I've started doing the detailed analysis on memory timing for Eth mining.

With tRRD=6, tRC=62, tCL=21 and 2000 mem clock, I can get almost 27Mh/s mining eth.  Each hash takes 64 random DAG reads of 128 bytes each, and since they are random, each read should be from a different page.  As well, the L2 cache hit rate should be near 0, so each DAG access requires a read from GDDR (2x32-byte reads from 2 GDDR chips).

Before reading, a page (row) has to be activated(opened), so 27Mh * 64 activate = 1728M activates per second.  The Rx470/480 has 4 independent cache controllers, so a single GDDR5 chip will open 432M pages per second.  With a 2Ghz mem clock, that's about 5 (4.73) clocks per activate.  The closer that gets to 4, the better.  Lower than 4 is not possible with Eth mining, since it takes 4 clocks to transfer 64 bytes (half a DAG entry).  Note that if tRRD=6, means 6 clocks, some other timing factor is allowing the RAM to sustain <5 clocks per activate

I tried tRRD=5, and it only makes a small (~1%) improvement.  That makes sense, since RRD is the delay between 2 activate commands when they are going to different banks.  With only 16 banks, the memory controller has lots of opportunity to batch activate commands together in the same bank.  However tRC is defined as, "The minimum time interval between two successive ACTIVE commands on the same bank".  With tRC=62, the fastest access pattern would be to spread the accesses across different banks rather than batching them in the same bank.

So it seems I'm missing something about how the RAM timing.  I know there are multiple clocks for GDDR5, and some run at double data rate (i.e. WCK).  If tRRD=6 means six DDR address clocks, that would be 3 SDR command clocks (2Ghz is the command clock rate).

Keep in mind that there is huge diff linux/windows and amdgpu-pro <16.60, I've wrote u on zawawa's thread to update kernel to 4.10/4.11 and install only amdgpu-pro 16.60 ocl packages and their deps. Hashrate will increase +1.2MH guaranteed.

Keep in mind that there is huge diff linux/windows and amdgpu-pro <16.60, I've wrote u on zawawa's thread to update kernel to 4.10/4.11 and install only amdgpu-pro 16.60 ocl packages and their deps. Hashrate will increase +1.2MH guaranteed. Also ras/cas timings must be equally calculated for better stability. MC_SEQ_MISC_TIMING contains tRP value which combined with tCL equals tRAS. By raising memory above 2000 you should increase refresh rate and keep read/write operations at the same level or close. ARB_DRAM timings can improve stability on driver level also. If u get 29MH on 2000 it means your timings are too tight and won't be as stable as you think.

Great minds think alike  

Sometimes loosening the timings is better, and clocking higher - specifically on Eth.

"If u get 29MH on 2000 it means your timings are too tight and won't be as stable"