[llvm] [RuntimeLibCalls] Consistently disable unavailable libcalls (PR #116214)
Nikita Popov via llvm-commits
llvm-commits at lists.llvm.org
Thu Nov 14 06:26:44 PST 2024
https://github.com/nikic updated https://github.com/llvm/llvm-project/pull/116214
>From b28daf5039bd4af041483ae5c39fd0fc8b911dbf Mon Sep 17 00:00:00 2001
From: Nikita Popov <npopov at redhat.com>
Date: Thu, 14 Nov 2024 12:29:07 +0100
Subject: [PATCH 1/2] [RuntimeLibCalls] Consistently disable unavailable
libcalls
The logic for marking runtime libcalls unavailable currently
duplicates essentially the logic for some subset of targets,
where someone reported an issue and then someone went and fixed
the issue for that specific target. However, the availability
for most of these is completely target independent. In particular:
* MULO_I128 is never available in libgcc
* Various I128 libcalls are only available for 64-bit targets in
libgcc
* powi is never available in MSVCRT
Unify the logic for these, so we don't miss any targets. This
fixes https://github.com/llvm/llvm-project/issues/16778 on
AArch64, which is one of the targets that was previously missed
in this logic.
---
llvm/lib/IR/RuntimeLibcalls.cpp | 108 ++-----------------
llvm/test/CodeGen/AArch64/i128-math.ll | 144 ++++++++++++++++++-------
2 files changed, 115 insertions(+), 137 deletions(-)
diff --git a/llvm/lib/IR/RuntimeLibcalls.cpp b/llvm/lib/IR/RuntimeLibcalls.cpp
index 06167559a77697..e38fce764b6403 100644
--- a/llvm/lib/IR/RuntimeLibcalls.cpp
+++ b/llvm/lib/IR/RuntimeLibcalls.cpp
@@ -205,14 +205,6 @@ void RuntimeLibcallsInfo::initLibcalls(const Triple &TT) {
setLibcallName(RTLIB::FREXP_PPCF128, nullptr);
}
- if (TT.isAArch64()) {
- if (TT.isOSMSVCRT()) {
- // MSVCRT doesn't have powi; fall back to pow
- setLibcallName(RTLIB::POWI_F32, nullptr);
- setLibcallName(RTLIB::POWI_F64, nullptr);
- }
- }
-
// Disable most libcalls on AMDGPU.
if (TT.isAMDGPU()) {
for (int I = 0; I < RTLIB::UNKNOWN_LIBCALL; ++I) {
@@ -228,20 +220,10 @@ void RuntimeLibcallsInfo::initLibcalls(const Triple &TT) {
setLibcallName(static_cast<RTLIB::Libcall>(I), nullptr);
}
- if (TT.isARM() || TT.isThumb()) {
- // These libcalls are not available in 32-bit.
- setLibcallName(RTLIB::SHL_I128, nullptr);
- setLibcallName(RTLIB::SRL_I128, nullptr);
- setLibcallName(RTLIB::SRA_I128, nullptr);
- setLibcallName(RTLIB::MUL_I128, nullptr);
- setLibcallName(RTLIB::MULO_I64, nullptr);
- setLibcallName(RTLIB::MULO_I128, nullptr);
-
- if (TT.isOSMSVCRT()) {
- // MSVCRT doesn't have powi; fall back to pow
- setLibcallName(RTLIB::POWI_F32, nullptr);
- setLibcallName(RTLIB::POWI_F64, nullptr);
- }
+ if (TT.isOSMSVCRT()) {
+ // MSVCRT doesn't have powi; fall back to pow
+ setLibcallName(RTLIB::POWI_F32, nullptr);
+ setLibcallName(RTLIB::POWI_F64, nullptr);
}
if (TT.getArch() == Triple::ArchType::avr) {
@@ -262,37 +244,9 @@ void RuntimeLibcallsInfo::initLibcalls(const Triple &TT) {
setLibcallName(RTLIB::UREM_I32, nullptr);
}
- if (TT.getArch() == Triple::ArchType::hexagon) {
- // These cause problems when the shift amount is non-constant.
- setLibcallName(RTLIB::SHL_I128, nullptr);
- setLibcallName(RTLIB::SRL_I128, nullptr);
- setLibcallName(RTLIB::SRA_I128, nullptr);
- }
-
- if (TT.isLoongArch()) {
- if (!TT.isLoongArch64()) {
- // Set libcalls.
- setLibcallName(RTLIB::MUL_I128, nullptr);
- // The MULO libcall is not part of libgcc, only compiler-rt.
- setLibcallName(RTLIB::MULO_I64, nullptr);
- }
- // The MULO libcall is not part of libgcc, only compiler-rt.
- setLibcallName(RTLIB::MULO_I128, nullptr);
- }
-
- if (TT.isMIPS32()) {
- // These libcalls are not available in 32-bit.
- setLibcallName(RTLIB::SHL_I128, nullptr);
- setLibcallName(RTLIB::SRL_I128, nullptr);
- setLibcallName(RTLIB::SRA_I128, nullptr);
- setLibcallName(RTLIB::MUL_I128, nullptr);
- setLibcallName(RTLIB::MULO_I64, nullptr);
- setLibcallName(RTLIB::MULO_I128, nullptr);
- }
-
- if (TT.isPPC()) {
- if (!TT.isPPC64()) {
- // These libcalls are not available in 32-bit.
+ if (!TT.isWasm()) {
+ // These libcalls are only available in compiler-rt, not libgcc.
+ if (TT.isArch32Bit()) {
setLibcallName(RTLIB::SHL_I128, nullptr);
setLibcallName(RTLIB::SRL_I128, nullptr);
setLibcallName(RTLIB::SRA_I128, nullptr);
@@ -301,52 +255,4 @@ void RuntimeLibcallsInfo::initLibcalls(const Triple &TT) {
}
setLibcallName(RTLIB::MULO_I128, nullptr);
}
-
- if (TT.isRISCV32()) {
- // These libcalls are not available in 32-bit.
- setLibcallName(RTLIB::SHL_I128, nullptr);
- setLibcallName(RTLIB::SRL_I128, nullptr);
- setLibcallName(RTLIB::SRA_I128, nullptr);
- setLibcallName(RTLIB::MUL_I128, nullptr);
- setLibcallName(RTLIB::MULO_I64, nullptr);
- }
-
- if (TT.isSPARC()) {
- if (!TT.isSPARC64()) {
- // These libcalls are not available in 32-bit.
- setLibcallName(RTLIB::MULO_I64, nullptr);
- setLibcallName(RTLIB::MUL_I128, nullptr);
- setLibcallName(RTLIB::SHL_I128, nullptr);
- setLibcallName(RTLIB::SRL_I128, nullptr);
- setLibcallName(RTLIB::SRA_I128, nullptr);
- }
- setLibcallName(RTLIB::MULO_I128, nullptr);
- }
-
- if (TT.isSystemZ()) {
- setLibcallName(RTLIB::SRL_I128, nullptr);
- setLibcallName(RTLIB::SHL_I128, nullptr);
- setLibcallName(RTLIB::SRA_I128, nullptr);
- }
-
- if (TT.isX86()) {
- if (TT.getArch() == Triple::ArchType::x86) {
- // These libcalls are not available in 32-bit.
- setLibcallName(RTLIB::SHL_I128, nullptr);
- setLibcallName(RTLIB::SRL_I128, nullptr);
- setLibcallName(RTLIB::SRA_I128, nullptr);
- setLibcallName(RTLIB::MUL_I128, nullptr);
- // The MULO libcall is not part of libgcc, only compiler-rt.
- setLibcallName(RTLIB::MULO_I64, nullptr);
- }
-
- // The MULO libcall is not part of libgcc, only compiler-rt.
- setLibcallName(RTLIB::MULO_I128, nullptr);
-
- if (TT.isOSMSVCRT()) {
- // MSVCRT doesn't have powi; fall back to pow
- setLibcallName(RTLIB::POWI_F32, nullptr);
- setLibcallName(RTLIB::POWI_F64, nullptr);
- }
- }
}
diff --git a/llvm/test/CodeGen/AArch64/i128-math.ll b/llvm/test/CodeGen/AArch64/i128-math.ll
index 7c1d9141421fd3..9ae906249826d3 100644
--- a/llvm/test/CodeGen/AArch64/i128-math.ll
+++ b/llvm/test/CodeGen/AArch64/i128-math.ll
@@ -355,15 +355,41 @@ define i128 @i128_mul(i128 %x, i128 %y) {
define { i128, i8 } @i128_checked_mul(i128 %x, i128 %y) {
; CHECK-LABEL: i128_checked_mul:
; CHECK: // %bb.0:
-; CHECK-NEXT: stp x30, xzr, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT: .cfi_def_cfa_offset 16
-; CHECK-NEXT: .cfi_offset w30, -16
-; CHECK-NEXT: add x4, sp, #8
-; CHECK-NEXT: bl __muloti4
-; CHECK-NEXT: ldr x8, [sp, #8]
-; CHECK-NEXT: cmp x8, #0
+; CHECK-NEXT: asr x8, x1, #63
+; CHECK-NEXT: asr x11, x3, #63
+; CHECK-NEXT: umulh x13, x0, x2
+; CHECK-NEXT: mul x9, x2, x8
+; CHECK-NEXT: umulh x10, x2, x8
+; CHECK-NEXT: umulh x12, x11, x0
+; CHECK-NEXT: mul x14, x1, x2
+; CHECK-NEXT: add x10, x10, x9
+; CHECK-NEXT: madd x8, x3, x8, x10
+; CHECK-NEXT: madd x10, x11, x1, x12
+; CHECK-NEXT: mul x11, x11, x0
+; CHECK-NEXT: umulh x12, x1, x2
+; CHECK-NEXT: mul x15, x0, x3
+; CHECK-NEXT: add x10, x10, x11
+; CHECK-NEXT: adds x9, x11, x9
+; CHECK-NEXT: umulh x16, x0, x3
+; CHECK-NEXT: adc x10, x10, x8
+; CHECK-NEXT: adds x8, x14, x13
+; CHECK-NEXT: cinc x12, x12, hs
+; CHECK-NEXT: mul x11, x1, x3
+; CHECK-NEXT: adds x8, x15, x8
+; CHECK-NEXT: umulh x13, x1, x3
+; CHECK-NEXT: mov x1, x8
+; CHECK-NEXT: cinc x14, x16, hs
+; CHECK-NEXT: adds x12, x12, x14
+; CHECK-NEXT: mul x0, x0, x2
+; CHECK-NEXT: cset w14, hs
+; CHECK-NEXT: adds x11, x11, x12
+; CHECK-NEXT: asr x12, x8, #63
+; CHECK-NEXT: adc x13, x13, x14
+; CHECK-NEXT: adds x9, x11, x9
+; CHECK-NEXT: adc x10, x13, x10
+; CHECK-NEXT: cmp x9, x12
+; CHECK-NEXT: ccmp x10, x12, #0, eq
; CHECK-NEXT: cset w2, eq
-; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%1 = tail call { i128, i1 } @llvm.smul.with.overflow.i128(i128 %x, i128 %y)
%2 = extractvalue { i128, i1 } %1, 0
@@ -378,15 +404,41 @@ define { i128, i8 } @i128_checked_mul(i128 %x, i128 %y) {
define { i128, i8 } @i128_overflowing_mul(i128 %x, i128 %y) {
; CHECK-LABEL: i128_overflowing_mul:
; CHECK: // %bb.0:
-; CHECK-NEXT: stp x30, xzr, [sp, #-16]! // 8-byte Folded Spill
-; CHECK-NEXT: .cfi_def_cfa_offset 16
-; CHECK-NEXT: .cfi_offset w30, -16
-; CHECK-NEXT: add x4, sp, #8
-; CHECK-NEXT: bl __muloti4
-; CHECK-NEXT: ldr x8, [sp, #8]
-; CHECK-NEXT: cmp x8, #0
+; CHECK-NEXT: asr x8, x1, #63
+; CHECK-NEXT: asr x11, x3, #63
+; CHECK-NEXT: umulh x13, x0, x2
+; CHECK-NEXT: mul x9, x2, x8
+; CHECK-NEXT: umulh x10, x2, x8
+; CHECK-NEXT: umulh x12, x11, x0
+; CHECK-NEXT: mul x14, x1, x2
+; CHECK-NEXT: add x10, x10, x9
+; CHECK-NEXT: madd x8, x3, x8, x10
+; CHECK-NEXT: madd x10, x11, x1, x12
+; CHECK-NEXT: mul x11, x11, x0
+; CHECK-NEXT: umulh x12, x1, x2
+; CHECK-NEXT: mul x15, x0, x3
+; CHECK-NEXT: add x10, x10, x11
+; CHECK-NEXT: adds x9, x11, x9
+; CHECK-NEXT: umulh x16, x0, x3
+; CHECK-NEXT: adc x10, x10, x8
+; CHECK-NEXT: adds x8, x14, x13
+; CHECK-NEXT: cinc x12, x12, hs
+; CHECK-NEXT: mul x11, x1, x3
+; CHECK-NEXT: adds x8, x15, x8
+; CHECK-NEXT: umulh x13, x1, x3
+; CHECK-NEXT: mov x1, x8
+; CHECK-NEXT: cinc x14, x16, hs
+; CHECK-NEXT: adds x12, x12, x14
+; CHECK-NEXT: mul x0, x0, x2
+; CHECK-NEXT: cset w14, hs
+; CHECK-NEXT: adds x11, x11, x12
+; CHECK-NEXT: asr x12, x8, #63
+; CHECK-NEXT: adc x13, x13, x14
+; CHECK-NEXT: adds x9, x11, x9
+; CHECK-NEXT: adc x10, x13, x10
+; CHECK-NEXT: cmp x9, x12
+; CHECK-NEXT: ccmp x10, x12, #0, eq
; CHECK-NEXT: cset w2, ne
-; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%1 = tail call { i128, i1 } @llvm.smul.with.overflow.i128(i128 %x, i128 %y)
%2 = extractvalue { i128, i1 } %1, 0
@@ -400,26 +452,46 @@ define { i128, i8 } @i128_overflowing_mul(i128 %x, i128 %y) {
define i128 @i128_saturating_mul(i128 %x, i128 %y) {
; CHECK-LABEL: i128_saturating_mul:
; CHECK: // %bb.0:
-; CHECK-NEXT: str x30, [sp, #-32]! // 8-byte Folded Spill
-; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
-; CHECK-NEXT: .cfi_def_cfa_offset 32
-; CHECK-NEXT: .cfi_offset w19, -8
-; CHECK-NEXT: .cfi_offset w20, -16
-; CHECK-NEXT: .cfi_offset w30, -32
-; CHECK-NEXT: add x4, sp, #8
-; CHECK-NEXT: mov x19, x3
-; CHECK-NEXT: mov x20, x1
-; CHECK-NEXT: str xzr, [sp, #8]
-; CHECK-NEXT: bl __muloti4
-; CHECK-NEXT: eor x8, x19, x20
-; CHECK-NEXT: ldr x9, [sp, #8]
-; CHECK-NEXT: asr x8, x8, #63
-; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
-; CHECK-NEXT: cmp x9, #0
-; CHECK-NEXT: eor x10, x8, #0x7fffffffffffffff
-; CHECK-NEXT: csinv x0, x0, x8, eq
-; CHECK-NEXT: csel x1, x10, x1, ne
-; CHECK-NEXT: ldr x30, [sp], #32 // 8-byte Folded Reload
+; CHECK-NEXT: asr x8, x1, #63
+; CHECK-NEXT: asr x11, x3, #63
+; CHECK-NEXT: umulh x13, x0, x2
+; CHECK-NEXT: mul x9, x2, x8
+; CHECK-NEXT: umulh x10, x2, x8
+; CHECK-NEXT: umulh x12, x11, x0
+; CHECK-NEXT: mul x14, x1, x2
+; CHECK-NEXT: add x10, x10, x9
+; CHECK-NEXT: madd x8, x3, x8, x10
+; CHECK-NEXT: madd x10, x11, x1, x12
+; CHECK-NEXT: mul x11, x11, x0
+; CHECK-NEXT: umulh x12, x1, x2
+; CHECK-NEXT: mul x16, x0, x3
+; CHECK-NEXT: add x10, x10, x11
+; CHECK-NEXT: adds x9, x11, x9
+; CHECK-NEXT: umulh x15, x0, x3
+; CHECK-NEXT: adc x8, x10, x8
+; CHECK-NEXT: adds x10, x14, x13
+; CHECK-NEXT: cinc x12, x12, hs
+; CHECK-NEXT: mul x17, x1, x3
+; CHECK-NEXT: adds x10, x16, x10
+; CHECK-NEXT: umulh x11, x1, x3
+; CHECK-NEXT: cinc x13, x15, hs
+; CHECK-NEXT: adds x12, x12, x13
+; CHECK-NEXT: cset w13, hs
+; CHECK-NEXT: adds x12, x17, x12
+; CHECK-NEXT: adc x11, x11, x13
+; CHECK-NEXT: adds x9, x12, x9
+; CHECK-NEXT: asr x12, x10, #63
+; CHECK-NEXT: mul x13, x0, x2
+; CHECK-NEXT: adc x8, x11, x8
+; CHECK-NEXT: eor x11, x3, x1
+; CHECK-NEXT: eor x8, x8, x12
+; CHECK-NEXT: eor x9, x9, x12
+; CHECK-NEXT: asr x11, x11, #63
+; CHECK-NEXT: orr x8, x9, x8
+; CHECK-NEXT: eor x9, x11, #0x7fffffffffffffff
+; CHECK-NEXT: cmp x8, #0
+; CHECK-NEXT: csel x1, x9, x10, ne
+; CHECK-NEXT: csinv x0, x13, x11, eq
; CHECK-NEXT: ret
%1 = tail call { i128, i1 } @llvm.smul.with.overflow.i128(i128 %x, i128 %y)
%2 = extractvalue { i128, i1 } %1, 0
>From feb7fc8a86128f69b9fa62987582c4ed08cb66f7 Mon Sep 17 00:00:00 2001
From: Nikita Popov <npopov at redhat.com>
Date: Thu, 14 Nov 2024 15:26:18 +0100
Subject: [PATCH 2/2] try to fix xcore test
---
llvm/test/CodeGen/XCore/float-intrinsics.ll | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/llvm/test/CodeGen/XCore/float-intrinsics.ll b/llvm/test/CodeGen/XCore/float-intrinsics.ll
index 81350497a4f266..7bf16585ce0d5d 100644
--- a/llvm/test/CodeGen/XCore/float-intrinsics.ll
+++ b/llvm/test/CodeGen/XCore/float-intrinsics.ll
@@ -1,4 +1,4 @@
-; RUN: llc < %s -march=xcore | FileCheck %s
+; RUN: llc < %s -mtriple=xcore | FileCheck %s
declare double @llvm.cos.f64(double)
declare double @llvm.exp.f64(double)
declare double @llvm.exp2.f64(double)
More information about the llvm-commits
mailing list