Memory problems revisited.

Alex Buell (alex.buell@tahallah.demon.co.uk)
Sat, 20 Nov 1999 14:02:52 +0000 (GMT)


I've set the machine back to the slowest possible settings and I'm still
getting errors with the memory testing program.

However, I've just noticed that all the locations in memory where the
errors occurs always ends in '37'. I'm wondering whether these are
significant. The locations seems to be at different places each time, and
sometimes subsequent runs don't show up the errors.

Run 1:
Test 1: Random value: Setting...Testing...Passed.
Test 2: XOR comparison: Setting...Testing...Passed.
Test 3: SUB comparison: Setting...Testing...
FAILURE: 0x5aa0f5c5 != 0x5aa0f585 at offset 0x0067f837.
Skipping to next test...
Test 4: MUL comparison: Setting...Testing...
FAILURE: 0x574ee9e8 != 0x574ee9a8 at offset 0x005dc037.
Skipping to next test...
Test 5: DIV comparison: Setting...Testing...
FAILURE: 0x00000000 != 0x00000001 at offset 0x0067f837.
Skipping to next test...
Test 6: OR comparison: Setting...Testing...
FAILURE: 0x5dfdd684 != 0x5dfdd685 at offset 0x0067f837.
Skipping to next test...
Test 7: AND comparison: Setting...Testing...
FAILURE: 0x49edc280 != 0x49edc281 at offset 0x0067f837.
Skipping to next test...
Test 8: Sequential Increment: Setting...Testing...
FAILURE: 0xf6877f01 != 0xf6877f41 at offset 0x0014f837.
Skipping to next test...
Test 9: Block Sequential: Testing... 64
FAILURE: 0x40404000 != 0x40404040 at offset 0x0014fc37.
Skipping to next test...
Passed.
Test 10: Solid Ones: Setting...Testing...Passed.
Test 11: Solid Zeroes: Setting...Testing...Passed.
Test 12: Checkerboard1: Setting...Testing...Passed.
Test 13: Checkerboard2: Setting...Testing...
FAILURE: 0x55555515 != 0x55555555 at offset 0x0014f837.

I'm beginning to wonder whether it's the motherboard or the processors
themselves. This machine has never been overclocked or had the bus speed
overclocked.

Cheers,
Alex

-- 

Legalise cannabis today! Got GnuPG? Ask me for public key.

http://www.tahallah.demon.co.uk - updated!

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/