- 4cfea4f by sewardj · 18 years ago
- 4eee476 by sewardj · 18 years ago
- ae0e07b Expand the first para of the custom-allocator section so it says what by sewardj · 18 years ago
- af92f45 Regression tests for Graydon Hoare's enhanced mempool stuff, from by sewardj · 18 years ago
- c740d76 A memory pool update from Graydon Hoare. by sewardj · 18 years ago
- ce10c26 Excellent documentation from Graydon Hoare on his mempool client-request work. by sewardj · 18 years ago
- ba7b458 Add a comment about marking static memory as defined. by njn · 18 years ago
- 7982056 Merge (from 3_2_BRANCH) r6048 (SuSE 10.1 (ppc32) minor fixes) by sewardj · 18 years ago
- 7fd62e9 Add a regtest for #133694 (munmapping of segments below by sewardj · 18 years ago
- 8aeeaa9 A small fix to the "mempool trim" client request; the previous version by sewardj · 18 years ago
- ef68c5b Regression test for #132146. by sewardj · 18 years ago
- d874687 Update expected output following Graydon H's leak checker fixes. by sewardj · 18 years ago
- 5bee4f8 Followup to r5991: when leak checking, treat zero-sized blocks as if by sewardj · 18 years ago
- 2c1c9df Add a mempool-trimming client request (Graydon Hoare). by sewardj · 18 years ago
- 3cf26a5 Leak checking fixes from Graydon Hoare: by sewardj · 18 years ago
- de3ad73 When doing leak checks, don't poke around in device segments as this by sewardj · 18 years ago
- 3f5f556 Fix copy-n-paste error to do with ppc64-linux stack redzone handling by sewardj · 18 years ago
- e4b0bf0 Update copyright dates. by sewardj · 18 years ago
- 3024d03 Sigh .. now fix for 32-bit targets. by sewardj · 18 years ago
- 3cbed8c Fix gcc pedantry on 64-bit platforms by sewardj · 18 years ago
- a7bd8cc Update expected output. by sewardj · 18 years ago
- 1cf56cf Assertion is too restrictive; it's possible to validly get an by sewardj · 18 years ago
- 183375a A 1 page stack isn't big enough for this test on ppc32-linux. by sewardj · 18 years ago
- 42a32a2 Update expected output following vex r1619. by sewardj · 18 years ago
- 49ceddc Yet more messing with masking approximate results. by sewardj · 19 years ago
- 7f1f7a8 Apparently Intel's rcpps etc approximations are more approximate than by sewardj · 19 years ago
- 5b0acb0 Update expected results following change in r5898. by sewardj · 19 years ago
- 2de0441 Add masking for results of rcpps/rcpss/rsqrtps/rsqrtps so as to give by sewardj · 19 years ago
- dbdb36f Comprehensive tests for bt{s,r,c,}{w,l,q} on amd64. by sewardj · 19 years ago
- 1636922 Test x86 {push,pop}{w,l}. by sewardj · 19 years ago
- f218491 Vectorise copy_address_range_perms for common cases. This gives about by sewardj · 19 years ago
- e26e42f Add another test of permissions range copying (copy_address_range_perms). by sewardj · 19 years ago
- e5b662b Get rid of executable permissions on C source file. by sewardj · 19 years ago
- ca54af3 by njn · 19 years ago
- 5bac8e5 On x86, don't use x87 registers for 8-byte FP loads/stores; instead by sewardj · 19 years ago
- 36c11e9 Commit a patch from Olly Betts which avoids a possible problem with by njn · 19 years ago
- 4cf530b Use better variable names. by njn · 19 years ago
- fc3b5ba Test program which uses templates to generate very long stabs (debug by sewardj · 19 years ago
- e250412 Un-break make dist. by sewardj · 19 years ago
- bca134f Add 64-bit test output. by sewardj · 19 years ago
- 3dfd9f0 Don't print an address on stdout as it doesn't get automagically by sewardj · 19 years ago
- dc6734b Another shadow memory test. This one does a huge number of loads and by sewardj · 19 years ago
- 2229db0 In check_all, allow two different acceptable byte values, so as to by sewardj · 19 years ago
- b2963ad Partial fix for the sh-mem.c failure on PPC32. This should make it work by njn · 19 years ago
- 7fd15d6 Make the BSD-style license notices slightly more accurate. by njn · 19 years ago
- dbf7ca7 by njn · 19 years ago
- a7c7ebd Change to some better function names. by njn · 19 years ago
- 45e8125 Change some uses of bytes to bits for consistency. by njn · 19 years ago
- 1d0825f Merge in the COMPVBITS branch to the trunk. This is a big change to by njn · 19 years ago
- eb662fa Update expected output following r5785; also add a missing 's'. by sewardj · 19 years ago
- a895e4e Mess with this even more so that fn_1 doesn't return zero. by sewardj · 19 years ago
- e638a8d Updated expected output following r5753. by sewardj · 19 years ago
- b70b96a TRASH_IREGS: add enough live variables to make ppc32 spill (not easy) by sewardj · 19 years ago
- f4f22d5 Majorly beef up this test: by sewardj · 19 years ago
- 0928fed Fix comment typo. by sewardj · 19 years ago
- fb1e9ad Add a new kind of memory-painting primitive, which is: 'make_defined'. by sewardj · 19 years ago
- 1c85d5c Oops, missed out of r5724. by sewardj · 19 years ago
- ae43d04 Regression test for memcheck's SET/GET_VBITS client requests. by sewardj · 19 years ago
- c2c12c2 Reinstate the SET/GET_VBITS client requests. by sewardj · 19 years ago
- 7d647cb get_abit_and_vbyte/get_abit can be a significant bottleneck when by sewardj · 19 years ago
- 776de2c Apparently on SLES9 the dynamic linker is called (soname'd) ld64.so.1. by sewardj · 19 years ago
- f5c8e37 Extend stack-permissions-change fast-case machinery to handle +/- 112, by sewardj · 19 years ago
- 39eb667 Fix minor anomaly pointed out by icc9. by sewardj · 19 years ago
- 453e8f8 Get rid of general case in mkLazy3 and instead add new cases as they appear. by sewardj · 19 years ago
- e91cea7 Track vex r1573 (introduction of 4-arg IR primops for ppc fmadd/fmsub). by sewardj · 19 years ago
- b0e1ccc This causes problems on setups where ld.so is mapped at just over 1M: by sewardj · 19 years ago
- c7e8c74 Test program aimed at exercising x87 insns a bit on amd64. by sewardj · 19 years ago
- bee2c28 Add a check for fsincos. by sewardj · 19 years ago
- 672f778 Yet more x86 instruction tests, mostly aimed at wierd/transcendental x87 insns. by sewardj · 19 years ago
- d6075eb Tidy up a couple more x86-related primops following rounding changes. by sewardj · 19 years ago
- 22ac5f4 Followup to r5605: fixes for x86 by sewardj · 19 years ago
- ed69fdb by sewardj · 19 years ago
- 9af10a1 Change the number of client request args from 4 to 5 as that may by sewardj · 19 years ago
- 4f3e0f2 Track vex r1553 (addition of Iop_Est8FRecip, case Iop_Est5FRSqrt) by sewardj · 19 years ago
- 02fd0d7 Test program to check the behaviour of a bunch of FP functions. by sewardj · 19 years ago
- 48e7bc4 Use perf/fbench as a simple FP test too. This is a modified copy, not a symlink. by sewardj · 19 years ago
- 46712cd Use the bz2 test in perf/ as a regression-test, just as a moderately by sewardj · 19 years ago
- 5a6d7e4 Wibble by sewardj · 19 years ago
- c885844 Make amd64 function wrapping work again following recent changes. by sewardj · 19 years ago
- d68ac3e Changes to make function wrapping work better on ppc64-linux: by sewardj · 19 years ago
- 134d1aa More function wrapping tests. by sewardj · 19 years ago
- 7d5c209 Track line number changes. by sewardj · 19 years ago
- 80d9eac More __libc_start_main -> "(below_main)" changes. by sewardj · 19 years ago
- 2da8f33 Update with new expected outputs. by sewardj · 19 years ago
- 9e9864c Suppressions-tests fixes. by sewardj · 19 years ago
- 4658b35 Fixes to track the "(below main)" change. by sewardj · 19 years ago
- 5a3f36f Don't try sys_sigprocmask on ppc64-linux. by sewardj · 19 years ago
- 81c145a getcontext() seems to be unimplemented on glibc-2.3.3 on ppc64-linux. by sewardj · 19 years ago
- a151c39 Clever handling of partially defined equality does not work on by sewardj · 19 years ago
- 714cbe0 This was segfaulting on ppc64-linux, even natively. These changes by sewardj · 19 years ago
- 26fd33d Make a bit less nonsensical on 64-bit platforms. by sewardj · 19 years ago
- e21a858 To reduce the endless nuisance of multiple different names for "the by sewardj · 19 years ago
- 9085f7e Make these behave correctly on ppc64 ELF. by sewardj · 19 years ago
- 2e1a677 Valgrind-side handling (fast case) for the ppc64 ELF stack redzone. by sewardj · 19 years ago
- 461df9c These files all speak about instrumentation functions. by sewardj · 19 years ago
- 62eae5f Increase size of the largest guest state handled. by sewardj · 19 years ago
- 0ec07f3 Merge in function wrapping support from the FNWRAP branch. That by sewardj · 19 years ago
- 6792df3 Make this test 64-bit clean. by sewardj · 19 years ago
- 7894793 Fix a casting bug in the LOADV8 slow (misaligned) case spotted by Nick. by sewardj · 19 years ago
- 48540da Build fix for oset_test following recent build system hackery. by sewardj · 19 years ago