diff --git a/src/Futhark/CodeGen/ImpGen/GPU/SegScan/SinglePass.hs b/src/Futhark/CodeGen/ImpGen/GPU/SegScan/SinglePass.hs index 4dbe3fb56f..b1473cb15e 100644 --- a/src/Futhark/CodeGen/ImpGen/GPU/SegScan/SinglePass.hs +++ b/src/Futhark/CodeGen/ImpGen/GPU/SegScan/SinglePass.hs @@ -359,7 +359,7 @@ compileSegScan pat lvl space scanOp kbody = do sFor "i" m $ \i -> do sharedIdx <- dPrimV "sharedIdx" $ kernelLocalThreadId constants * m + i copyDWIMFix priv [sExt64 i] (Var trans) [sExt64 $ tvExp sharedIdx] - sOp localBarrier + sOp $ Imp.ErrorSync Imp.FenceLocal sComment "Per thread scan" $ do -- We don't need to touch the first element, so only m-1