Enrico Deiana
Enrico Deiana
Simple record_filter_t::record_filter_func_t filter that modifies a field of every trace_entry_t record in a trace and leverages record_filter to output such modified records onto a "filtered" output trace. Issue: #6662
We want to create a new tool to filter traces of Google workloads for public release. The new public Google workload traces will contain more information compared to the previous...
When running record_filter without any filter, the resulting trace file has some trace_entry_t records flipped, while we expect them to be the same. Specifically, TRACE_TYPE_ENCODING and TRACE_TYPE_MARKER.TRACE_MARKER_TYPE_BRANCH_TARGET are flipped in...
A sequence of `trace_entry_t` records is what we use for on-disk representation of traces. To keep traces compact, the fields in the `trace_entry_t` struct are overloaded (i.e., they mean different...
Traces on disk are a sequence of 12 byte entries of type #trace_entry_t. Currently we visualize such traces in binary form as described here: https://dynamorio.org/page_debug_memtrace.html#autotoc_md136. We want to implement a...
Currently we don't have a way to iterate over the register operands of an instr_t directly. To do so, we have to: 1) obtain the number of src (`instr_num_srcs()`) and...
Modifies the view tool to handle OFFLINE_FILE_TYPE_ARCH_REGDEPS traces. Specifically, when we disassemble DR_ISA_REGDEPS instructions, we print the instruction encoding (can span multiple lines), we substitute the opcode with the categories,...
Fixes a data race due to multiple dr_standalone_init() done in parallel (per shard) by encodings2regdeps_filter_t. dcontext is now initialized one time by record_filter_t and passed to its filters through the...
`analysis_tool_tmpl_t` deprecated the use of `initialize()` and `parallel_shard_init()` in favor of `initialize_stream()` and `parallel_shard_init_stream()` respectively. These two methods allow initializations for the analysis tool as a whole (rather than doing...
Hi everyone, when I try to compile DCA (in my case on Summit, at ORNL) with DCA_WITH_SINGLE_PRECISION_MC=ON I get the attached errors. [error_float.txt](https://github.com/CompFUSE/DCA/files/5690227/error_float.txt) If DCA_WITH_SINGLE_PRECISION_MC=OFF, DCA compiles successfully. Please let...