Skip to content

Commit

Permalink
Merge pull request #42041 from JuliaLang/vc/llvm_13
Browse files Browse the repository at this point in the history 
Allow Julia to build on LLVM 13
  • Loading branch information
@vchuravy
vchuravy committed Sep 10, 2021
2 parents 1709f79 + 9e0d8e9 commit d7028da
Show file tree
Hide file tree
Showing 12 changed files with 923 additions and 6 deletions.
19 changes: 17 additions & 2 deletions deps/llvm.mk
View file
Original file line number Diff line number Diff line change
Expand Up @@ -508,16 +508,31 @@ $(eval $(call LLVM_PATCH,llvm-D88630-clang-cmake))
endif
$(eval $(call LLVM_PATCH,llvm-invalid-addrspacecast-sink)) # Still being upstreamed as D92210
$(eval $(call LLVM_PATCH,llvm-11-D93154-globalisel-as))
$(eval $(call LLVM_PATCH,llvm-11-D94813-mergeicmps))
$(eval $(call LLVM_PATCH,llvm-11-D94813-mergeicmps)) # remove for LLVM 14
$(eval $(call LLVM_PROJ_PATCH,llvm-11-AArch64-FastIsel-bug))
$(eval $(call LLVM_PATCH,llvm-12-D97435-AArch64-movaddrreg))
$(eval $(call LLVM_PROJ_PATCH,llvm-11-D97571-AArch64-loh)) # remove for LLVM 13
$(eval $(call LLVM_PROJ_PATCH,llvm-11-aarch64-addrspace)) # remove for LLVM 13
$(eval $(call LLVM_PROJ_PATCH,llvm-12-fde-symbols-aarch64)) # remove for LLVM 13
$(eval $(call LLVM_PROJ_PATCH,llvm-12-force-eh_frame-aarch64)) # remove for LLVM 13
$(eval $(call LLVM_PROJ_PATCH,llvm-12-D109203-stackprobe-x86)) # remove for LLVM 13
$(eval $(call LLVM_PROJ_PATCH,llvm-12-D109203-stackprobe-x86)) # remove for LLVM 14
endif # LLVM_VER 12.0

ifeq ($(LLVM_VER_SHORT),13.0)
$(eval $(call LLVM_PATCH,llvm7-revert-D44485)) # Needs upstreaming
# $(eval $(call LLVM_PROJ_PATCH,llvm-13-D75072-SCEV-add-type)) # Should no longer be necessary
$(eval $(call LLVM_PATCH,llvm-julia-tsan-custom-as))
ifeq ($(BUILD_LLVM_CLANG),1)
$(eval $(call LLVM_PATCH,llvm-D88630-clang-cmake))
endif
$(eval $(call LLVM_PATCH,llvm-invalid-addrspacecast-sink)) # Still being upstreamed as D92210
$(eval $(call LLVM_PATCH,llvm-11-D93154-globalisel-as))
$(eval $(call LLVM_PATCH,llvm-11-D94813-mergeicmps)) # remove for LLVM 14
$(eval $(call LLVM_PATCH,llvm-13-AArch64-FastIsel-bug))
$(eval $(call LLVM_PATCH,llvm-13-D97435-AArch64-movaddrreg))
$(eval $(call LLVM_PROJ_PATCH,llvm-13-D109203-stackprobe-x86)) # remove for LLVM 14 (nominated for backport)
endif # LLVM_VER 13.0

# Add a JL prefix to the version map. DO NOT REMOVE
ifneq ($(LLVM_VER), svn)
$(eval $(call LLVM_PATCH,llvm7-symver-jlprefix))
Expand Down
42 changes: 42 additions & 0 deletions deps/patches/llvm-13-AArch64-FastIsel-bug.patch
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,42 @@
From d82434785ecab16223a0bd4ec8ede020bf244003 Mon Sep 17 00:00:00 2001
From: Keno Fischer <keno@juliacomputing.com>
Date: Mon, 1 Mar 2021 16:42:05 -0500
Subject: [PATCH 4/4] AArch64: Remove Bad optimization

Removes the code responsible for causing https://bugs.llvm.org/show_bug.cgi?id=49357.
A fix is in progress upstream, but I don't think it's easy, so this
fixes the bug in the meantime. The optimization it does is minor.
---
llvm/lib/Target/AArch64/AArch64FastISel.cpp | 19 ---------------------
1 file changed, 19 deletions(-)

diff --git llvm/lib/Target/AArch64/AArch64FastISel.cpp llvm/lib/Target/AArch64/AArch64FastISel.cpp
index 9acda17b816f..5f0c7922569b 100644
--- llvm/lib/Target/AArch64/AArch64FastISel.cpp
+++ llvm/lib/Target/AArch64/AArch64FastISel.cpp
@@ -4494,25 +4494,6 @@ bool AArch64FastISel::selectIntExt(const Instruction *I) {
if (!SrcReg)
return false;

- // Try to optimize already sign-/zero-extended values from function arguments.
- bool IsZExt = isa<ZExtInst>(I);
- if (const auto *Arg = dyn_cast<Argument>(I->getOperand(0))) {
- if ((IsZExt && Arg->hasZExtAttr()) || (!IsZExt && Arg->hasSExtAttr())) {
- if (RetVT == MVT::i64 && SrcVT != MVT::i64) {
- unsigned ResultReg = createResultReg(&AArch64::GPR64RegClass);
- BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc,
- TII.get(AArch64::SUBREG_TO_REG), ResultReg)
- .addImm(0)
- .addReg(SrcReg)
- .addImm(AArch64::sub_32);
- SrcReg = ResultReg;
- }
-
- updateValueMap(I, SrcReg);
- return true;
- }
- }
-
unsigned ResultReg = emitIntExt(SrcVT, SrcReg, RetVT, IsZExt);
if (!ResultReg)
return false;
157 changes: 157 additions & 0 deletions deps/patches/llvm-13-D109203-stackprobe-x86.patch
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,157 @@
From d914f133f8d6770cfd230e1b55aef67c16d19473 Mon Sep 17 00:00:00 2001
From: Elliot Saba <staticfloat@gmail.com>
Date: Tue, 7 Sep 2021 10:10:49 -0400
Subject: [PATCH] [X86] Don't clobber EBX in stackprobes

On X86, the stackprobe emission code chooses the `R11D` register, which
is illegal on i686. This ends up wrapping around to `EBX`, which does
not get properly callee-saved within the stack probing prologue,
clobbering the register for the callers.

We fix this by explicitly using `EAX` as the stack probe register.

Reviewed By: pengfei

Differential Revision: https://reviews.llvm.org/D109203
---
llvm/lib/Target/X86/X86FrameLowering.cpp | 8 +-
llvm/test/CodeGen/X86/stack-clash-large.ll | 97 +++++++++++++---------
2 files changed, 64 insertions(+), 41 deletions(-)

diff --git a/llvm/lib/Target/X86/X86FrameLowering.cpp b/llvm/lib/Target/X86/X86FrameLowering.cpp
index 4cde7971e597..86cb86b19d62 100644
--- a/llvm/lib/Target/X86/X86FrameLowering.cpp
+++ b/llvm/lib/Target/X86/X86FrameLowering.cpp
@@ -671,7 +671,9 @@ void X86FrameLowering::emitStackProbeInlineGenericLoop(
MF.insert(MBBIter, testMBB);
MF.insert(MBBIter, tailMBB);

- Register FinalStackProbed = Uses64BitFramePtr ? X86::R11 : X86::R11D;
+ Register FinalStackProbed = Uses64BitFramePtr ? X86::R11
+ : Is64Bit ? X86::R11D
+ : X86::EAX;
BuildMI(MBB, MBBI, DL, TII.get(TargetOpcode::COPY), FinalStackProbed)
.addReg(StackPtr)
.setMIFlag(MachineInstr::FrameSetup);
@@ -1092,7 +1094,9 @@ void X86FrameLowering::BuildStackAlignAND(MachineBasicBlock &MBB,
MF.insert(MBBIter, bodyMBB);
MF.insert(MBBIter, footMBB);
const unsigned MovMIOpc = Is64Bit ? X86::MOV64mi32 : X86::MOV32mi;
- Register FinalStackProbed = Uses64BitFramePtr ? X86::R11 : X86::R11D;
+ Register FinalStackProbed = Uses64BitFramePtr ? X86::R11
+ : Is64Bit ? X86::R11D
+ : X86::EAX;

// Setup entry block
{
diff --git a/llvm/test/CodeGen/X86/stack-clash-large.ll b/llvm/test/CodeGen/X86/stack-clash-large.ll
index 9129e4ed40fd..00c7843b54f5 100644
--- a/llvm/test/CodeGen/X86/stack-clash-large.ll
+++ b/llvm/test/CodeGen/X86/stack-clash-large.ll
@@ -1,45 +1,64 @@
-; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --no_x86_scrub_sp
-; RUN: llc -mtriple=x86_64-linux-android < %s | FileCheck -check-prefix=CHECK-X86-64 %s
-; RUN: llc -mtriple=i686-linux-android < %s | FileCheck -check-prefix=CHECK-X86-32 %s
+; RUN: llc -mtriple=x86_64-linux-android < %s | FileCheck -check-prefix=CHECK-X64 %s
+; RUN: llc -mtriple=i686-linux-android < %s | FileCheck -check-prefix=CHECK-X86 %s
+; RUN: llc -mtriple=x86_64-linux-gnux32 < %s | FileCheck -check-prefix=CHECK-X32 %s

define i32 @foo() local_unnamed_addr #0 {
-; CHECK-X86-64-LABEL: foo:
-; CHECK-X86-64: # %bb.0:
-; CHECK-X86-64-NEXT: movq %rsp, %r11
-; CHECK-X86-64-NEXT: subq $69632, %r11 # imm = 0x11000
-; CHECK-X86-64-NEXT: .LBB0_1: # =>This Inner Loop Header: Depth=1
-; CHECK-X86-64-NEXT: subq $4096, %rsp # imm = 0x1000
-; CHECK-X86-64-NEXT: movq $0, (%rsp)
-; CHECK-X86-64-NEXT: cmpq %r11, %rsp
-; CHECK-X86-64-NEXT: jne .LBB0_1
-; CHECK-X86-64-NEXT: # %bb.2:
-; CHECK-X86-64-NEXT: subq $2248, %rsp # imm = 0x8C8
-; CHECK-X86-64-NEXT: .cfi_def_cfa_offset 71888
-; CHECK-X86-64-NEXT: movl $1, 264(%rsp)
-; CHECK-X86-64-NEXT: movl $1, 28664(%rsp)
-; CHECK-X86-64-NEXT: movl -128(%rsp), %eax
-; CHECK-X86-64-NEXT: addq $71880, %rsp # imm = 0x118C8
-; CHECK-X86-64-NEXT: .cfi_def_cfa_offset 8
-; CHECK-X86-64-NEXT: retq
+; CHECK-X64-LABEL: foo:
+; CHECK-X64: # %bb.0:
+; CHECK-X64-NEXT: movq %rsp, %r11
+; CHECK-X64-NEXT: subq $69632, %r11 # imm = 0x11000
+; CHECK-X64-NEXT: .LBB0_1: # =>This Inner Loop Header: Depth=1
+; CHECK-X64-NEXT: subq $4096, %rsp # imm = 0x1000
+; CHECK-X64-NEXT: movq $0, (%rsp)
+; CHECK-X64-NEXT: cmpq %r11, %rsp
+; CHECK-X64-NEXT: jne .LBB0_1
+; CHECK-X64-NEXT: # %bb.2:
+; CHECK-X64-NEXT: subq $2248, %rsp # imm = 0x8C8
+; CHECK-X64-NEXT: .cfi_def_cfa_offset 71888
+; CHECK-X64-NEXT: movl $1, 264(%rsp)
+; CHECK-X64-NEXT: movl $1, 28664(%rsp)
+; CHECK-X64-NEXT: movl -128(%rsp), %eax
+; CHECK-X64-NEXT: addq $71880, %rsp # imm = 0x118C8
+; CHECK-X64-NEXT: .cfi_def_cfa_offset 8
+; CHECK-X64-NEXT: retq
;
-; CHECK-X86-32-LABEL: foo:
-; CHECK-X86-32: # %bb.0:
-; CHECK-X86-32-NEXT: movl %esp, %r11d
-; CHECK-X86-32-NEXT: subl $69632, %r11d # imm = 0x11000
-; CHECK-X86-32-NEXT: .LBB0_1: # =>This Inner Loop Header: Depth=1
-; CHECK-X86-32-NEXT: subl $4096, %esp # imm = 0x1000
-; CHECK-X86-32-NEXT: movl $0, (%esp)
-; CHECK-X86-32-NEXT: cmpl %r11d, %esp
-; CHECK-X86-32-NEXT: jne .LBB0_1
-; CHECK-X86-32-NEXT: # %bb.2:
-; CHECK-X86-32-NEXT: subl $2380, %esp # imm = 0x94C
-; CHECK-X86-32-NEXT: .cfi_def_cfa_offset 72016
-; CHECK-X86-32-NEXT: movl $1, 392(%esp)
-; CHECK-X86-32-NEXT: movl $1, 28792(%esp)
-; CHECK-X86-32-NEXT: movl (%esp), %eax
-; CHECK-X86-32-NEXT: addl $72012, %esp # imm = 0x1194C
-; CHECK-X86-32-NEXT: .cfi_def_cfa_offset 4
-; CHECK-X86-32-NEXT: retl
+; CHECK-X86-LABEL: foo:
+; CHECK-X86: # %bb.0:
+; CHECK-X86-NEXT: movl %esp, %eax
+; CHECK-X86-NEXT: subl $69632, %eax # imm = 0x11000
+; CHECK-X86-NEXT: .LBB0_1: # =>This Inner Loop Header: Depth=1
+; CHECK-X86-NEXT: subl $4096, %esp # imm = 0x1000
+; CHECK-X86-NEXT: movl $0, (%esp)
+; CHECK-X86-NEXT: cmpl %eax, %esp
+; CHECK-X86-NEXT: jne .LBB0_1
+; CHECK-X86-NEXT: # %bb.2:
+; CHECK-X86-NEXT: subl $2380, %esp # imm = 0x94C
+; CHECK-X86-NEXT: .cfi_def_cfa_offset 72016
+; CHECK-X86-NEXT: movl $1, 392(%esp)
+; CHECK-X86-NEXT: movl $1, 28792(%esp)
+; CHECK-X86-NEXT: movl (%esp), %eax
+; CHECK-X86-NEXT: addl $72012, %esp # imm = 0x1194C
+; CHECK-X86-NEXT: .cfi_def_cfa_offset 4
+; CHECK-X86-NEXT: retl
+;
+; CHECK-X32-LABEL: foo:
+; CHECK-X32: # %bb.0:
+; CHECK-X32-NEXT: movl %esp, %r11d
+; CHECK-X32-NEXT: subl $69632, %r11d # imm = 0x11000
+; CHECK-X32-NEXT: .LBB0_1: # =>This Inner Loop Header: Depth=1
+; CHECK-X32-NEXT: subl $4096, %esp # imm = 0x1000
+; CHECK-X32-NEXT: movq $0, (%esp)
+; CHECK-X32-NEXT: cmpl %r11d, %esp
+; CHECK-X32-NEXT: jne .LBB0_1
+; CHECK-X32-NEXT: # %bb.2:
+; CHECK-X32-NEXT: subl $2248, %esp # imm = 0x8C8
+; CHECK-X32-NEXT: .cfi_def_cfa_offset 71888
+; CHECK-X32-NEXT: movl $1, 264(%esp)
+; CHECK-X32-NEXT: movl $1, 28664(%esp)
+; CHECK-X32-NEXT: movl -128(%esp), %eax
+; CHECK-X32-NEXT: addl $71880, %esp # imm = 0x118C8
+; CHECK-X32-NEXT: .cfi_def_cfa_offset 8
+; CHECK-X32-NEXT: retq
%a = alloca i32, i64 18000, align 16
%b0 = getelementptr inbounds i32, i32* %a, i64 98
%b1 = getelementptr inbounds i32, i32* %a, i64 7198
--
2.33.0

Loading

0 comments on commit d7028da

Please sign in to comment.