[PATCH] D97009: [CUDA] fix builtin constraints for PTX 7.2

[Jordan Rupprecht via Phabricator via cfe-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rG1a368ae3b78d: [CUDA] fix builtin constraints for PTX 7.2 
(authored by tra, committed by rupprecht).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D97009/new/

https://reviews.llvm.org/D97009

Files:
  clang/include/clang/Basic/BuiltinsNVPTX.def
  clang/test/CodeGen/builtins-nvptx-sm_70.cu


Index: clang/test/CodeGen/builtins-nvptx-sm_70.cu
===================================================================
--- clang/test/CodeGen/builtins-nvptx-sm_70.cu
+++ clang/test/CodeGen/builtins-nvptx-sm_70.cu
@@ -6,6 +6,11 @@
 // RUN:            -fcuda-is-device -target-feature +ptx61 -DPTX61 \
 // RUN:            -S -emit-llvm -o - -x cuda %s \
 // RUN:   | FileCheck -check-prefixes=CHECK_M16,CHECK_M32_M8 %s
+// Make sure builtins still work with the latest combination of GPU & PTX.
+// RUN: %clang_cc1 -triple nvptx64-unknown-unknown -target-cpu sm_86 \
+// RUN:            -fcuda-is-device -target-feature +ptx72 -DPTX61 \
+// RUN:            -S -emit-llvm -o - -x cuda %s \
+// RUN:   | FileCheck -check-prefixes=CHECK_M16,CHECK_M32_M8 %s
 // RUN: %clang_cc1 -triple nvptx-unknown-unknown -target-cpu sm_60 \
 // RUN:   -DPTX61 -fcuda-is-device -S -o /dev/null -x cuda -verify=pre-sm_70 %s
 // RUN: %clang_cc1 -triple nvptx-unknown-unknown \
Index: clang/include/clang/Basic/BuiltinsNVPTX.def
===================================================================
--- clang/include/clang/Basic/BuiltinsNVPTX.def
+++ clang/include/clang/Basic/BuiltinsNVPTX.def
@@ -38,7 +38,9 @@
 #pragma push_macro("PTX65")
 #pragma push_macro("PTX70")
 #pragma push_macro("PTX71")
-#define PTX71 "ptx71"
+#pragma push_macro("PTX72")
+#define PTX72 "ptx72"
+#define PTX71 "ptx71|" PTX72
 #define PTX70 "ptx70|" PTX71
 #define PTX65 "ptx65|" PTX70
 #define PTX64 "ptx64|" PTX65
@@ -740,3 +742,4 @@
 #pragma pop_macro("PTX65")
 #pragma pop_macro("PTX70")
 #pragma pop_macro("PTX71")
+#pragma pop_macro("PTX72")



Index: clang/test/CodeGen/builtins-nvptx-sm_70.cu
===================================================================
--- clang/test/CodeGen/builtins-nvptx-sm_70.cu
+++ clang/test/CodeGen/builtins-nvptx-sm_70.cu
@@ -6,6 +6,11 @@
 // RUN:            -fcuda-is-device -target-feature +ptx61 -DPTX61 \
 // RUN:            -S -emit-llvm -o - -x cuda %s \
 // RUN:   | FileCheck -check-prefixes=CHECK_M16,CHECK_M32_M8 %s
+// Make sure builtins still work with the latest combination of GPU & PTX.
+// RUN: %clang_cc1 -triple nvptx64-unknown-unknown -target-cpu sm_86 \
+// RUN:            -fcuda-is-device -target-feature +ptx72 -DPTX61 \
+// RUN:            -S -emit-llvm -o - -x cuda %s \
+// RUN:   | FileCheck -check-prefixes=CHECK_M16,CHECK_M32_M8 %s
 // RUN: %clang_cc1 -triple nvptx-unknown-unknown -target-cpu sm_60 \
 // RUN:   -DPTX61 -fcuda-is-device -S -o /dev/null -x cuda -verify=pre-sm_70 %s
 // RUN: %clang_cc1 -triple nvptx-unknown-unknown \
Index: clang/include/clang/Basic/BuiltinsNVPTX.def
===================================================================
--- clang/include/clang/Basic/BuiltinsNVPTX.def
+++ clang/include/clang/Basic/BuiltinsNVPTX.def
@@ -38,7 +38,9 @@
 #pragma push_macro("PTX65")
 #pragma push_macro("PTX70")
 #pragma push_macro("PTX71")
-#define PTX71 "ptx71"
+#pragma push_macro("PTX72")
+#define PTX72 "ptx72"
+#define PTX71 "ptx71|" PTX72
 #define PTX70 "ptx70|" PTX71
 #define PTX65 "ptx65|" PTX70
 #define PTX64 "ptx64|" PTX65
@@ -740,3 +742,4 @@
 #pragma pop_macro("PTX65")
 #pragma pop_macro("PTX70")
 #pragma pop_macro("PTX71")
+#pragma pop_macro("PTX72")

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits