similar to: No cpu throttling for Xeon E5405?

Hi, I've noticed that LLVM tends to generate suboptimal code and spill an excessive amount of registers in large functions, such as in those that are automatically generated by FFTW. LLVM generates good code for a function that computes an 8-point complex FFT, but from 16-point upwards, icc or gcc generates much better code. Here is an example of a sequence of instructions from a 32-point

Hello, Using kernel: 2.6.18-92.1.13.el5.centos.plus the cpu throttling works as desired (see 2 traces below) ------------- trace snips -------------- dmesg | grep -i pow ACPI: SSDT (v001 PTLTD POWERNOW 0x00000001 LTP 0x00000001) @ 0x3fff9b40 powernow-k8: Found 1 AMD Athlon(tm) 64 X2 Dual Core Processor 4600+ processors ( 2 cpu cores) (version 2.20.00) powernow-k8: 0 :

Hi, Yes, ldd is generating wrong tbss size. It is just considering one tbss section and not calculating all sections from all objects. The following example on x86_64 shows the issue: --- t0.c --- #include <stdio.h> extern __thread int t0; extern __thread int t1; extern __thread int t2; extern __thread int t3; __thread int t4; __thread int t5; __thread int t6; __thread int t7; int

It appears as cpuspeed is not running on my centos 5 box(s). One is a biostar motherboard Am2 6400+ the other is Asus am2 4800+. If I do "service cpuspeed stop" it says OK, If I do a "service cpuspeed start" is says OK. However at no time is cpuspeed running. /proc/cpuinfo only shows the cpu running at 1000 Mhz. If I manually run "cpuspeed -C & " I now have

Have you read http://llvm.org/docs/WritingAnLLVMBackend.html and http://llvm.org/docs/CodeGenerator.html ? http://llvm.org/docs/WritingAnLLVMBackend.html#instruction-selector describes how to define a store instruction. -Eli On 7/6/2017 6:51 PM, hameeza ahmed via llvm-dev wrote: > Please correct me i m stuck at this point. > > On Jul 6, 2017 5:18 PM, "hameeza ahmed"

We are using CentOS-4.3 (x86_64) with Opteron servers, and noticed a problem with cpuspeed: If we reboot by doing "# reboot" or similar from a shell, the boot will hang not long after cpuspeed starts. The machine freezes: ctrl-alt-del doesn't work, and only pressing the reset button or a power cycle will restart the machine. If we reboot from power-up or by pressing the reset

also i further run the following command; llc -debug filer-knl_o3.ll and its output is attached here. by looking at the output can we say that legalization runs fine and the error is due to instruction selection/ pattern matching which is not yet implemented? so do i need to worry and try to correct it at this stage or should i move forward to implement instruction selection/ pattern matching?

I have a desktop unit with a sempron 2500+ to play with. doing "more /proc/cpuinfo" indicates cpu Mhz as1044 not the 2500 I am familiar with cpuspeed. doing ps ax | grep cpuspeed resulting in nothing. I did service cpuspeed start. No errors reported. ps ax | grep cpuspeed resulted in nothing. I was going to do "killall -SIGUSR1 cpuspeed" to attempt to get 2500+ cpu speed. I

Change the assembly code to use only relative references of symbols for the kernel to be PIE compatible. Position Independent Executable (PIE) support will allow to extended the KASLR randomization range below the -2G memory limit. Signed-off-by: Thomas Garnier <thgarnie at google.com> --- arch/x86/crypto/aes-x86_64-asm_64.S | 45 ++++++++----- arch/x86/crypto/aesni-intel_asm.S

Hi all, I think I've spotted a few stupidities (bugs) in the current version of kernel-utils (kernel-utils-2.4-13.1.80). I'm sure these are all propagated from upstream, but I hope someone could have a quick look to verify this and see if we either can push complaints upwards, or provide local fixes. The kernel-utils package provides several 'kernel-type' functions -

Hi to the list, I am trying to find a way to painlessly move structured data back and forth between R and Matlab (also Octave). For this purpose I found the R.matlab package great help. I wish to use a Matlab -v6 MAT file as an intermediary format, because it is well read by both Matlab and Octave. It is also well read by 'readMat' function in R.matlab package, but that is where I run

On Fri, Jul 21, 2017 at 5:55 PM, Karol Herbst <karolherbst at gmail.com> wrote: > Signed-off-by: Karol Herbst <karolherbst at gmail.com> > --- > drm/nouveau/include/nvkm/subdev/clk.h | 2 ++ > drm/nouveau/nvkm/subdev/clk/base.c | 42 +++++++++++++++++++++++++++++++++++ > 2 files changed, 44 insertions(+) > > diff --git a/drm/nouveau/include/nvkm/subdev/clk.h

what is the correct way to set an AMD64 CPU into performance mode at boot time? I have tried doing service network cpuspeed start, then killall -SIGUSR1 cpuspeed and this works but I cant get it working this way at boot. I have set chkconfig cpuspeed on but that didnt seem to help. I just want this particular machine to boot in performance mode and stay there. Jerry

I come across a situation that I am having a hard time to understand. When I compile the following code : char *tst( char *dest, const char *src, unsigned int len ) { for (int i=0 ; i<len ; i++) { dest[i] = src[i]; } return dest; } Clang generates this for the ‘for’ body: for.body: ; preds = %for.cond %arrayidx = getelementptr inbounds i8,

On 2017-09-15 — 17:11, Karol Herbst wrote: > v2: use min_t > > Signed-off-by: Karol Herbst <karolherbst at gmail.com> > --- > drm/nouveau/include/nvkm/subdev/clk.h | 2 ++ > drm/nouveau/nvkm/subdev/clk/base.c | 42 +++++++++++++++++++++++++++++++++++ > 2 files changed, 44 insertions(+) > > diff --git a/drm/nouveau/include/nvkm/subdev/clk.h

Hi zfs-discuss, I have some questions about throttling on ZFS 1) I know that throttling is activating while one sync is waiting for another. (http://blogs.sun.com/roller/page/roch?entry=the_dynamics_of_zfs) Is it possible to throttle only selected processes (e.g. nfsd) ? 2) How can I obtain some statistics about it? I want to know how often throttling is activating on my host etc. 3) Is it

Hi, I am tracking some TLS issues with lld and found that it is generating wrong tbss size for case where multiple modules have non initialized threads variables. For instance: -- t0.c -- __thread int x0; __thread int x1; __thread int x2; extern __thread int e0; extern __thread int e1; extern __thread int e2; extern __thread int e3; int foo0 () { return x0; } int main () { return x0; }

After upgrade my laptop, I discovered a low performance on it. The laptop is a 2,73GHz Intel centrino and from some kernels versions to now, it had a good performance, the cpu scaling worked fine. Now, I discover that forcing in /etc/sysconfig/cpuspeed the governors and/or max/min speeds, it don't want to run more quickly. The laptop boots fine with the correct speed (usual speed), but when

Hey, folks, Sometimes my workstation bogs down... slows to a crawl. Using gkrellm, it's obvious the CPU is the laggard. The top utility confirms: the load average gets up over 4 at times. But this occurs when cpu stepping pegs the speed at 600MHz. This processor is capable of 1.5GHz and when it's allowed to run at that speed, the load average is under 2, which is fine. So the

I have a rather basic set of data. It is simply a variable that can be 0, 1 or 2 and its value over a series of time t0 - t9 like so: y: 1 1 2 0 1 2 2 1 2 1 x: t0 t1 t2 t3 t4 t5 t6 t7 t8 t9 I need to predict what the value of y will be at t10 through t13. As you can see its rather basic. I am rather new to solving these types of problems so I am looking for some good straight forward things