN: %if ptxas %{ llc < %s -mcpu=sm_60 | %ptxas -arch=sm_60 - %}
+target triple = "nvptx64-nvidia-nvcl"
%struct.Large = type { [16 x double] }
diff --git a/llvm/test/CodeGen/NVPTX/lower-args-cuda.ll b/llvm/test/CodeGen/NVPTX/lower-args-cuda.ll
new file mode 100644
index 0000000000000..7361ab28badb9
--- /dev/null
+++ b/llvm/test/CodeGen/NVPTX/lower-args-cuda.ll
@@ -0,0 +1,13 @@
+; RUN: not --crash llc < %s -mcpu=sm_75 -o /dev/null 2>&1 | FileCheck %s
+
+target datalayout = "e-i64:64-i128:128-v16:16-v32:32-n16:32:64"
+target triple = "nvptx64-nvidia-cuda"
+
+; Make sure we exit with an error message for this input, as pointers to the
+; shared address-space are only supported as kernel args in NVCL, not CUDA.
+; CHECK: .shared ptr kernel args unsupported in CUDA.
+define ptx_kernel void @ptr_nongeneric(ptr addrspace(1) %out, ptr addrspace(3) %in) {
+ %v = load i32, ptr addrspace(3) %in, align 4
+ store i32 %v, ptr addrspace(1) %out, align 4
+ ret void
+}
diff --git a/llvm/test/CodeGen/NVPTX/lower-args-nvcl.ll b/llvm/test/CodeGen/NVPTX/lower-args-nvcl.ll
new file mode 100644
index 0000000000000..44b44e0c17626
--- /dev/null
+++ b/llvm/test/CodeGen/NVPTX/lower-args-nvcl.ll
@@ -0,0 +1,17 @@
+; RUN: opt < %s -S -nvptx-lower-args | FileCheck %s --check-prefixes COMMON,IR
+; RUN: llc < %s -mcpu=sm_20 | FileCheck %s --check-prefixes COMMON,PTX
+; RUN: %if ptxas %{ llc < %s -mcpu=sm_20 | %ptxas-verify %}
+
+target datalayout = "e-i64:64-i128:128-v16:16-v32:32-n16:32:64"
+target triple = "nvptx64-nvidia-nvcl"
+
+; COMMON-LABEL: ptr_nongeneric
+define ptx_kernel void @ptr_nongeneric(ptr addrspace(1) %out, ptr addrspace(3) %in) {
+; IR-NOT: addrspacecast
+; PTX-NOT: cvta.to.global
+; PTX: ld.shared.u32
+; PTX st.global.u32
+ %v = load i32, ptr addrspace(3) %in, align 4
+ store i32 %v, ptr addrspace(1) %out, align 4
+ ret void
+}
diff --git a/llvm/test/CodeGen/NVPTX/lower-args.ll b/llvm/test/CodeGen/NVPTX/lower-args.ll
index 8e879871e295b..44445a17d1eb3 100644
--- a/llvm/test/CodeGen/NVPTX/lower-args.ll
+++ b/llvm/test/CodeGen/NVPTX/lower-args.ll
@@ -140,29 +140,6 @@ define ptx_kernel void @ptr_generic(ptr %out, ptr %in) {
ret void
}
-define ptx_kernel void @ptr_nongeneric(ptr addrspace(1) %out, ptr addrspace(3) %in) {
-; IR-LABEL: define ptx_kernel void @ptr_nongeneric(
-; IR-SAME: ptr addrspace(1) [[OUT:%.*]], ptr addrspace(3) [[IN:%.*]]) {
-; IR-NEXT: [[V:%.*]] = load i32, ptr addrspace(3) [[IN]], align 4
-; IR-NEXT: store i32 [[V]], ptr addrspace(1) [[OUT]], align 4
-; IR-NEXT: ret void
-;
-; PTX-LABEL: ptr_nongeneric(
-; PTX: {
-; PTX-NEXT: .reg .b32 %r<2>;
-; PTX-NEXT: .reg .b64 %rd<3>;
-; PTX-EMPTY:
-; PTX-NEXT: // %bb.0:
-; PTX-NEXT: ld.param.u64 %rd1, [ptr_nongeneric_param_0];
-; PTX-NEXT: ld.param.u64 %rd2, [ptr_nongeneric_param_1];
-; PTX-NEXT: ld.shared.u32 %r1, [%rd2];
-; PTX-NEXT: st.global.u32 [%rd1], %r1;
-; PTX-NEXT: ret;
- %v = load i32, ptr addrspace(3) %in, align 4
- store i32 %v, ptr addrspace(1) %out, align 4
- ret void
-}
-
define ptx_kernel void @ptr_as_int(i64 noundef %i, i32 noundef %v) {
; IRC-LABEL: define ptx_kernel void @ptr_as_int(
; IRC-SAME: i64 noundef [[I:%.*]], i32 noundef [[V:%.*]]) {
|
gonzalobg
approved these changes
May 6, 2025
|
One thing I wonder is whether this sort of logic really belongs in assembly printing. It seems like this verification could happen at any point during compilation, such as during an IR pass. Are there examples from other targets of target-specific IR verification? Do you have any thoughts about alternative locations for this verification? |
Artem-B
reviewed
May 6, 2025
The CUDA API only accepts kernel params in the global and generic address spaces, so display an error message when attempting to emit pointers outside those address-spaces from CUDA (but still allow them for OpenCL).
Fix a clang test which failed with these new error messages, as it illegally passed in kernel args in the .local address space while using the -cuda triple.
c67fc1c to
7853795
Compare
Update the lower-args-nvcl.ll test to use the newly preferred untyped load/stores to b64 instead of the u64 ones the origninal version of the test used.
Move the CUDA address-space checks out of ASMPrinter and into the IR Verifier.
Artem-B
reviewed
May 19, 2025
Comment on lines
+2936
to
+2937
| Check(AS != NVPTXAS::AddressSpace::ADDRESS_SPACE_SHARED, | ||
| ".shared ptr kernel args unsupported in CUDA.", &Arg, &F); |
There was a problem hiding this comment.
I think the check should be rephrased to only allow generic and global AS, and error out on anything else, so we don't have to update it when a new AS is added, or if/when someone uses a nonsensical AS.
|
I think it might be best to just close this, and leave it to front-ends to validate instead of adding IR-level validation, as it would make certain IR-level tests a lot more inconvenient to write. The chances of someone hitting problems from using invalid address-spaces like this in a real kernel in a way that bypasses any error-checking the front-end are a lot lower than someone hitting the new error message from this patch while trying to write an IR-level test and having to find an inconvenient workaround for it. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The CUDA API only accepts kernel params in the global and generic address spaces, so display an error message when attempting to emit pointers outside those address-spaces from CUDA (but still allow them for OpenCL).