diff --git a/CMakeLists.txt b/CMakeLists.txt
index 57c83a8ef..79801b719 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -47,11 +47,16 @@ ENDIF()
 # came out differently from the same source and data. Off, every x86-64 level computes the same bits
 # (measured: identical p.mtz on nine battery sets, no measurable time cost), and aarch64, where FMA is
 # always there and GCC contracts by default, follows the same arithmetic. MSVC does not contract under
-# its default /fp:precise. Host code of .cu sources gets it through nvcc; device code is not affected.
+# its default /fp:precise. Host code of .cu sources gets it through nvcc.
 IF (NOT MSVC)
     ADD_COMPILE_OPTIONS($<$<COMPILE_LANGUAGE:C,CXX>:-ffp-contract=off>)
     ADD_COMPILE_OPTIONS($<$<COMPILE_LANGUAGE:CUDA>:-Xcompiler=-ffp-contract=off>)
 ENDIF()
+# The same for device code. nvcc contracts by default and does it separately for every architecture
+# it compiles for, so a T4 (sm_75) and an RTX 5080 (sm_120) ran the same kernels to different bits
+# and a run that hit a knife edge came out differently on the two machines. Off, the architectures
+# compute the same bits (measured: identical p.hkl from sm_75 and sm_120 builds, no measurable time cost).
+ADD_COMPILE_OPTIONS($<$<COMPILE_LANGUAGE:CUDA>:--fmad=false>)
 
 SET(JFJOCH_WRITER_ONLY           OFF CACHE BOOL "Compile HDF5 writer only")
 SET(JFJOCH_INSTALL_DRIVER_SOURCE OFF CACHE BOOL "Install kernel driver source (ignored if building writer only; necessary for RPM building)")