Page history
4 November 2013
3 September 2013
25 June 2013
20 June 2013
→The hopefully interesting parts
+146
→The hopefully interesting parts
+2
→Timing differences in equality comparisons
+971
→The hopefully interesting parts
−1,210
→Some CPUs have surprising timing differences on 64-bit integer arithmetic using 32-bit integer arithmetic instructions, when DAZ is enabled
→The hopefully interesting parts
+1,886
→A significant mass of SSE2-capable CPUs do not have DAZ
+104
→A significant mass of SSE2-capable CPUs do not have DAZ
+74
→Some Intel CPUs have slow multiplications with NaN values, even with SSE2 instructions
+447
8 June 2013
7 June 2013
6 June 2013
→Some recent AMD CPUs have abnormally fast comparisons with NaN, even with SSE2 instructions
−7
→Some Intel CPUs have abnormally slow comparisons with NaN and denormals, even with SSE2, DAZ and FTZ
+2
→The hopefully interesting parts
+741
3 June 2013
→Running the code
+133
→x87 is highly non-constant-time
+14
→Some recent AMD CPUs have slow float comparisons with NaN values, even with SSE2 instructions
+141
no edit summary
+6,913
Created page with "This page is about which scalar floating-point arithmetic instructions fail to execute in constant time (independently of their operands) on various CPUs. We also study some m..."
+2,348