[llvm-branch-commits] [libc] [libc][math][c23] Add tanhf16 C23 math function (PR #106006)
https://github.com/overmighty created
https://github.com/llvm/llvm-project/pull/106006
Part of #95250.
>From eadda81a46d6b3bdf44574467deb3d94add102ac Mon Sep 17 00:00:00 2001
From: OverMighty
Date: Sun, 25 Aug 2024 22:02:09 +0200
Subject: [PATCH] [libc][math][c23] Add tanhf16 C23 math function
Part of #95250.
---
libc/config/gpu/entrypoints.txt | 1 +
libc/config/linux/x86_64/entrypoints.txt | 1 +
libc/docs/math/index.rst | 2 +-
libc/spec/stdc.td | 1 +
libc/src/math/CMakeLists.txt | 1 +
libc/src/math/generic/CMakeLists.txt | 22
libc/src/math/generic/tanhf16.cpp | 144 ++
libc/src/math/tanhf16.h | 21
libc/test/src/math/CMakeLists.txt | 11 ++
libc/test/src/math/smoke/CMakeLists.txt | 12 ++
libc/test/src/math/smoke/tanhf16_test.cpp | 131
libc/test/src/math/tanhf16_test.cpp | 40 ++
12 files changed, 386 insertions(+), 1 deletion(-)
create mode 100644 libc/src/math/generic/tanhf16.cpp
create mode 100644 libc/src/math/tanhf16.h
create mode 100644 libc/test/src/math/smoke/tanhf16_test.cpp
create mode 100644 libc/test/src/math/tanhf16_test.cpp
diff --git a/libc/config/gpu/entrypoints.txt b/libc/config/gpu/entrypoints.txt
index 7fdebe9322c283..b206bb7c936f39 100644
--- a/libc/config/gpu/entrypoints.txt
+++ b/libc/config/gpu/entrypoints.txt
@@ -551,6 +551,7 @@ if(LIBC_TYPES_HAS_FLOAT16)
libc.src.math.setpayloadf16
libc.src.math.setpayloadsigf16
libc.src.math.sinhf16
+libc.src.math.tanhf16
libc.src.math.totalorderf16
libc.src.math.totalordermagf16
libc.src.math.truncf16
diff --git a/libc/config/linux/x86_64/entrypoints.txt
b/libc/config/linux/x86_64/entrypoints.txt
index 5b984c4bcd501d..b702a7ff482a5c 100644
--- a/libc/config/linux/x86_64/entrypoints.txt
+++ b/libc/config/linux/x86_64/entrypoints.txt
@@ -662,6 +662,7 @@ if(LIBC_TYPES_HAS_FLOAT16)
libc.src.math.setpayloadf16
libc.src.math.setpayloadsigf16
libc.src.math.sinhf16
+libc.src.math.tanhf16
libc.src.math.totalorderf16
libc.src.math.totalordermagf16
libc.src.math.truncf16
diff --git a/libc/docs/math/index.rst b/libc/docs/math/index.rst
index 6f17d4fa022c9a..de88f14426799f 100644
--- a/libc/docs/math/index.rst
+++ b/libc/docs/math/index.rst
@@ -344,7 +344,7 @@ Higher Math Functions
+---+--+-++--++++
| tan | |check| | |check| ||
|| 7.12.4.7 | F.10.1.7
|
+---+--+-++--++++
-| tanh | |check| | ||
|| 7.12.5.6 | F.10.2.6
|
+| tanh | |check| | ||
|check| || 7.12.5.6 |
F.10.2.6 |
+---+--+-++--++++
| tanpi | | ||
|| 7.12.4.14 | F.10.1.14
|
+---+--+-++--++++
diff --git a/libc/spec/stdc.td b/libc/spec/stdc.td
index 71c0c0364eecdf..043762bb227456 100644
--- a/libc/spec/stdc.td
+++ b/libc/spec/stdc.td
@@ -712,6 +712,7 @@ def StdC : StandardSpec<"stdc"> {
GuardedFunctionSpec<"sinhf16", RetValSpec,
[ArgSpec], "LIBC_TYPES_HAS_FLOAT16">,
FunctionSpec<"tanhf", RetValSpec, [ArgSpec]>,
+ GuardedFunctionSpec<"tanhf16", RetValSpec,
[ArgSpec], "LIBC_TYPES_HAS_FLOAT16">,
FunctionSpec<"acosf", RetValSpec, [ArgSpec]>,
diff --git a/libc/src/math/CMakeLists.txt b/libc/src/math/CMakeLists.txt
index a9b866a31411e5..be05903d4a1c6e 100644
--- a/libc/src/math/CMakeLists.txt
+++ b/libc/src/math/CMakeLists.txt
@@ -483,6 +483,7 @@ add_math_entrypoint_object(tanf)
add_math_entrypoint_object(tanh)
add_math_entrypoint_object(tanhf)
+add_math_entrypoint_object(tanhf16)
add_math_entrypoint_object(tgamma)
add_math_entrypoint_object(tgammaf)
diff --git a/libc/src/math/generic/CMakeLists.txt
b/libc/src/math/generic/CMakeLists.txt
index 12188eaf344f77..9534d17426486b 100644
--- a/libc/src/math/generic/CMakeLists.txt
+++ b/libc/src
[llvm-branch-commits] [libc] [libc][math][c23] Add tanhf16 C23 math function (PR #106006)
llvmbot wrote:
@llvm/pr-subscribers-libc
Author: OverMighty (overmighty)
Changes
Part of #95250.
---
Full diff: https://github.com/llvm/llvm-project/pull/106006.diff
12 Files Affected:
- (modified) libc/config/gpu/entrypoints.txt (+1)
- (modified) libc/config/linux/x86_64/entrypoints.txt (+1)
- (modified) libc/docs/math/index.rst (+1-1)
- (modified) libc/spec/stdc.td (+1)
- (modified) libc/src/math/CMakeLists.txt (+1)
- (modified) libc/src/math/generic/CMakeLists.txt (+22)
- (added) libc/src/math/generic/tanhf16.cpp (+144)
- (added) libc/src/math/tanhf16.h (+21)
- (modified) libc/test/src/math/CMakeLists.txt (+11)
- (modified) libc/test/src/math/smoke/CMakeLists.txt (+12)
- (added) libc/test/src/math/smoke/tanhf16_test.cpp (+131)
- (added) libc/test/src/math/tanhf16_test.cpp (+40)
``diff
diff --git a/libc/config/gpu/entrypoints.txt b/libc/config/gpu/entrypoints.txt
index 7fdebe9322c283..b206bb7c936f39 100644
--- a/libc/config/gpu/entrypoints.txt
+++ b/libc/config/gpu/entrypoints.txt
@@ -551,6 +551,7 @@ if(LIBC_TYPES_HAS_FLOAT16)
libc.src.math.setpayloadf16
libc.src.math.setpayloadsigf16
libc.src.math.sinhf16
+libc.src.math.tanhf16
libc.src.math.totalorderf16
libc.src.math.totalordermagf16
libc.src.math.truncf16
diff --git a/libc/config/linux/x86_64/entrypoints.txt
b/libc/config/linux/x86_64/entrypoints.txt
index 5b984c4bcd501d..b702a7ff482a5c 100644
--- a/libc/config/linux/x86_64/entrypoints.txt
+++ b/libc/config/linux/x86_64/entrypoints.txt
@@ -662,6 +662,7 @@ if(LIBC_TYPES_HAS_FLOAT16)
libc.src.math.setpayloadf16
libc.src.math.setpayloadsigf16
libc.src.math.sinhf16
+libc.src.math.tanhf16
libc.src.math.totalorderf16
libc.src.math.totalordermagf16
libc.src.math.truncf16
diff --git a/libc/docs/math/index.rst b/libc/docs/math/index.rst
index 6f17d4fa022c9a..de88f14426799f 100644
--- a/libc/docs/math/index.rst
+++ b/libc/docs/math/index.rst
@@ -344,7 +344,7 @@ Higher Math Functions
+---+--+-++--++++
| tan | |check| | |check| ||
|| 7.12.4.7 | F.10.1.7
|
+---+--+-++--++++
-| tanh | |check| | ||
|| 7.12.5.6 | F.10.2.6
|
+| tanh | |check| | ||
|check| || 7.12.5.6 |
F.10.2.6 |
+---+--+-++--++++
| tanpi | | ||
|| 7.12.4.14 | F.10.1.14
|
+---+--+-++--++++
diff --git a/libc/spec/stdc.td b/libc/spec/stdc.td
index 71c0c0364eecdf..043762bb227456 100644
--- a/libc/spec/stdc.td
+++ b/libc/spec/stdc.td
@@ -712,6 +712,7 @@ def StdC : StandardSpec<"stdc"> {
GuardedFunctionSpec<"sinhf16", RetValSpec,
[ArgSpec], "LIBC_TYPES_HAS_FLOAT16">,
FunctionSpec<"tanhf", RetValSpec, [ArgSpec]>,
+ GuardedFunctionSpec<"tanhf16", RetValSpec,
[ArgSpec], "LIBC_TYPES_HAS_FLOAT16">,
FunctionSpec<"acosf", RetValSpec, [ArgSpec]>,
diff --git a/libc/src/math/CMakeLists.txt b/libc/src/math/CMakeLists.txt
index a9b866a31411e5..be05903d4a1c6e 100644
--- a/libc/src/math/CMakeLists.txt
+++ b/libc/src/math/CMakeLists.txt
@@ -483,6 +483,7 @@ add_math_entrypoint_object(tanf)
add_math_entrypoint_object(tanh)
add_math_entrypoint_object(tanhf)
+add_math_entrypoint_object(tanhf16)
add_math_entrypoint_object(tgamma)
add_math_entrypoint_object(tgammaf)
diff --git a/libc/src/math/generic/CMakeLists.txt
b/libc/src/math/generic/CMakeLists.txt
index 12188eaf344f77..9534d17426486b 100644
--- a/libc/src/math/generic/CMakeLists.txt
+++ b/libc/src/math/generic/CMakeLists.txt
@@ -4154,6 +4154,28 @@ add_entrypoint_object(
-O3
)
+add_entrypoint_object(
+ tanhf16
+ SRCS
+tanhf16.cpp
+ HDRS
+../tanhf16.h
+ DEPENDS
+.expxf16
+libc.hdr.fenv_macros
+libc.src.__support.CPP.array
+libc.src.__support.FPUtil.except_value_utils
+libc.src.__support.FPUtil.fenv_impl
+libc.src.__support.FPUtil.fp_bits
+libc.src.__support.FPUtil.m
[llvm-branch-commits] [llvm] release/19.x: [MIPS] Optimize sortRelocs for o32 (PR #106008)
https://github.com/alexrp created
https://github.com/llvm/llvm-project/pull/106008
Manual backport of #104723.
From 9a72d8b12202d27c4229ff9ccab0f0cdb6b6f583 Mon Sep 17 00:00:00 2001
From: Fangrui Song
Date: Sun, 18 Aug 2024 11:24:44 -0700
Subject: [PATCH 1/3] [MIPS] Remove expensive LLVM_DEBUG relocation dump
The input is usually ordered by offset, so inspecting the output is
sufficient. The super expensive relocation dump is not conventional.
---
.../Mips/MCTargetDesc/MipsELFObjectWriter.cpp | 32 ++-
1 file changed, 2 insertions(+), 30 deletions(-)
diff --git a/llvm/lib/Target/Mips/MCTargetDesc/MipsELFObjectWriter.cpp
b/llvm/lib/Target/Mips/MCTargetDesc/MipsELFObjectWriter.cpp
index 4d6a00c14a3575..1f047020d96c80 100644
--- a/llvm/lib/Target/Mips/MCTargetDesc/MipsELFObjectWriter.cpp
+++ b/llvm/lib/Target/Mips/MCTargetDesc/MipsELFObjectWriter.cpp
@@ -47,13 +47,6 @@ struct MipsRelocationEntry {
}
};
-#ifndef NDEBUG
-raw_ostream &operator<<(raw_ostream &OS, const MipsRelocationEntry &RHS) {
- RHS.print(OS);
- return OS;
-}
-#endif
-
class MipsELFObjectWriter : public MCELFObjectTargetWriter {
public:
MipsELFObjectWriter(uint8_t OSABI, bool HasRelocationAddend, bool Is64);
@@ -115,17 +108,11 @@ static InputIt find_best(InputIt First, InputIt Last,
UnaryPredicate Predicate,
for (InputIt I = First; I != Last; ++I) {
unsigned Matched = Predicate(*I);
if (Matched != FindBest_NoMatch) {
- LLVM_DEBUG(dbgs() << std::distance(First, I) << " is a match (";
- I->print(dbgs()); dbgs() << ")\n");
- if (Best == Last || BetterThan(*I, *Best)) {
-LLVM_DEBUG(dbgs() << ".. and it beats the last one\n");
+ if (Best == Last || BetterThan(*I, *Best))
Best = I;
- }
}
-if (Matched == FindBest_PerfectMatch) {
- LLVM_DEBUG(dbgs() << ".. and it is unbeatable\n");
+if (Matched == FindBest_PerfectMatch)
break;
-}
}
return Best;
@@ -201,15 +188,6 @@ static bool compareMatchingRelocs(const
MipsRelocationEntry &Candidate,
return PreviousBest.Matched && !Candidate.Matched;
}
-#ifndef NDEBUG
-/// Print all the relocations.
-template
-static void dumpRelocs(const char *Prefix, const Container &Relocs) {
- for (const auto &R : Relocs)
-dbgs() << Prefix << R << "\n";
-}
-#endif
-
MipsELFObjectWriter::MipsELFObjectWriter(uint8_t OSABI,
bool HasRelocationAddend, bool Is64)
: MCELFObjectTargetWriter(Is64, OSABI, ELF::EM_MIPS, HasRelocationAddend)
{}
@@ -448,8 +426,6 @@ void MipsELFObjectWriter::sortRelocs(const MCAssembler &Asm,
std::list Sorted;
std::list Remainder;
- LLVM_DEBUG(dumpRelocs("R: ", Relocs));
-
// Separate the movable relocations (AHL relocations using the high bits)
from
// the immobile relocations (everything else). This does not preserve
high/low
// matches that already existed in the input.
@@ -459,8 +435,6 @@ void MipsELFObjectWriter::sortRelocs(const MCAssembler &Asm,
});
for (auto &R : Remainder) {
-LLVM_DEBUG(dbgs() << "Matching: " << R << "\n");
-
unsigned MatchingType = getMatchingLoType(R);
assert(MatchingType != ELF::R_MIPS_NONE &&
"Wrong list for reloc that doesn't need a match");
@@ -494,8 +468,6 @@ void MipsELFObjectWriter::sortRelocs(const MCAssembler &Asm,
Sorted.insert(InsertionPoint, R)->Matched = true;
}
- LLVM_DEBUG(dumpRelocs("S: ", Sorted));
-
assert(Relocs.size() == Sorted.size() && "Some relocs were not consumed");
// Overwrite the original vector with the sorted elements.
From f139a3296123eb567c158fd1219b33e2263cc5f7 Mon Sep 17 00:00:00 2001
From: Fangrui Song
Date: Sun, 18 Aug 2024 15:47:38 -0700
Subject: [PATCH 2/3] [MC] Remove ELFRelocationEntry::OriginalAddend
For MIPS's o32 ABI (REL), https://reviews.llvm.org/D19718 introduced
`OriginalAddend` to find the matching R_MIPS_LO16 relocation for
R_MIPS_GOT16 when STT_SECTION conversion is applicable.
lw $2, %lo(local1)
lui $2, %got(local1)
However, we could just store the original `Addend` in
`ELFRelocationEntry` and remove `OriginalAddend`.
Note: The relocation ordering algorithm in
https://reviews.llvm.org/D19718 is inefficient (#104562), which will be
addressed by another patch.
---
llvm/include/llvm/MC/MCELFObjectWriter.h| 9 +++--
llvm/lib/MC/ELFObjectWriter.cpp | 17 ++---
.../Mips/MCTargetDesc/MipsELFObjectWriter.cpp | 9 -
3 files changed, 13 insertions(+), 22 deletions(-)
diff --git a/llvm/include/llvm/MC/MCELFObjectWriter.h
b/llvm/include/llvm/MC/MCELFObjectWriter.h
index 9b74cbc3d3a520..d48840c0f89877 100644
--- a/llvm/include/llvm/MC/MCELFObjectWriter.h
+++ b/llvm/include/llvm/MC/MCELFObjectWriter.h
@@ -38,18 +38,15 @@ struct ELFRelocationEntry {
unsigned Type; // The type of the relocation.
uint64_t Addend; // The addend to use.
const MCSymbolELF *OriginalSymbol; // The original
[llvm-branch-commits] [llvm] release/19.x: [MIPS] Optimize sortRelocs for o32 (PR #106008)
llvmbot wrote:
@llvm/pr-subscribers-mc
Author: Alex Rønne Petersen (alexrp)
Changes
Manual backport of #104723.
---
Full diff: https://github.com/llvm/llvm-project/pull/106008.diff
4 Files Affected:
- (modified) llvm/include/llvm/MC/MCELFObjectWriter.h (+3-8)
- (modified) llvm/lib/MC/ELFObjectWriter.cpp (+6-11)
- (modified) llvm/lib/Target/Mips/MCTargetDesc/MipsELFObjectWriter.cpp
(+43-117)
- (modified) llvm/test/MC/Mips/sort-relocation-table.s (+3-3)
``diff
diff --git a/llvm/include/llvm/MC/MCELFObjectWriter.h
b/llvm/include/llvm/MC/MCELFObjectWriter.h
index 9b74cbc3d3a520..cbb010fa2fd802 100644
--- a/llvm/include/llvm/MC/MCELFObjectWriter.h
+++ b/llvm/include/llvm/MC/MCELFObjectWriter.h
@@ -37,19 +37,14 @@ struct ELFRelocationEntry {
const MCSymbolELF *Symbol; // The symbol to relocate with.
unsigned Type; // The type of the relocation.
uint64_t Addend; // The addend to use.
- const MCSymbolELF *OriginalSymbol; // The original value of Symbol if we
changed it.
- uint64_t OriginalAddend; // The original value of addend.
ELFRelocationEntry(uint64_t Offset, const MCSymbolELF *Symbol, unsigned Type,
- uint64_t Addend, const MCSymbolELF *OriginalSymbol,
- uint64_t OriginalAddend)
- : Offset(Offset), Symbol(Symbol), Type(Type), Addend(Addend),
-OriginalSymbol(OriginalSymbol), OriginalAddend(OriginalAddend) {}
+ uint64_t Addend)
+ : Offset(Offset), Symbol(Symbol), Type(Type), Addend(Addend) {}
void print(raw_ostream &Out) const {
Out << "Off=" << Offset << ", Sym=" << Symbol << ", Type=" << Type
-<< ", Addend=" << Addend << ", OriginalSymbol=" << OriginalSymbol
-<< ", OriginalAddend=" << OriginalAddend;
+<< ", Addend=" << Addend;
}
LLVM_DUMP_METHOD void dump() const { print(errs()); }
diff --git a/llvm/lib/MC/ELFObjectWriter.cpp b/llvm/lib/MC/ELFObjectWriter.cpp
index f958905a26aa42..8e8705500126e7 100644
--- a/llvm/lib/MC/ELFObjectWriter.cpp
+++ b/llvm/lib/MC/ELFObjectWriter.cpp
@@ -1393,22 +1393,17 @@ void ELFObjectWriter::recordRelocation(MCAssembler &Asm,
bool RelocateWithSymbol =
shouldRelocateWithSymbol(Asm, Target, SymA, C, Type) ||
(Parent->getType() == ELF::SHT_LLVM_CALL_GRAPH_PROFILE);
- uint64_t Addend = 0;
-
- FixedValue = !RelocateWithSymbol && SymA && !SymA->isUndefined()
- ? C + Asm.getSymbolOffset(*SymA)
- : C;
- if (usesRela(TO, FixupSection)) {
-Addend = FixedValue;
-FixedValue = 0;
- }
+ uint64_t Addend = !RelocateWithSymbol && SymA && !SymA->isUndefined()
+? C + Asm.getSymbolOffset(*SymA)
+: C;
+ FixedValue = usesRela(TO, FixupSection) ? 0 : Addend;
if (!RelocateWithSymbol) {
const auto *SectionSymbol =
SecA ? cast(SecA->getBeginSymbol()) : nullptr;
if (SectionSymbol)
SectionSymbol->setUsedInReloc();
-ELFRelocationEntry Rec(FixupOffset, SectionSymbol, Type, Addend, SymA, C);
+ELFRelocationEntry Rec(FixupOffset, SectionSymbol, Type, Addend);
Relocations[&FixupSection].push_back(Rec);
return;
}
@@ -1423,7 +1418,7 @@ void ELFObjectWriter::recordRelocation(MCAssembler &Asm,
else
RenamedSymA->setUsedInReloc();
}
- ELFRelocationEntry Rec(FixupOffset, RenamedSymA, Type, Addend, SymA, C);
+ ELFRelocationEntry Rec(FixupOffset, RenamedSymA, Type, Addend);
Relocations[&FixupSection].push_back(Rec);
}
diff --git a/llvm/lib/Target/Mips/MCTargetDesc/MipsELFObjectWriter.cpp
b/llvm/lib/Target/Mips/MCTargetDesc/MipsELFObjectWriter.cpp
index 4d6a00c14a3575..faf9772ab75756 100644
--- a/llvm/lib/Target/Mips/MCTargetDesc/MipsELFObjectWriter.cpp
+++ b/llvm/lib/Target/Mips/MCTargetDesc/MipsELFObjectWriter.cpp
@@ -40,20 +40,8 @@ struct MipsRelocationEntry {
bool Matched = false; ///< Is this relocation part of a match.
MipsRelocationEntry(const ELFRelocationEntry &R) : R(R) {}
-
- void print(raw_ostream &Out) const {
-R.print(Out);
-Out << ", Matched=" << Matched;
- }
};
-#ifndef NDEBUG
-raw_ostream &operator<<(raw_ostream &OS, const MipsRelocationEntry &RHS) {
- RHS.print(OS);
- return OS;
-}
-#endif
-
class MipsELFObjectWriter : public MCELFObjectTargetWriter {
public:
MipsELFObjectWriter(uint8_t OSABI, bool HasRelocationAddend, bool Is64);
@@ -115,17 +103,11 @@ static InputIt find_best(InputIt First, InputIt Last,
UnaryPredicate Predicate,
for (InputIt I = First; I != Last; ++I) {
unsigned Matched = Predicate(*I);
if (Matched != FindBest_NoMatch) {
- LLVM_DEBUG(dbgs() << std::distance(First, I) << " is a match (";
- I->print(dbgs()); dbgs() << ")\n");
- if (Best == Last || BetterThan(*I, *Best)) {
-LLVM_DEBUG(dbgs() << ".. and it beats the last one\n");
+ if (Best == Last || BetterThan(*I, *Best))
Best = I;
- }
}
-if (Matched == FindBest_PerfectMatch)
[llvm-branch-commits] [llvm] release/19.x: [MIPS] Optimize sortRelocs for o32 (PR #106008)
alexrp wrote: cc @MaskRay @brad0 https://github.com/llvm/llvm-project/pull/106008 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [libc] [libc][math][c23] Add exp10m1f16 C23 math function (PR #105706)
@@ -606,6 +606,8 @@ def StdC : StandardSpec<"stdc"> {
FunctionSpec<"exp10f", RetValSpec, [ArgSpec]>,
GuardedFunctionSpec<"exp10f16", RetValSpec,
[ArgSpec], "LIBC_TYPES_HAS_FLOAT16">,
+ GuardedFunctionSpec<"exp10m1f16", RetValSpec,
[ArgSpec], "LIBC_TYPES_HAS_FLOAT16">,
lntue wrote:
also update new header gen.
https://github.com/llvm/llvm-project/pull/105706
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [libc] [libc][math][c23] Add exp10m1f16 C23 math function (PR #105706)
@@ -0,0 +1,162 @@
+//===-- Half-precision 10^x - 1 function
--===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM
Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===--===//
+
+#include "src/math/exp10m1f16.h"
+#include "expxf16.h"
+#include "hdr/errno_macros.h"
+#include "hdr/fenv_macros.h"
+#include "src/__support/FPUtil/FEnvImpl.h"
+#include "src/__support/FPUtil/FPBits.h"
+#include "src/__support/FPUtil/PolyEval.h"
+#include "src/__support/FPUtil/except_value_utils.h"
+#include "src/__support/FPUtil/multiply_add.h"
+#include "src/__support/FPUtil/rounding_mode.h"
+#include "src/__support/common.h"
+#include "src/__support/macros/config.h"
+#include "src/__support/macros/optimization.h"
+#include "src/__support/macros/properties/cpu_features.h"
+
+namespace LIBC_NAMESPACE_DECL {
+
+static constexpr fputil::ExceptValues EXP10M1F16_EXCEPTS_LO = {{
+// (input, RZ output, RU offset, RD offset, RN offset)
+// x = 0x1.5c4p-4, exp10m1f16(x) = 0x1.bacp-3 (RZ)
+{0x2d71U, 0x32ebU, 1U, 0U, 0U},
+// x = -0x1.5ep-13, exp10m1f16(x) = -0x1.92cp-12 (RZ)
+{0x8978U, 0x8e4bU, 0U, 1U, 0U},
+// x = -0x1.e2p-10, exp10m1f16(x) = -0x1.14cp-8 (RZ)
+{0x9788U, 0x9c53U, 0U, 1U, 0U},
+}};
+
+#ifdef LIBC_TARGET_CPU_HAS_FMA
+static constexpr size_t N_EXP10M1F16_EXCEPTS_HI = 3;
+#else
+static constexpr size_t N_EXP10M1F16_EXCEPTS_HI = 6;
+#endif
+
+static constexpr fputil::ExceptValues
+EXP10M1F16_EXCEPTS_HI = {{
+// (input, RZ output, RU offset, RD offset, RN offset)
+// x = 0x1.8f4p-2, exp10m1f16(x) = 0x1.744p+0 (RZ)
+{0x363dU, 0x3dd1U, 1U, 0U, 0U},
+// x = 0x1.95cp-2, exp10m1f16(x) = 0x1.7d8p+0 (RZ)
+{0x3657U, 0x3df6U, 1U, 0U, 0U},
+// x = 0x1.d04p-2, exp10m1f16(x) = 0x1.d7p+0 (RZ)
+{0x3741U, 0x3f5cU, 1U, 0U, 1U},
+#ifndef LIBC_TARGET_CPU_HAS_FMA
+// x = 0x1.0cp+1, exp10m1f16(x) = 0x1.ec4p+6 (RZ)
+{0x4030U, 0x57b1U, 1U, 0U, 1U},
+// x = 0x1.1b8p+1, exp10m1f16(x) = 0x1.45cp+7 (RZ)
+{0x406eU, 0x5917U, 1U, 0U, 1U},
+// x = 0x1.2f4p+2, exp10m1f16(x) = 0x1.ab8p+15 (RZ)
+{0x44bdU, 0x7aaeU, 1U, 0U, 1U},
+#endif
+}};
+
+LLVM_LIBC_FUNCTION(float16, exp10m1f16, (float16 x)) {
+ using FPBits = fputil::FPBits;
+ FPBits x_bits(x);
+
+ uint16_t x_u = x_bits.uintval();
+ uint16_t x_abs = x_u & 0x7fffU;
+
+ // When |x| <= 2^(-3), or |x| >= 11 * log10(2), or x is NaN.
+ if (LIBC_UNLIKELY(x_abs <= 0x3000U || x_abs >= 0x429fU)) {
+// exp10m1(NaN) = NaN
+if (x_bits.is_nan()) {
+ if (x_bits.is_signaling_nan()) {
+fputil::raise_except_if_required(FE_INVALID);
+return FPBits::quiet_nan().get_val();
+ }
+
+ return x;
+}
+
+// When x >= 16 * log10(2).
+if (x_u >= 0x44d1U && x_bits.is_pos()) {
+ // exp10m1(+inf) = +inf
+ if (x_bits.is_inf())
+return FPBits::inf().get_val();
+
+ switch (fputil::quick_get_round()) {
+ case FE_TONEAREST:
+ case FE_UPWARD:
+fputil::set_errno_if_required(ERANGE);
+fputil::raise_except_if_required(FE_OVERFLOW | FE_INEXACT);
+return FPBits::inf().get_val();
+ default:
+return FPBits::max_normal().get_val();
+ }
+}
+
+// When x < -11 * log10(2).
+if (x_u > 0xc29fU) {
+ // exp10m1(-inf) = -1
+ if (x_bits.is_inf())
+return FPBits::one(Sign::NEG).get_val();
+
+ // When x >= -0x1.ce4p+1, round(10^x - 1, HP, RN) = -0x1.ffcp-1.
+ if (x_u <= 0xc339U) {
+return fputil::round_result_slightly_down(
+static_cast(-0x1.ffcp-1));
+ }
+
+ // When x < -0x1.ce4p+1, round(10^x - 1, HP, RN) = -1.
+ switch (fputil::quick_get_round()) {
+ case FE_TONEAREST:
+ case FE_DOWNWARD:
+return FPBits::one(Sign::NEG).get_val();
+ default:
+return static_cast(-0x1.ffcp-1);
+ }
+}
+
+// When |x| <= 2^(-3).
+if (x_abs <= 0x3000U) {
+ if (auto r = EXP10M1F16_EXCEPTS_LO.lookup(x_u);
+ LIBC_UNLIKELY(r.has_value()))
+return r.value();
+
+ float xf = x;
+ // Degree-5 minimax polynomial generated by Sollya with the following
+ // commands:
+ // > display = hexadecimal;
+ // > P = fpminimax((10^x - 1)/x, 4, [|SG...|], [-2^-3, 2^-3]);
+ // > x * P;
+ return static_cast(
+ xf * fputil::polyeval(xf, 0x1.26bb1cp+1f, 0x1.5351c8p+1f,
+0x1.04704p+1f, 0x1.2ce084p+0f,
0x1.14a6bep-1f));
+}
+ }
+
+ // When x is 1, 2, or 3. These are hard-to-round cases with exact results.
+ // 10^4 - 1 = 9'999 is not exactly representable as a float16, but luckily
the
lntue wrote:
It's actually not luck, because the relative error of `9'999` to the
[llvm-branch-commits] [llvm] release/19.x: [MIPS] Optimize sortRelocs for o32 (PR #106008)
https://github.com/brad0 milestoned https://github.com/llvm/llvm-project/pull/106008 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] release/19.x: [Clang][Concepts] Fix the constraint equivalence checking involving parameter packs (#102131) (PR #106043)
https://github.com/llvmbot created
https://github.com/llvm/llvm-project/pull/106043
Backport e6974daa
Requested by: @zyn0217
>From f40c547eb78c91a9b35ae4ccefbf00c2983038e7 Mon Sep 17 00:00:00 2001
From: Younan Zhang
Date: Mon, 26 Aug 2024 14:30:26 +0800
Subject: [PATCH] [Clang][Concepts] Fix the constraint equivalence checking
involving parameter packs (#102131)
We established an instantiation scope in order for constraint
equivalence checking to properly map the uninstantiated parameters.
That mechanism mapped even packs to themselves. Consequently, parameter
packs e.g. appearing in a function call, were not expanded. So they
would end up becoming `SubstTemplateTypeParmPackType`s that circularly
depend on the canonical declaration of the function template, which is
not yet determined, hence the spurious error.
No release note as I plan to backport it to 19.
Fixes https://github.com/llvm/llvm-project/issues/101735
-
Co-authored-by: cor3ntin
(cherry picked from commit e6974daa7bc100c8b88057d50f3ec3eca7282243)
---
clang/lib/Sema/SemaConcept.cpp| 26 +--
.../SemaTemplate/concepts-out-of-line-def.cpp | 23
2 files changed, 47 insertions(+), 2 deletions(-)
diff --git a/clang/lib/Sema/SemaConcept.cpp b/clang/lib/Sema/SemaConcept.cpp
index c34d32002b5ad7..244f6ef2f53faa 100644
--- a/clang/lib/Sema/SemaConcept.cpp
+++ b/clang/lib/Sema/SemaConcept.cpp
@@ -969,8 +969,30 @@ static const Expr
*SubstituteConstraintExpressionWithoutSatisfaction(
// equivalence.
LocalInstantiationScope ScopeForParameters(S);
if (auto *FD = DeclInfo.getDecl()->getAsFunction())
-for (auto *PVD : FD->parameters())
- ScopeForParameters.InstantiatedLocal(PVD, PVD);
+for (auto *PVD : FD->parameters()) {
+ if (!PVD->isParameterPack()) {
+ScopeForParameters.InstantiatedLocal(PVD, PVD);
+continue;
+ }
+ // This is hacky: we're mapping the parameter pack to a size-of-1
argument
+ // to avoid building SubstTemplateTypeParmPackTypes for
+ // PackExpansionTypes. The SubstTemplateTypeParmPackType node would
+ // otherwise reference the AssociatedDecl of the template arguments,
which
+ // is, in this case, the template declaration.
+ //
+ // However, as we are in the process of comparing potential
+ // re-declarations, the canonical declaration is the declaration itself
at
+ // this point. So if we didn't expand these packs, we would end up with
an
+ // incorrect profile difference because we will be profiling the
+ // canonical types!
+ //
+ // FIXME: Improve the "no-transform" machinery in FindInstantiatedDecl so
+ // that we can eliminate the Scope in the cases where the declarations
are
+ // not necessarily instantiated. It would also benefit the noexcept
+ // specifier comparison.
+ ScopeForParameters.MakeInstantiatedLocalArgPack(PVD);
+ ScopeForParameters.InstantiatedLocalPackArg(PVD, PVD);
+}
std::optional ThisScope;
diff --git a/clang/test/SemaTemplate/concepts-out-of-line-def.cpp
b/clang/test/SemaTemplate/concepts-out-of-line-def.cpp
index 0142efcdc3ee86..333187b0d74ad6 100644
--- a/clang/test/SemaTemplate/concepts-out-of-line-def.cpp
+++ b/clang/test/SemaTemplate/concepts-out-of-line-def.cpp
@@ -599,3 +599,26 @@ template
unsigned long DerivedCollection::index() {}
} // namespace GH72557
+
+namespace GH101735 {
+
+template
+concept True = true;
+
+template
+class A {
+ template
+ void method(Ts&... ts)
+requires requires (T t) {
+ { t.method(static_cast(ts)...) } -> True;
+};
+};
+
+template
+template
+void A::method(Ts&... ts)
+ requires requires (T t) {
+{ t.method(static_cast(ts)...) } -> True;
+ } {}
+
+}
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] release/19.x: [Clang][Concepts] Fix the constraint equivalence checking involving parameter packs (#102131) (PR #106043)
https://github.com/llvmbot milestoned https://github.com/llvm/llvm-project/pull/106043 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] release/19.x: [Clang][Concepts] Fix the constraint equivalence checking involving parameter packs (#102131) (PR #106043)
llvmbot wrote: @zyn0217 What do you think about merging this PR to the release branch? https://github.com/llvm/llvm-project/pull/106043 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] release/19.x: [Clang][Concepts] Fix the constraint equivalence checking involving parameter packs (#102131) (PR #106043)
llvmbot wrote:
@llvm/pr-subscribers-clang
Author: None (llvmbot)
Changes
Backport e6974daa
Requested by: @zyn0217
---
Full diff: https://github.com/llvm/llvm-project/pull/106043.diff
2 Files Affected:
- (modified) clang/lib/Sema/SemaConcept.cpp (+24-2)
- (modified) clang/test/SemaTemplate/concepts-out-of-line-def.cpp (+23)
``diff
diff --git a/clang/lib/Sema/SemaConcept.cpp b/clang/lib/Sema/SemaConcept.cpp
index c34d32002b5ad7..244f6ef2f53faa 100644
--- a/clang/lib/Sema/SemaConcept.cpp
+++ b/clang/lib/Sema/SemaConcept.cpp
@@ -969,8 +969,30 @@ static const Expr
*SubstituteConstraintExpressionWithoutSatisfaction(
// equivalence.
LocalInstantiationScope ScopeForParameters(S);
if (auto *FD = DeclInfo.getDecl()->getAsFunction())
-for (auto *PVD : FD->parameters())
- ScopeForParameters.InstantiatedLocal(PVD, PVD);
+for (auto *PVD : FD->parameters()) {
+ if (!PVD->isParameterPack()) {
+ScopeForParameters.InstantiatedLocal(PVD, PVD);
+continue;
+ }
+ // This is hacky: we're mapping the parameter pack to a size-of-1
argument
+ // to avoid building SubstTemplateTypeParmPackTypes for
+ // PackExpansionTypes. The SubstTemplateTypeParmPackType node would
+ // otherwise reference the AssociatedDecl of the template arguments,
which
+ // is, in this case, the template declaration.
+ //
+ // However, as we are in the process of comparing potential
+ // re-declarations, the canonical declaration is the declaration itself
at
+ // this point. So if we didn't expand these packs, we would end up with
an
+ // incorrect profile difference because we will be profiling the
+ // canonical types!
+ //
+ // FIXME: Improve the "no-transform" machinery in FindInstantiatedDecl so
+ // that we can eliminate the Scope in the cases where the declarations
are
+ // not necessarily instantiated. It would also benefit the noexcept
+ // specifier comparison.
+ ScopeForParameters.MakeInstantiatedLocalArgPack(PVD);
+ ScopeForParameters.InstantiatedLocalPackArg(PVD, PVD);
+}
std::optional ThisScope;
diff --git a/clang/test/SemaTemplate/concepts-out-of-line-def.cpp
b/clang/test/SemaTemplate/concepts-out-of-line-def.cpp
index 0142efcdc3ee86..333187b0d74ad6 100644
--- a/clang/test/SemaTemplate/concepts-out-of-line-def.cpp
+++ b/clang/test/SemaTemplate/concepts-out-of-line-def.cpp
@@ -599,3 +599,26 @@ template
unsigned long DerivedCollection::index() {}
} // namespace GH72557
+
+namespace GH101735 {
+
+template
+concept True = true;
+
+template
+class A {
+ template
+ void method(Ts&... ts)
+requires requires (T t) {
+ { t.method(static_cast(ts)...) } -> True;
+};
+};
+
+template
+template
+void A::method(Ts&... ts)
+ requires requires (T t) {
+{ t.method(static_cast(ts)...) } -> True;
+ } {}
+
+}
``
https://github.com/llvm/llvm-project/pull/106043
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
