similar to: [LLVMdev] Poor register allocation (constants causing spilling)

On Jan 9, 2012, at 10:00 AM, Jakob Stoklund Olesen wrote: > > On Jan 8, 2012, at 11:18 PM, Demikhovsky, Elena wrote: > >> I'll explain what we see in the code. >> 1. The caller saves XMM registers across the call if needed (according to DEFS definition). >> YMMs are not in the set, so caller does not take care. > > This is not how the register allocator

Hi LLVMers, I have finally sorted out licensing issues and found some time, so I'm trying to port my PBQP register allocator to 2.4 in order to contribute it (if you want it). I've run into a bug that has me confused though. I'm currently failing the following assertion: llc: VirtRegMap.cpp:1733: void<unnamed>::LocalSpiller::RewriteMBB(llvm::MachineBasicBlock&,

Dear LLVMdev, I've noticed an unusual behavior of the LLVM x86 code generator (with default options) that results in nearly a 4x slow-down in floating-point throughput for my microbenchmark. I've written a compute-intensive microbenchmark to approach theoretical peak throughput of the target processor by issuing a large number of independent floating-point multiplies. The distance

On Sep 3, 2008, at 5:58 AM, Lang Hames wrote: > Hi LLVMers, > > I have finally sorted out licensing issues and found some time, so I'm > trying to port my PBQP register allocator to 2.4 in order to Nice! We would definitely welcome your contribution. > > contribute it (if you want it). I've run into a bug that has me > confused though. > > I'm currently

On 20.10.2010 05:00, Jakob Stoklund Olesen wrote: > On Oct 19, 2010, at 6:37 PM, Roland Scheidegger wrote: > >> Thanks for giving it a look! >> >> On 19.10.2010 23:21, Jakob Stoklund Olesen wrote: >>> On Oct 19, 2010, at 11:40 AM, Roland Scheidegger wrote: >>> >>>> So I saw that the code is doing lots of register >>>>

Hi again, Now, after I fixed the graph coloring regalloc bug that was triggered by the ARM target, I continue testing and found another bug, this time on the XCore target. First I thought that it is again specific to my register allocator, but it seems to be trigerred also by LLVM's linearscan register allocator. I don't know if the XCore target is stable enough in LLVM, or may be I

This is the wrong code: declare <16 x float> @foo(<16 x float>) define <16 x float> @test(<16 x float> %x, <16 x float> %y) nounwind { entry: %x1 = fadd <16 x float> %x, %y %call = call <16 x float> @foo(<16 x float> %x1) nounwind %y1 = fsub <16 x float> %call, %y ret <16 x float> %y1 } ./llc -mattr=+avx

On Oct 20, 2010, at 7:46 AM, Roland Scheidegger wrote: > On 20.10.2010 05:00, Jakob Stoklund Olesen wrote: >> Look in X86InstrControl.td. The call instructions are all prefixed >> by: >> >> let Defs = [RAX, RCX, RDX, RSI, RDI, R8, R9, R10, R11, FP0, FP1, FP2, >> FP3, FP4, FP5, FP6, ST0, ST1, MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7, >> XMM0, XMM1, XMM2, XMM3,

Greetings LLVM hackers and x86 vector shufflers! I would like to flip on another chunk of the new vector shuffling, specifically the logic to mark ~all shuffles as "legal". This can be tested today with the flag "-x86-experimental-vector-shuffle-legality". I would essentially like to make this the default (by removing the "false" path). Doing this will allow me to

Thanks for giving it a look! On 19.10.2010 23:21, Jakob Stoklund Olesen wrote: > On Oct 19, 2010, at 11:40 AM, Roland Scheidegger wrote: > >> So I saw that the code is doing lots of register >> spilling/reloading. Now I understand that due to calling >> conventions, there's not really a way to avoid this - I tried using >> coldcc but apparently the backend

I am a bit confused how the rematerialization works. It seems currently in our backend we get lots of code where some stack offset address is calculated, but this address is then spilled to stack, and loaded from stack later. This does not make sense, it would be better to just recalculate the address later, ie rematerialize the original stack offset calculation. But marking some instruction

(repost with right sender address) On 20.10.2010 18:13, Jakob Stoklund Olesen wrote: > On Oct 20, 2010, at 7:46 AM, Roland Scheidegger wrote: > >> On 20.10.2010 05:00, Jakob Stoklund Olesen wrote: >>> Look in X86InstrControl.td. The call instructions are all prefixed >>> by: >>> >>> let Defs = [RAX, RCX, RDX, RSI, RDI, R8, R9, R10, R11, FP0, FP1,

Roman Levenstein wrote: > Hi again, > > Now, after I fixed the graph coloring regalloc bug that was triggered > by the ARM target, I continue testing and found another bug, this time > on the XCore target. First I thought that it is again specific to my > register allocator, but it seems to be trigerred also by LLVM's > linearscan register allocator. > > I don't

On Oct 19, 2010, at 6:37 PM, Roland Scheidegger wrote: > Thanks for giving it a look! > > On 19.10.2010 23:21, Jakob Stoklund Olesen wrote: >> On Oct 19, 2010, at 11:40 AM, Roland Scheidegger wrote: >> >>> So I saw that the code is doing lots of register >>> spilling/reloading. Now I understand that due to calling >>> conventions, there's not

On Jan 13, 2009, at 11:20 AM, Richard Osborne <richard at xmos.com> wrote: > Roman Levenstein wrote: >> Hi again, >> >> Now, after I fixed the graph coloring regalloc bug that was triggered >> by the ARM target, I continue testing and found another bug, this >> time >> on the XCore target. First I thought that it is again specific to my >>

On May 3, 2011, at 12:03 PM, David A. Greene wrote: >> >> The greedy allocator is trying to pick registers so inner loops are as >> small as possible, but that is not always the right thing to do. > > How does it balance that against spill cost? I added the CostPerUse field to the register descriptions. The allocator will try to minimize the spill weight assigned to

Jakob Stoklund Olesen <stoklund at 2pi.dk> writes: >>> The greedy allocator is trying to pick registers so inner loops are as >>> small as possible, but that is not always the right thing to do. >> >> How does it balance that against spill cost? > > I added the CostPerUse field to the register descriptions. The > allocator will try to minimize the

Hi, Please consider the following loop: using v4f32 = float __attribute__((__vector_size__(16))); void fct6(v4f32 *x) { #pragma clang loop vectorize(enable) for (int i = 0; i < 256; ++i) x[i] = 7 * x[i]; } After compiling it with: clang++ -O3 -march=native -mtune=native \ -Rpass=loop-vectorize,slp-vectorize -Rpass-missed=loop-vectorize,slp-vectorize

Hello, Depending on how I extract integer lanes from an x86_64 xmm register, the backend may spill that register in order to load scalars. The effect was observed on two targets: corei7-avx and btver1 (I haven't checked other targets). Here's a test case with spilling/no-spilling code put on conditional compile: #if __SSE4_1__ != 0 #include <smmintrin.h> #else #include

Hello LLVM Developers, We are working on extending currently available register rematerialization to include cases where sequence of multiple instructions is required to rematerialize a value. We had a discussion on this in community mailing list and link is here: http://lists.llvm.org/pipermail/llvm-dev/2016-September/subject.html#104777 >From the above discussion and studying the code we