[GitHub] [incubator-tvm] tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT
tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#issuecomment-609895984 LGTM from my side, @liangfu let us also make sure we add the crt test to the CI. possibly by running some of the quick tests in the apps This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] [incubator-tvm] tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT
tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#issuecomment-607490917 ping @liangfu This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] [incubator-tvm] tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT
tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#issuecomment-606247382 @tmoreau89 please followup @liangfu please rebase against the master This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] [incubator-tvm] tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT
tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#issuecomment-604516628 OK, however, note that havinbg a arena based allocator will likely mean remove the vmalloc based versions(for simplicity reasons) This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] [incubator-tvm] tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT
tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#issuecomment-603312590 The workspace memory could have a different strategy. The way it works is that we create a different arena for workspace, along with a counter. - When a memory is allocated, we allocate memory from the arena, and add the counter - When a memory is de-allocated, we decrease the counter - When the counter goes to zero, we free all the memory. This will work because all workspace memory are temporal This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] [incubator-tvm] tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT
tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#issuecomment-602952533 I wonder if VMem allocator is a bit overkill for cases like micro controller. If we have a constant memory usage and do not do frequent alloc and free, perhaps we will be good by use an arena style allocator(which just allocs but do not free) and frees everything once we are done with the task. It would be nice to do a quick benchmark of the vmemory allocator vs alternatives(in terms of binary size and efficiency) This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] [incubator-tvm] tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT
tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#issuecomment-602682420 cc @tmoreau89 @ajtulloch @ZihengJiang @weberlo please help to take a look This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services