similar to: [LLVMdev] Function pointer parameters in PTX backend

Hi everybody, I am testing the PTX backend using the OpenCL NVIDIA SDK benchmarks. Compiling the Histogram64.cl program I get a several backend errors. I isolated one of them in the following kernel program: __kernel void kernel_function(__global int *input) { __local char localArray[16]; for(unsigned int index = 0; index < 16; ++index) localArray[index] = 0; input[0] =

On Mon, Nov 14, 2011 at 8:57 AM, Alberto Magni <alberto.magni86 at gmail.com>wrote: > Hi everybody, > > I am testing the PTX backend using the OpenCL NVIDIA SDK benchmarks. > Compiling the Histogram64.cl program I get a several backend errors. > > I isolated one of them in the following kernel program: > > __kernel void kernel_function(__global int *input) { >

Justin, Add this to your TargetLowering constructor, this fixes the mem* issue. maxStoresPerMemcpy = 4096; maxStoresPerMemmove = 4096; maxStoresPerMemset = 4096; From: llvmdev-bounces at cs.uiuc.edu [mailto:llvmdev-bounces at cs.uiuc.edu] On Behalf Of Justin Holewinski Sent: Monday, November 14, 2011 7:12 AM To: Alberto Magni Cc: llvmdev at cs.uiuc.edu Subject: Re: [LLVMdev] PTX backend

Hi all, Does PTX backend support llvm sitofp instruction? I failed to compile my llvm source when use llc -march=ptx32. The reason is that the source has a sitofp instruction. After i changed the instruction into uitofp manually, it passed. Thanks in advance, best, Yabin -------------- next part -------------- An HTML attachment was scrubbed... URL:

Hi Justin, I download llvm-ptx-samples [1] and try to build them. I found it seems lack of a complete document on how to build them with LLVM/Clang/libclc. Do you think it's a good idea to put a complete document/tutorial in _one_ place? Currently, there are your website [2], LLVM [3], Clang and libclc websites [5] over there. I feel people might get lost among those websites. ;-) Here

On Tue, Dec 6, 2011 at 10:17 PM, 陳韋任 <chenwj at iis.sinica.edu.tw> wrote: > Hi Justin, > > I download llvm-ptx-samples [1] and try to build them. I found it seems > lack > of a complete document on how to build them with LLVM/Clang/libclc. Do you > think > it's a good idea to put a complete document/tutorial in _one_ place? > Currently, > there are your

On Mon, Nov 21, 2011 at 3:36 PM, Justin Holewinski <justin.holewinski at gmail.com> wrote: > On Mon, Nov 21, 2011 at 7:01 AM, Alberto Magni <alberto.magni86 at gmail.com> > wrote: >> >> Hi Justin, >> >> attached you find the patch for the integer max instruction. >> The multiclass PTX_INTRINSIC_INT3 in file PTXIntrinsicInstrInfo.td >> is almost

On Mon, Nov 21, 2011 at 7:01 AM, Alberto Magni <alberto.magni86 at gmail.com>wrote: > Hi Justin, > > attached you find the patch for the integer max instruction. > The multiclass PTX_INTRINSIC_INT3 in file PTXIntrinsicInstrInfo.td > is almost an exact copy of PTX_INT3 in PTXInstrInfo.td, maybe > a modification of this class can be defined in a separate file. > I'm

On Mon, Nov 21, 2011 at 5:31 PM, Justin Holewinski <justin.holewinski at gmail.com> wrote: > On Mon, Nov 21, 2011 at 11:45 AM, Alberto Magni <alberto.magni86 at gmail.com> > wrote: >> >> On Mon, Nov 21, 2011 at 3:36 PM, Justin Holewinski >> <justin.holewinski at gmail.com> wrote: >> > On Mon, Nov 21, 2011 at 7:01 AM, Alberto Magni >> >

On Mon, Nov 21, 2011 at 11:45 AM, Alberto Magni <alberto.magni86 at gmail.com>wrote: > On Mon, Nov 21, 2011 at 3:36 PM, Justin Holewinski > <justin.holewinski at gmail.com> wrote: > > On Mon, Nov 21, 2011 at 7:01 AM, Alberto Magni < > alberto.magni86 at gmail.com> > > wrote: > >> > >> Hi Justin, > >> > >> attached you find

Dear Justin, I am trying to add the support for some OpenCL builtin functions to the PTX backend. The attached file represent the first stub of a patch for the fmax builtin function. The test case I am trying is the following: define ptx_device float @f(float %x, float %y) { entry: %z = call float @fmax(float %x, float %y) ret float %z } declare float @fmax(float, float) But at the moment

On Tue, Nov 22, 2011 at 5:01 PM, Villmow, Micah <Micah.Villmow at amd.com> wrote: > Alberto, >  The AMDIL backend solves your problem with intrinsic overloading this way: > def int_AMDIL_mad     : GCCBuiltin<"__amdil_mad">, TernaryIntFloat; > > Where TernaryIntFloat is defined as: > class TernaryIntFloat : >          Intrinsic<[llvm_anyfloat_ty],

Alberto, The AMDIL backend solves your problem with intrinsic overloading this way: def int_AMDIL_mad : GCCBuiltin<"__amdil_mad">, TernaryIntFloat; Where TernaryIntFloat is defined as: class TernaryIntFloat : Intrinsic<[llvm_anyfloat_ty], [LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>], []>; This allows us to write a

On Nov 23, 2011 8:33 AM, "Justin Holewinski" <justin.holewinski at gmail.com> wrote: > > > On Nov 23, 2011 6:57 AM, "Alberto Magni" <alberto.magni86 at gmail.com> wrote: > > > > On Tue, Nov 22, 2011 at 5:01 PM, Villmow, Micah <Micah.Villmow at amd.com> wrote: > > > Alberto, > > > The AMDIL backend solves your problem

On Nov 23, 2011 6:57 AM, "Alberto Magni" <alberto.magni86 at gmail.com> wrote: > > On Tue, Nov 22, 2011 at 5:01 PM, Villmow, Micah <Micah.Villmow at amd.com> wrote: > > Alberto, > > The AMDIL backend solves your problem with intrinsic overloading this way: > > def int_AMDIL_mad : GCCBuiltin<"__amdil_mad">, TernaryIntFloat; >

On Sun, Dec 4, 2011 at 1:10 PM, Alberto Magni <alberto.magni86 at gmail.com>wrote: > Hi Justin, > > sorry for the delay, I have been busy. > > Micah's proposal requires to move the definitions of the intrinsics > from include/llvm/IntrinsicsPTX.td to lib/Target/PTX/PTXIntrinsics.td > thus allowing the generation of the file PTXGenIntrinsics.inc which > will be

I have data of the form tC <- textConnection(" Subject Date parameter1 bob 3/2/99 10 bob 4/2/99 10 bob 5/5/99 10 bob 6/27/99 NA bob 8/35/01 10 bob 3/2/02 10 steve 1/2/99 4 steve 2/2/00 7 steve 3/2/01 10 steve 4/2/02 NA steve 5/2/03 16 kevin 6/5/04 24 ") data <- read.table(header=TRUE, tC) close.connection(tC) rm(tC) I am trying to calculate rate of change of parameter1 in

Hi, I have a file fileFoo.R, say that contains these two lines, invoking function foo that is specified in "foo_details.R": source("foo_details.R") foo(parameter1) I want to specify and pass parameter1 in my command line when invoking R in linux: R --no-save <fileFoo.R. How can I do that? And how can I retrieve the value of parameter1 in my fileFoo.R function

Hello everyone, I have the following matrix [,1] [,2] [,3] [,4] [1,] 0.002809706 0.0063856960 0.0063856960 0.011749681 [2,] 0.004893124 0.0023118418 -0.0005122951 -0.014646465 [3,] 0.003547897 0.0063355297 0.0030410542 0.011403953 [4,] 0.004838299 -0.0040383645 -0.0090406831 -0.011027569 [5,] 0.035648755 0.0334815590 0.0380977404

On Thu, Dec 8, 2011 at 11:36 AM, Villmow, Micah <Micah.Villmow at amd.com>wrote: > It is my understanding that all you need to do is specify let isTarget = > 1 in your .td file and it will generate target specific intrinsics. This > should allow you to keep the IntrinsicsPTX.td file in the same location. > So we keep the intrinsics defined in include/llvm/IntrinsicsPTX.td?