Fix repro build: add -arch=native to use correct GPU architecture

NVCC 13.1 defaults to a PTX version incompatible with the installed
driver (580.105.08), causing kernels to silently fail with "provided
PTX was compiled with an unsupported toolchain". Use -arch=native so
NVCC auto-detects the target GPU (H100, sm_90) at build time.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Basil Milanich
2026-04-06 13:33:05 -05:00
parent f74dd21573
commit d9a1cc06c1

View File

@@ -10,8 +10,8 @@ LIBS := -L$(CUPTI_LIB) -lcuda -lcupti -lpthread -ldl
CXXFLAGS_REL := -O2 -DTRACY_ENABLE
CXXFLAGS_DBG := -g -O0 -DTRACY_ENABLE
NVCCFLAGS_REL := -O2 -DTRACY_ENABLE
NVCCFLAGS_DBG := -g -O0 -DTRACY_ENABLE
NVCCFLAGS_REL := -arch=native -O2 -DTRACY_ENABLE
NVCCFLAGS_DBG := -arch=native -g -O0 -DTRACY_ENABLE
.PHONY: all debug clean