similar to: [LLVMdev] API change: add, sub, and mul no longer do floating-point

On Mon, May 3, 2010 at 3:53 PM, Dan Gohman <gohman at apple.com> wrote: > Quick heads up: On LLVM trunk, the add, sub, and mul instructions no > longer accept floating-point operands. The fadd, fsub, and fmul instructions > should be used instead. > > This change actually happened back in LLVM 2.6; since then, LLVM has just > been silently converting add into fadd and so

On May 3, 2010, at 3:59 PM, Eli Friedman wrote: > On Mon, May 3, 2010 at 3:53 PM, Dan Gohman <gohman at apple.com> wrote: >> Quick heads up: On LLVM trunk, the add, sub, and mul instructions no >> longer accept floating-point operands. The fadd, fsub, and fmul instructions >> should be used instead. >> >> This change actually happened back in LLVM 2.6;

Hello, The LLVM IR opcodes Add, Sub, and Mul have been each split into two. Add, Sub, and Mul now only handle integer types, and three new opcodes, FAdd, FSub, and FMul now handle floating-point types. The main LLVM APIs are currently preserving backwards compatibility, transparently mapping integer opcodes to corresponding floating-point opcodes when the operands have floating-point types.

On Jun 16, 2009, at 7:34 AM, Aaron Gray wrote: >> The LLVM IR opcodes Add, Sub, and Mul have been each split into >> two. Add, Sub, and Mul now only handle integer types, and three >> new opcodes, FAdd, FSub, and FMul now handle floating-point types. > > Dan, > > Wondering the reason why there is no FDiv ? FDiv already exists; div was split quite a while ago. Dan

I looked more into this. For the previously sent IR the vector width of 256 bit is found mistakenly (and reproducibly) on this hardware: model name : Intel(R) Xeon(R) CPU E5-2650 0 @ 2.00GHz For the same IR the loop vectorizer finds the correct vector width (128 bit) on: model name : Intel(R) Xeon(R) CPU E5630 @ 2.53GHz model name : Intel(R) Core(TM) i7 CPU M 640 @

The loop vectorizer is doing an amazing job so far. Most of the time. I just came across one function which led to unexpected behavior: On this function the loop vectorizer finds a 256 bit vector as the wides vector type for the x86-64 architecture. (!) This is strange, as it was always finding the correct size of 128 bit as the widest type. I isolated the IR of the function to check if this is

Hi Frank, I'm not an Intel expert, but it seems that your Xeon E5 supports AVX, which does have 256-bit vectors. The other two only supports SSE instructions, which are only 128-bit long. cheers, --renato On 10 November 2013 06:05, Frank Winter <fwinter at jlab.org> wrote: > I looked more into this. For the previously sent IR the vector width of > 256 bit is found mistakenly

Hi, On LLVM 5.0 (current trunk), fadd/fsub and fmul that are both marked with `contract` or `fast` can be merged to a fma instruction by the backend. I'm wondering about the exact semantic of this new flag as well as `fast` and in particular, would it be valid to do this when only the `fadd`/`fsub` (and not the `fmul`) is marked with `contract` or at least `fast`. The reasoning is that doing

> The LLVM IR opcodes Add, Sub, and Mul have been each split into > two. Add, Sub, and Mul now only handle integer types, and three > new opcodes, FAdd, FSub, and FMul now handle floating-point types. Dan, Wondering the reason why there is no FDiv ? Thanks, Aaron

On Oct 17, 2011, at 6:40 PM, Hal Finkel wrote: > On Mon, 2011-10-17 at 17:33 -0700, Dan Gohman wrote: >> On Oct 17, 2011, at 3:40 PM, Hal Finkel wrote: >> >>> How should I go about matching floating-point addsub-like vector >>> instructions? My first inclination is to write something which matches >>> build_vector 1.0, -1.0, and then use that in

On Tue, 2011-10-18 at 10:51 -0700, Dan Gohman wrote: > On Oct 17, 2011, at 6:40 PM, Hal Finkel wrote: > > > On Mon, 2011-10-17 at 17:33 -0700, Dan Gohman wrote: > >> On Oct 17, 2011, at 3:40 PM, Hal Finkel wrote: > >> > >>> How should I go about matching floating-point addsub-like vector > >>> instructions? My first inclination is to write

The loads, stores and float arithmetic in attached function should be completely vectorizable. The bb-vectorizer does a good job at first, but from instruction %96 on it messes up by adding unnecessary vectorshuffles. (The function was designed so that no shuffle would be needed in order to vectorize it). I tested this with llvm 3.6 with the following command:

Hi Duncan, On 17.09.2014 21:10, Duncan Sands wrote: > Hi Oleg, > > On 17/09/14 18:45, Oleg Ranevskyy wrote: >> Hi, >> >> Thank you for all your helpful comments. >> >> To sum up, below is the list of correct folding examples for fadd: >> (1) fadd %x, -0.0 -> %x >> (2) fadd undef, undef -> undef

On Mon, 2011-10-17 at 17:33 -0700, Dan Gohman wrote: > On Oct 17, 2011, at 3:40 PM, Hal Finkel wrote: > > > How should I go about matching floating-point addsub-like vector > > instructions? My first inclination is to write something which matches > > build_vector 1.0, -1.0, and then use that in combination with a match on > > fadd, but that does not seem to work. I

Hi all! It takes the current SLP vectorizer too long to vectorize my scalar code. I am talking here about functions that have a single, huge basic block with O(10^6) instructions. Here's an example: %0 = getelementptr float* %arg1, i32 49 %1 = load float* %0 %2 = getelementptr float* %arg1, i32 4145 %3 = load float* %2 %4 = getelementptr float* %arg2, i32 49 %5 = load

Hi, Thank you for all your helpful comments. To sum up, below is the list of correct folding examples for fadd: (1) fadd %x, -0.0 -> %x (2) fadd undef, undef -> undef (3) fadd %x, undef -> NaN (undef is a NaN which is propagated) Looking through the code I found the "NoNaNs" flag accessed through an instance of

%y = fadd float %x, undef Can we simplify this? Currently in IR, we do nothing for fadd/fsub/fmul. For fdiv/frem, we propagate undef. The code comment for fdiv/frem says: "the undef could be a snan" If that's correct, then shouldn't it be the same for fadd/fsub/fmul? But this can't be correct because we support targets that don't raise exceptions...and even targets

On Mon, 2 Sep 2019 at 16:59, Roman Lebedev <lebedev.ri at gmail.com> wrote: > > It appears you need 'reassoc' on fmul/fadd: > https://godbolt.org/z/nuTzx2 Thanks very much, that was it. Either that or providing -enable-unsafe-fp-math to llc yielded FMAs. I didn't expect this since using FMAs here instead of mul/add appears to be safer (the reverse is unsafe). ~ Uday

I’m not sure the transformation happening with fdiv is correct. If we have “%y = fdiv float %x, undef” and %x is a NaN then the result will be NaN for any value of the undef, right? So if I understand the undef rules correctly (never a certainty) then we can’t safely replace the expression with undef. We could, I think, replace it with “%y = %x” though. I think the same is true for fadd, fsub,

Yes, if %x is a NaN, we should expect that NaN is propagated. I'm still not sure what to do here. We can take comfort in knowing that whatever we do is likely an improvement over the current situation though. :) That's because the code in InstSimplify is inconsistent with the LangRef: http://llvm.org/docs/LangRef.html#undefined-values (UB for fdiv by 0?) ...and both of those are