search for: dowork

...torizer. Problem Statement ================= Currently, if a loop calls a user-defined function or a 3rd party library function, the loop can't be vectorized unless the function is inlined. In the example below the LoopVectorizer fails to vectorize the k loop due to its function call to "dowork" because "dowork" is an external function. Note that inlining the "dowork" function may result in vectorization for some of the cases, but that is not a generally applicable solution. Also, there may be reasons why compiler may not (or can't) inline the "dowork&quo...

...nse to start from here? Yes, we can vectorize this loop by calling scalar code VL times as an emulation of SIMD execution if the SIMD version does not exist to start with. See below example, we need this functionality anyway as a fall back for vecotizing this loop when there is no SIMD version of dowork exist. E.g. #pragma clang loop vectorize(enable) for (k = 0; k < 4096; k++) { a[k] = k * 0.5; a[k] = dowork(a, k); } ==> Vectorized_for (k = 0; k < 4096; k+=VL) { // assume VL = 4. No vector version of dowork function exist. a[k:VL] = {k, k+1, K+2, k+3) * 0.5.;...

...18b902ae 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -2079,18 +2079,40 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, { struct drm_dp_mst_topology_mgr *mgr = mstb->mgr; struct drm_dp_mst_port *port; - int old_ddps; - bool dowork = false; + int old_ddps, ret; + u8 new_pdt; + bool dowork = false, create_connector = false; port = drm_dp_get_port(mstb, conn_stat->port_number); if (!port) return; - /* Locking is only needed if the port's exposed to userspace */ - if (port->connector) + if (port->connecto...

...nn_stat(struct drm_dp_mst_branch *mstb, struct drm_dp_connection_status_notify *conn_stat) { - struct drm_device *dev = mstb->mgr->dev; + struct drm_dp_mst_topology_mgr *mgr = mstb->mgr; + struct drm_device *dev = mgr->dev; struct drm_dp_mst_port *port; - int old_ddps; - bool dowork = false; + struct drm_connector *connector_to_destroy = NULL; + int old_ddps, ret; + u8 new_pdt; + bool dowork = false, create_connector = false; port = drm_dp_get_port(mstb, conn_stat->port_number); if (!port) return; + mutex_lock(&port->lock); drm_modeset_lock(&dev->...

...> + /// Run the coalescer on this function, providing interference > + /// data to query. Return whether we removed any copies. > + virtual bool coalesceFunction(MachineFunction &mf, > InterferenceData &ifd) = 0; > > 80 col violation. Ok. > 6. > + /// doWork - The main coalescing algorithm. Return whether any > + /// copies were coalesced. > + bool doWork(MachineFunction &mf); > > Please rename it to something like performCoalescing. Also, is this > defined anywhere? It's just what runOnMachineFunction used to be. I spli...

...ceData out from RegisterCoalescer.h? 5. + /// Run the coalescer on this function, providing interference + /// data to query. Return whether we removed any copies. + virtual bool coalesceFunction(MachineFunction &mf, InterferenceData &ifd) = 0; 80 col violation. 6. + /// doWork - The main coalescing algorithm. Return whether any + /// copies were coalesced. + bool doWork(MachineFunction &mf); Please rename it to something like performCoalescing. Also, is this defined anywhere? 7. About class LinearScanInterferenceData. Since it's just an example, per...

Here's a proposed patch for reworking register coalescing to allow pluggable coalescers. I think I've got the interfaces where I want them and am reasonably sure I've squashed most of the bugs. I'm still doing some testing and want to get through a whole regimen before committing. As a reminder, this patch has several goals: - Allow user-specified register coalescers, similar

...function, providing interference >> + /// data to query. Return whether we removed any copies. >> + virtual bool coalesceFunction(MachineFunction &mf, >> InterferenceData &ifd) = 0; >> >> 80 col violation. > > Ok. > >> 6. >> + /// doWork - The main coalescing algorithm. Return whether any >> + /// copies were coalesced. >> + bool doWork(MachineFunction &mf); >> >> Please rename it to something like performCoalescing. Also, is this >> defined anywhere? > > It's just what runOnMachin...

> On Mar 2, 2016, at 1:33 AM, Renato Golin <renato.golin at linaro.org> wrote: > > On 2 March 2016 at 01:14, John McCall via llvm-dev > <llvm-dev at lists.llvm.org> wrote: >> Hi, all. >> - We sometimes want to return more values in registers than the convention normally does, and we want to be able to use both integer and floating-point registers. For

...ence */ > + drm_dp_mst_topology_put_port(port); > } > > static void drm_dp_update_port(struct drm_dp_mst_branch *mstb, > struct drm_dp_connection_status_notify *conn_stat) > { > struct drm_dp_mst_port *port; > - int old_pdt; > int old_ddps; > bool dowork = false; > + > port = drm_dp_get_port(mstb, conn_stat->port_number); > if (!port) > return; > > old_ddps = port->ddps; > - old_pdt = port->pdt; > - port->pdt = conn_stat->peer_device_type; > port->mcs = conn_stat->message_capability_statu...

...d now drop our reference */ + drm_dp_mst_topology_put_port(port); } static void @@ -1987,16 +2016,14 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, struct drm_dp_connection_status_notify *conn_stat) { struct drm_dp_mst_port *port; - int old_pdt; int old_ddps; bool dowork = false; + port = drm_dp_get_port(mstb, conn_stat->port_number); if (!port) return; old_ddps = port->ddps; - old_pdt = port->pdt; - port->pdt = conn_stat->peer_device_type; port->mcs = conn_stat->message_capability_status; port->ldps = conn_stat->legacy_dev...

...pology_put_port(port); + /* And now drop our reference */ + drm_dp_mst_topology_put_port(port); } static void drm_dp_update_port(struct drm_dp_mst_branch *mstb, struct drm_dp_connection_status_notify *conn_stat) { struct drm_dp_mst_port *port; - int old_pdt; int old_ddps; bool dowork = false; + port = drm_dp_get_port(mstb, conn_stat->port_number); if (!port) return; old_ddps = port->ddps; - old_pdt = port->pdt; - port->pdt = conn_stat->peer_device_type; port->mcs = conn_stat->message_capability_status; port->ldps = conn_stat->legacy_dev...

...> } > > > > static void drm_dp_update_port(struct drm_dp_mst_branch *mstb, > > struct drm_dp_connection_status_notify > > *conn_stat) > > { > > struct drm_dp_mst_port *port; > > - int old_pdt; > > int old_ddps; > > bool dowork = false; > > + > > port = drm_dp_get_port(mstb, conn_stat->port_number); > > if (!port) > > return; > > > > old_ddps = port->ddps; > > - old_pdt = port->pdt; > > - port->pdt = conn_stat->peer_device_type; > > port-&gt...

...tVector JoinedLIs; + /// didWork - Tell whether we have run on this function already. + /// This allows the coalescer to either run independently or from + /// within a register allocator. + typedef std::map<const MachineFunction *, bool> WorkMap; + WorkMap didWork; + void doWork(MachineFunction &mf); + public: static char ID; // Pass identifcation, replacement for typeid SimpleRegisterCoalescing() : MachineFunctionPass((intptr_t)&ID) {}; + const char *getPassName() const{ + return "Simple Register Coalescing"; + }; + + /// All...

On Jul 11, 2007, at 11:39 AM, David Greene wrote: > On Wednesday 11 July 2007 12:41, Tanya M. Lattner wrote: > >> I think the coalescer should be flexible enough to be run >> independent of >> the register allocator. For example, you may want to expose the >> copies >> induced by transforming out of SSA to the scheduler. If the >> scheduler is

...when implementing, I believe it is best to follow the name mangling proposed in Xinmin's RFC. What do you think? GCC Example ---------------- Compiler version: GCC 6.1.0 Compile line: gcc -c omp.c -fopenmp -Wall -S -o - -O3 > omp.s omp.c #include <omp.h> #pragma omp declare simd int dowork(int* a, int idx) { return a[idx] * a[idx]*7; } less omp.s | grep @function .type dowork, @function .type _ZGVbN4vv_dowork, @function .type _ZGVbM4vv_dowork, @function .type _ZGVcN4vv_dowork, @function .type _ZGVcM4vv_dowork, @function .typ...

...w the name mangling proposed >in Xinmin's RFC. What do you think? > >GCC Example >---------------- >Compiler version: GCC 6.1.0 >Compile line: gcc -c omp.c -fopenmp -Wall -S -o - -O3 > omp.s > >omp.c >#include <omp.h> > >#pragma omp declare simd >int dowork(int* a, int idx) >{ > return a[idx] * a[idx]*7; >} > >less omp.s | grep @function > .type dowork, @function > .type _ZGVbN4vv_dowork, @function > .type _ZGVbM4vv_dowork, @function > .type _ZGVcN4vv_dowork, @function > .type...

...gt; @@ -2022,6 +2078,7 @@ static void > drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, > struct drm_dp_connection_status_notify *conn_stat) > { > + struct drm_device *dev = mstb->mgr->dev; > struct drm_dp_mst_port *port; > int old_ddps; > bool dowork = false; > @@ -2030,6 +2087,8 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, > if (!port) > return; > > + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); > + > old_ddps = port->ddps; > port->mcs = conn_stat->message_capa...

This is the final portion of the large series for adding MST suspend/resume reprobing that I've been working on for quite a while now. In addition, I: * Refactored and cleaned up any code I ended up digging through in the process of understanding how some parts of these helpers worked. * Added some debugging tools along the way that I ended up needing to figure out some issues in my own

...lock); list_del(&port->next); @@ -2022,6 +2078,7 @@ static void drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, struct drm_dp_connection_status_notify *conn_stat) { + struct drm_device *dev = mstb->mgr->dev; struct drm_dp_mst_port *port; int old_ddps; bool dowork = false; @@ -2030,6 +2087,8 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb, if (!port) return; + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); + old_ddps = port->ddps; port->mcs = conn_stat->message_capability_status; port->ldps = conn_st...