diff --git a/src/singeli/src/accumulator.singeli b/src/singeli/src/accumulator.singeli index 5351334c..3a9dce3d 100644 --- a/src/singeli/src/accumulator.singeli +++ b/src/singeli/src/accumulator.singeli @@ -140,7 +140,7 @@ def sum_accumulator{DE, unr, VT=[_]SE if int_els{DE,SE} and DE>SE and hasarch{'A -# x86_64-specific accumulators; TODO: AVX-512 could use dpbusd/dpwssd +# x86_64-specific accumulators; TODO: AVX-512 could use dpbusd/dpwssd, though with the higher latency that should be behind a high unroll amount def sum_accumulator{DE, unr, VT=[k]SE if int_els{DE,SE} and width{SE}==8 and hasarch{'X86_64'}} = { def VM = [k/8]u64 def VU = [k]u8