Skip to content

[NVPTX] Fix ptxas failures (NFC) #125147

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Feb 2, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/griddepcontrol.ll
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mcpu=sm_90 -march=nvptx64 | FileCheck %s
; RUN: %if ptxas-11.8 %{ llc < %s -mcpu=sm_90 -march=nvptx64 | %ptxas-verify %}
; RUN: %if ptxas-11.8 %{ llc < %s -mcpu=sm_90 -march=nvptx64 | %ptxas-verify -arch=sm_90 %}

define void @griddepcontrol() {
; CHECK-LABEL: griddepcontrol(
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/CodeGen/NVPTX/kernel-param-align.ll
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_60 | FileCheck %s
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_60 | %ptxas-verify %}
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_60 | %ptxas -arch=sm_60 - %}

%struct.Large = type { [16 x double] }

Expand Down
6 changes: 3 additions & 3 deletions llvm/test/CodeGen/NVPTX/lower-args.ll
Original file line number Diff line number Diff line change
Expand Up @@ -87,12 +87,12 @@ define ptx_kernel void @ptr_generic(ptr %out, ptr %in) {
}

; COMMON-LABEL: ptr_nongeneric
define ptx_kernel void @ptr_nongeneric(ptr addrspace(1) %out, ptr addrspace(4) %in) {
define ptx_kernel void @ptr_nongeneric(ptr addrspace(1) %out, ptr addrspace(3) %in) {
; IR-NOT: addrspacecast
; PTX-NOT: cvta.to.global
; PTX: ld.const.u32
; PTX: ld.shared.u32
; PTX st.global.u32
%v = load i32, ptr addrspace(4) %in, align 4
%v = load i32, ptr addrspace(3) %in, align 4
store i32 %v, ptr addrspace(1) %out, align 4
ret void
}
Expand Down