search for: usat

Hi, Given a function like x < 0 ? 0 : x We can lower it to bic x, x, asr 31 because we can test if CC==LT && RHS==TrueVal==0 && LHS==FalseVal Further, give a function x > 255 ? 255 : (x < 0 ? 0 :x), we should lower it to: usat x, #8 However, things become more complicated if we have ((x < 0 ? 0 :x) << n ) & mask ... Because it will first be converted to x < 0 ? 0 : ((x << n) & mask) Now, it's hard to match the pattern. (Doable but nasty) Any suggestions? Thanks in advance. Weiming Qual...

...gt; The plan is to form calls to these intrinsics in InstCombine. Legalizer > can expand these intrinsics if they are not legal. The expansion should > be fairly straight forward and produce code that is at least as good as > what LLVM is currently generating for these code sequence. SSAT/USAT may set the Q (saturation) flag, which might cause problems for anyone relying on explicitly using saturating operations (QADD etc.) and testing the Q flag. So there are several possibilities: - you could do liveness analysis on Q and only introduce SSAT/USAT if Q is not live - you could fa...

Hi all, I'm proposing integer saturation intrinsics. def int_ssat : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>, llvm_i32_ty]>; def int_usat : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>, llvm_i32_ty]>; The first operand is the integer value being saturated, and second is the saturation bit position. For scalar integer types, the semantics are: int_ssat: x < -(1 << (bit-1)) ? -(1 << (bit-1)) : (x > (1...

Hi all, The patches linked below introduce a new family of intrinsics, for integer saturation: @llvm.usat, and @llvm.ssat (unsigned/signed). Quoting the added documentation: %r = call i32 @llvm.ssat.i32(i32 %x, i32 %n) is equivalent to the expression min(max(x, -2^(n-1)), 2^(n-1)-1), itself implementable as the following IR: %min_sint_n = i32 ... ; the min. signed integer of bitwidth n,...

...ese intrinsics in legalizer time. Also llvm is already generating inferior code for these patterns for ARM and x86. We also have to consider whether forming sset will require substantial changes to other passes; thinking about it, it won't be too bad here. I still don't see the point of a usat intrinsic; we ought to already handle constructs that should form into usat effectively. -Eli

...Do you have a specific part in mind? Anyway, thanks for the feedback! -Ahmed > Philip > > > On 01/14/2015 02:08 PM, Ahmed Bougacha wrote: >> >> Hi all, >> >> The patches linked below introduce a new family of intrinsics, for >> integer saturation: @llvm.usat, and @llvm.ssat (unsigned/signed). >> Quoting the added documentation: >> >> %r = call i32 @llvm.ssat.i32(i32 %x, i32 %n) >> >> is equivalent to the expression min(max(x, -2^(n-1)), 2^(n-1)-1), itself >> implementable as the following IR: >> >>...

On Fri, Jun 17, 2011 at 3:08 PM, Evan Cheng <evan.cheng at apple.com> wrote: > Hi all, > > I'm proposing integer saturation intrinsics. > > def int_ssat : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>, llvm_i32_ty]>; > def int_usat : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>, llvm_i32_ty]>; > > The first operand is the integer value being saturated, and second is the saturation bit position. > > For scalar integer types, the semantics are: > > int_ssat: x < -(1 << (bit-1)) ? -(1 <...

On Jun 17, 2011, at 5:49 PM, Eli Friedman wrote: > On Fri, Jun 17, 2011 at 4:50 PM, Eli Friedman <eli.friedman at gmail.com> wrote: >>>>> The plan is to form calls to these intrinsics in InstCombine. Legalizer can expand these intrinsics if they are not legal. The expansion should be fairly straight forward and produce code that is at least as good as what LLVM is

On Fri, Jun 17, 2011 at 4:50 PM, Eli Friedman <eli.friedman at gmail.com> wrote: >>>> The plan is to form calls to these intrinsics in InstCombine. Legalizer can expand these intrinsics if they are not legal. The expansion should be fairly straight forward and produce code that is at least as good as what LLVM is currently generating for these code sequence. >>>>

...> On Fri, Jun 17, 2011 at 3:08 PM, Evan Cheng <evan.cheng at apple.com> wrote: >> Hi all, >> >> I'm proposing integer saturation intrinsics. >> >> def int_ssat : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>, llvm_i32_ty]>; >> def int_usat : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>, llvm_i32_ty]>; >> >> The first operand is the integer value being saturated, and second is the saturation bit position. >> >> For scalar integer types, the semantics are: >> >> int_ssat: x < -(1 &...

...neficial > optimisations. > > David > > > On 14 Jan 2015, at 22:08, Ahmed Bougacha <ahmed.bougacha at gmail.com> > wrote: > > > > Hi all, > > > > The patches linked below introduce a new family of intrinsics, for > > integer saturation: @llvm.usat, and @llvm.ssat (unsigned/signed). > > Quoting the added documentation: > > > > %r = call i32 @llvm.ssat.i32(i32 %x, i32 %n) > > > > is equivalent to the expression min(max(x, -2^(n-1)), 2^(n-1)-1), itself > > implementable as the following IR: > > &gt...

...t; Anyway, thanks for the feedback! > > -Ahmed > >> Philip >> >> >> On 01/14/2015 02:08 PM, Ahmed Bougacha wrote: >>> Hi all, >>> >>> The patches linked below introduce a new family of intrinsics, for >>> integer saturation: @llvm.usat, and @llvm.ssat (unsigned/signed). >>> Quoting the added documentation: >>> >>> %r = call i32 @llvm.ssat.i32(i32 %x, i32 %n) >>> >>> is equivalent to the expression min(max(x, -2^(n-1)), 2^(n-1)-1), itself >>> implementable as the follow...

...ould be a number of separate intrinsics with well-defined semantics for each one, preferably semantics that can be described in a single line. That makes it easy to implement and understand. Like so: llvm.ssat.iN(iN A, i32 SatWidth) = saturate anything above SatWidth bits as a signed value llvm.usat.iN(iN B, i32 SatWidth) = saturate anything above SatWidth bits as an unsigned value llvm.fixsmul.iN(iN A, iN B, i32 Scale) = sext->mul->ashr->trunc llvm.fixumul.iN(iN A, iN B, i32 Scale) = zext->mul->lshr->trunc llvm.fixsmul.sat.iN(iN A, iN B, i32 Scale) = sext->mul->ashr-&...

...== * Evitare l'uso delle prima persona singolare ("Io", "mio" etc.) nelle pagine, poich? non ? molto utile al lettore, e d? un'aria poco professionale al tutto. Se dovete fare riferimento a voi stessi o a qualcun altro, riferitevi alla pagina del Wiki con il contatto (o usate il nome completo se la persona non ha una pagina su questo Wiki) -- Quando ti trovi d'accordo con la maggioranza, ? il momento di fermarti e riflettere - Mark Twain -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.centos.org/pipermail/centos-d...

...2011 at 3:08 PM, Evan Cheng <evan.cheng at apple.com> wrote: >>> Hi all, >>> >>> I'm proposing integer saturation intrinsics. >>> >>> def int_ssat : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>, llvm_i32_ty]>; >>> def int_usat : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>, llvm_i32_ty]>; >>> >>> The first operand is the integer value being saturated, and second is the saturation bit position. >>> >>> For scalar integer types, the semantics are: >>> >>> i...

On 2018-08-22 05:56, John McCall via llvm-dev wrote: >> On Aug 21, 2018, at 6:20 PM, Leonard Chan <leonardchan at google.com> wrote: >> If we were to create a new type down the line, I think the main >> features that would distinguish them from other types are the >> arbitrary width and scale. Saturation can be handled through >> instructions since saturation