aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2015-03-24Don't assume PRV1/2 and IE1/2 are resetAndrew Waterman2-6/+6
2015-03-21Merge rv64si and rv32si testsAndrew Waterman14-286/+324
2015-03-20Add fdiv testAndrew Waterman3-5/+48
2015-03-17need fence before scall for vector mmYunsup Lee1-0/+2
2015-03-17push envYunsup Lee1-5/+5
2015-03-17relay hwacha cause/aux to scause/sbadaddrYunsup Lee11-24/+24
2015-03-17Merge [shm]call into ecall, [shm]ret into eretAndrew Waterman6-11/+11
2015-03-16revamp vector tests with new privileged spec, and add scalar pt testsYunsup Lee19-165/+61
2015-03-14Add PTE dirty bit testAndrew Waterman3-5/+90
2015-03-12Use hcall instead of mcallAndrew Waterman1-5/+5
2015-03-12Update to new privileged specAndrew Waterman24-229/+174
2015-02-23Added more +/- NaN/inf tests for fcvt.{w/l/wu/lu}.{s/d}Christopher Celio1-8/+43
2015-02-22Added -NaN test for fcvt.{w/h}.sChristopher Celio1-0/+19
2015-02-19Unify rv32/rv64 timer testsAndrew Waterman2-43/+10
2015-02-17change organization to riscvYunsup Lee1-1/+1
2015-02-15Make rv64uf-p-ldst test the sign bit, tooAndrew Waterman1-4/+10
2015-02-07Change submodule pointers to github.com/riscvPalmer Dabbelt1-1/+1
This new organization is designed to make it easier for external collaborators to contribute.
2015-01-27Fix matmul performance on gcc 4.9Andrew Waterman2-96/+96
It's just loop interchange in the register blocking loop.
2015-01-09Add LICENSEAndrew Waterman323-5/+671
2015-01-04Avoid deprecated "b" pseudo-op; use "j" insteadAndrew Waterman6-16/+16
2015-01-02On misaligned fetch, EPC = branch target, not sourceAndrew Waterman1-5/+8
We can revert this commit if we decide to change the EPC behavior.
2014-12-17minor mt updatesHenry Cook2-2/+7
2014-12-15Remove dependence on machine/syscall.hAndrew Waterman1-1/+2
2014-12-13Initialize static TLS for the benchmarksAndrew Waterman3-12/+33
2014-12-12Add more entropy to matrix multiplication inputAndrew Waterman2-5/+15
This will exercise the floating-point units more thoroughly.
2014-12-12Use user stack in supervisor modeAndrew Waterman1-14/+1
This fixes a race condition, as there was only one kernel stack.
2014-12-03Use new toolchain and calling conventionAndrew Waterman9-49/+40
2014-12-03Rely on assembler to relax far branchesAndrew Waterman1-12/+3
2014-12-03Make timer test more thoroughAndrew Waterman1-12/+1043
2014-11-22push envYunsup Lee1-5/+9
2014-11-22relax rv32si timer test a bitYunsup Lee1-1/+2
2014-11-13remove zscale specific testsYunsup Lee4-192/+0
2014-11-13enable make subsetsYunsup Lee1-7/+16
2014-11-13make rv32si fault load/store test strongerYunsup Lee1-1/+5
2014-11-12beef up rv32si testsYunsup Lee11-0/+547
2014-11-11blocked mt-matmulHenry Cook1-8/+6
2014-11-07forgot barrier in mt-matmulHenry Cook1-0/+2
2014-11-07Clean up canonical mt benchmarks and reorganize extra versions in /mt. All ↵Henry Cook326-57593/+3390
versions support support at least 1/2/4 threads.
2014-11-06Fix build with riscv-gcc version 4.9Andrew Waterman5-10/+9
2014-11-06Don't access memory outside of the binary's rangeAndrew Waterman26-1/+27
2014-11-06Fix TLS in benchmarksAndrew Waterman1-0/+3
Linker relaxations were screwing up loading the thread pointer.
2014-10-24push envYunsup Lee1-5/+8
2014-09-24Updated mt testsHenry Cook119-1486/+1483
2014-09-10Enable interrupts in bmarksChristopher Celio1-6/+5
2014-08-28Added "simple" test to rv32ui.Christopher Celio2-0/+26
2014-08-06updatesYunsup Lee1-1/+1
2014-08-06update readmeYunsup Lee1-1/+156
2014-08-06update readmeYunsup Lee1-1/+4
2014-08-05cleanup README.md for webSagar Karandikar1-3/+6
2014-07-30prep-for-public: change to https ref for envSagar Karandikar1-1/+1