similar to: IR canonicalization: shufflevector or vector trunc?

On 1/12/2017 9:04 AM, Sanjay Patel via llvm-dev wrote: > It's time for another round of "What is the canonical IR?" > > Credit for this episode to Zvi and PR31551. :) > https://llvm.org/bugs/show_bug.cgi?id=31551 > define <4 x i16> @shuffle(<16 x i16> %x) { > %shuf = shufflevector <16 x i16> %x, <16 x i16> undef, <4 x i32> <i32 0,

On Thu, Jan 12, 2017 at 11:06 AM, Friedman, Eli <efriedma at codeaurora.org> wrote: > On 1/12/2017 9:04 AM, Sanjay Patel via llvm-dev wrote: > > It's time for another round of "What is the canonical IR?" > > Credit for this episode to Zvi and PR31551. :) > https://llvm.org/bugs/show_bug.cgi?id=31551 > > define <4 x i16> @shuffle(<16 x i16>

Right - I think that case looks like this for little endian: define <2 x i32> @zextshuffle(<2 x i16> %x) { %zext_shuffle = shufflevector <2 x i16> %x, <2 x i16> zeroinitializer, <4 x i32> <i32 0, i32 2, i32 1, i32 2> %bc = bitcast <4 x i16> %zext_shuffle to <2 x i32> ret <2 x i32> %bc } define <2 x i32> @zextvec(<2 x i16>

We use InstCombiner::ShouldChangeType() to prevent transforms to illegal integer types, but I'm not sure how that would apply to vector types. Ie, let's say v256 is a legal type in your example. DataLayout doesn't appear to specify what configurations of a 256-bit vector are legal, so I don't think we can currently use that to say v2i128 should be treated differently than v16i16.

On Thu, Jan 19, 2017 at 9:17 AM, Rackover, Zvi <zvi.rackover at intel.com> wrote: > Hi Sanjay, > > > > I agree we should also discuss **if** this canonicalization is beneficial. > > For starters, do we have a concrete case where we would benefit from > canonicalizing shuffles <-> truncates in LLVM IR? > > IMO, we should not count benefits for codegen

As Sanjay noted in D31426<https://reviews.llvm.org/D31426#712701>, InstructionSimplify is missing the following simplification: This function: define <4 x i32> @splat_operand(<4 x i32> %x) { %splat = shufflevector <4 x i32> %x, <4 x i32> undef, <4 x i32> zeroinitializer %shuf = shufflevector <4 x i32> %splat, <4 x i32> undef, <4 x i32>

A vector select with a constant vector condition operand: define <4 x i32> @foo(<4 x i32> %a, <4 x i32> %b) { %sel = select <4 x i1> <i1 true, i1 false, i1 false, i1 true>, <4 x i32> %a, <4 x i32> %b ret <4 x i32> %sel } ...is equivalent to a shufflevector: define <4 x i32> @goo(<4 x i32> %a, <4 x i32> %b) { %shuf =

I have a slight preference towards shufflevector, because it makes sequences of shuffles, where only some of the shuffles can be converted into selects (because the input and output vector sizes of the others don't match) simpler to reason about. I'm not sure this is a particularly good reason, though. On Mon, Aug 29, 2016 at 8:19 AM, Philip Reames via llvm-dev < llvm-dev at

x86 has also put a lot of effort into shuffle lowering...so much so that it is its own life-form and brings most online codeviewer apps to their knees when you try to open X86ISelLowering.cpp. :) Given that: 1. There are at least 2 targets that lean towards shuffle (Martin's comment + x86 uses lowerVSELECTtoVectorShuffle() for all cases like the example posted here) 2. Size-changing shuffles

Thanks, Sanjay, that makes sense. The opportunity for improving instcombining splat sounds promising. Another question about shuffle simplification. This is a testcase from test/Transforms/InstCombine/vec_shuffle.ll: define <4 x i32> @test10(<4 x i32> %tmp5) nounwind { %tmp6 = shufflevector <4 x i32> %tmp5, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32

Sanjay, I'm looking at some missed optimizations caused by D70246. Here's a test case: define <4 x float> @f(i32 %t32, <4 x float>* %t24) { .entry: %t43 = insertelement <3 x i32> undef, i32 %t32, i32 2 %t44 = bitcast <3 x i32> %t43 to <3 x float> %t45 = shufflevector <3 x float> %t44, <3 x float> undef, <4 x i32> <i32 0, i32 undef,

Hi, I am trying to understand LLVM vectorization implementation and was looking into both loop and SLP vectorization. test case 1: *int foo(int *a) {int sum = 0,i;for(i=0; i<16; i++) sum += a[i];return sum;}* This code is vectorized by loop vectorizer where we calculate scalar loop cost as 4 and vector loop cost as 2. Since vector loop cost is less and above reduction is legal to

Hi Nadav, Thanks for the quick reply !! Ok, so as of now we are lacking capability to handle flat large reductions. I did go through function vectorizeChainsInBlock() (line number 2862). In this function, we try to vectorize if we have phi nodes in the IR (several if's check for phi nodes) i.e we try to construct tree that starts at chains. Any pointers on how to join multiple trees? I

Hi Ahmed, >From what can be seen in the code snippet you provided, the reuse of XMM0 and XMM1 across loop-unroll instances does not inhibit instruction-level parallelism. Modern X86 processors use register renaming that can eliminate the dependencies in the instruction stream. In the example you provided, the processor should be able to identify the 2-vloads + vadd + vstore sequences as

Andreas, On Thu, Aug 24, 2017 at 03:37:07PM +0200, awl1 via samba wrote: > Before I follow your advice to move this whole issue/topic to the > samba-technical alias and start over there with a clean description of the > scenario and the findings, I have two simple questions: > > 1) I plan to use a new, reproducible test scenario with 2000 random small > files with a file length

Hi Martin Here is some more info in the libvirt/qemu/instance...log file . Does it help in resolving the issue of : error : qemuMonitorIO:614 : internal>error End of file from monitor In the libvirtd.log file I sent you could see clearly that the debug option is active and this is the most detailed info available (or some better option than log_leve=1 exists ?) Thx Zvi Dubitzky

Hi, Zvi, I agree. In the context of targeting the KNL, however, I'm a bit concerned about the addressing, and specifically, the size of the resulting encoding: > vmovdqu32 zmm0, zmmword ptr [rax + c+401280] ;load b[401280] in > zmm0 > > vpaddd zmm1, zmm1, zmmword ptr [rax + b+401344] > ; zmm1<-zmm1+b[401344] The KNL can only

Hi For some reason recent libvirt code (0.8.3 and even before) the 'virsh shutdown <domain> ' is not effective . It issues an ok message but the domians remains in a runnning state . Only th e destroy works fine. Any idea ? thanks Zvi Dubitzky Email:dubi at il.ibm.com

Hi, I have experimented with enabling the LoopVectorizer for SystemZ. I have come across a loop which, when vectorized, seems to have been poorly generated. In short, there seems to be a completely unnecessary sequence of shufflevector instructions, that doesn't get optimized away anywhere. In other words, there is a shuffling so that leads back to the original vector: [0 1 2 3

Using libvirt under openstack I encounter a problem when launching a VM with multiple partitions (2 G image) , While a single partition can be launched successfully . The launch is done with Openstack. We are using in libvirtd.conf log_level=1 and log_outputs="1:file:/var/log/libvirt/libvirtd.log" we can see that in /var/log/libvirt/libvirtd.log appear the following error