search for: spq

Hello, This patch fixes PR5382. The problem is that "bu_ls_rr_sort::operator()" and "td_ls_rr_sort::operator()" call getHeight() and getDepth() methods on SUnit, which can recompute values, what invalidates heap (SPQ). This patch guarantees that height and depth values won't be recomputed. The other solution would be to reheapify SPQ everytime when new SUnit is pop()ed, however I think it would be too expensive. Can anyone look at this? Thanks -Jakub -------------- next part -------------- A non-tex...

...ightToAtLeast(SU->getHeight() + PredEdge->getLatency()); but the latencies are considered only if the node as an ILP scheduling preference (the default in TargetLowering.h is None): bool LStall = (!checkPref || left->SchedulingPref == Sched::ILP) && BUHasStall(left, LHeight, SPQ); ... and the PPC backend does not override getSchedulingPreference. -Hal > > In addition, the stall computation is done using BUHasStall, and that > function only checks the current cycle. Without looking forward, I don't > understand how it could know how long the pipeline ha...

...tHeight() + PredEdge->getLatency()); > > but the latencies are considered only if the node as an ILP scheduling > preference (the default in TargetLowering.h is None): > bool LStall = (!checkPref || left->SchedulingPref == Sched::ILP) && > BUHasStall(left, LHeight, SPQ); > ... > > and the PPC backend does not override getSchedulingPreference. > Right, even with sched=hybrid, the scheduler will fall back to register pressure scheduling unless the target implements TargetLowering::getSchedulingPreference. I forgot that piece of the puzzle. You could...

On Mon, 2011-12-19 at 23:20 -0800, Andrew Trick wrote: > > On Dec 19, 2011, at 10:53 PM, Hal Finkel wrote: > > > Here's my "thought experiment" (from PR11589): I have a bunch of > > load-fadd-store chains to schedule. A store takes two cycles to > > clear > > its last pipeline stage. The fadd takes longer to compute its result > > (say 5

Dear Fusion Inventory fellows, I've been thinking about working on adding power devices knowledge to inventory systems for years. Following the last Ubuntu Developer Summit, I know have an "excuse" to do so: https://blueprints.launchpad.net/ubuntu/+spec/servercloud-p-cloud-power-management My below proposition is related to the above blueprint. So please keep in mind that the

...dp1dw62VZsEMULKYDn+Gljq8W4xJQ5YcDb6VrUs7FMIoBiYRw3StVMaLn5UZgFpN n7SLo2k9aEehLLWUIQvBaw61FGxbji+8IrtAWX1dCC8arruTJRgrNgt0kBKRaqdSsbSPa5xR Vz4ConwyPCJuEigoPHzFaXRyFgJuU5w4aS4DLph1eSQlixSvLHaccaudAJk1cax6n0mEPU1V n6Eli5xHfj23bj8OJDqvO5kPhEpyAwy4AMJRVKIHfQ8+CJhWEQ9OCIKqWb+RAncxLMcXqq0I B3sik4kwQISclHe+SpQ/aKiLD5xBLbmjlpK8 ----------eagybwsetvmfgusceufx--