maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/legalize-shl-vec.ll

257 lines
8.8 KiB
LLVM
Raw Normal View History

[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s --check-prefix=CHECK --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=CHECK --check-prefix=X64
Reapply fixed r241790: Fix shift legalization and lowering for big constants. Summary: If shift amount is a constant value > 64 bit it is handled incorrectly during type legalization and X86 lowering. This patch the type of shift amount argument in function DAGTypeLegalizer::ExpandShiftByConstant from unsigned to APInt. Reviewers: nadav, majnemer, sanjoy, RKSimon Subscribers: RKSimon, llvm-commits Differential Revision: http://reviews.llvm.org/D10767 llvm-svn: 241806
2015-07-09 22:58:04 +08:00
define <2 x i256> @test_shl(<2 x i256> %In) {
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-LABEL: test_shl:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0:
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
; X32-NEXT: shldl $2, %edx, %ecx
; X32-NEXT: movl %ecx, 60(%eax)
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: shldl $2, %ecx, %edx
; X32-NEXT: movl %edx, 56(%eax)
; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
; X32-NEXT: shldl $2, %edx, %ecx
; X32-NEXT: movl %ecx, 52(%eax)
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: shldl $2, %ecx, %edx
; X32-NEXT: movl %edx, 48(%eax)
; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
; X32-NEXT: shldl $2, %edx, %ecx
; X32-NEXT: movl %ecx, 44(%eax)
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: shldl $2, %ecx, %edx
; X32-NEXT: movl %edx, 40(%eax)
; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
; X32-NEXT: shldl $2, %edx, %ecx
; X32-NEXT: movl %ecx, 36(%eax)
; X32-NEXT: shll $2, %edx
; X32-NEXT: movl %edx, 32(%eax)
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: shll $31, %ecx
; X32-NEXT: movl %ecx, 28(%eax)
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-NEXT: movl $0, 24(%eax)
; X32-NEXT: movl $0, 20(%eax)
; X32-NEXT: movl $0, 16(%eax)
; X32-NEXT: movl $0, 12(%eax)
; X32-NEXT: movl $0, 8(%eax)
; X32-NEXT: movl $0, 4(%eax)
; X32-NEXT: movl $0, (%eax)
; X32-NEXT: retl $4
;
; X64-LABEL: test_shl:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0:
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: movq %rdi, %rax
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X64-NEXT: movq {{[0-9]+}}(%rsp), %rcx
; X64-NEXT: movq {{[0-9]+}}(%rsp), %rdx
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
; X64-NEXT: movq {{[0-9]+}}(%rsp), %rdi
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: shldq $2, %rcx, %rdx
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
; X64-NEXT: shldq $2, %rdi, %rcx
; X64-NEXT: shldq $2, %r9, %rdi
; X64-NEXT: shlq $63, %rsi
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X64-NEXT: shlq $2, %r9
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
; X64-NEXT: movq %rdx, 56(%rax)
; X64-NEXT: movq %rcx, 48(%rax)
; X64-NEXT: movq %rdi, 40(%rax)
; X64-NEXT: movq %r9, 32(%rax)
; X64-NEXT: movq %rsi, 24(%rax)
[X86][DAG] Switch X86 Target to post-legalized store merge Move store merge to happen after intrinsic lowering to allow lowered stores to be merged. Some regressions due in MergeConsecutiveStores to missing insert_subvector that are addressed in follow up patch. Reviewers: craig.topper, efriedma, RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D34559 llvm-svn: 310710
2017-08-11 21:21:35 +08:00
; X64-NEXT: xorps %xmm0, %xmm0
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
; X64-NEXT: movaps %xmm0, (%rax)
; X64-NEXT: movq $0, 16(%rax)
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X64-NEXT: retq
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
%Amt = insertelement <2 x i256> <i256 1, i256 2>, i256 255, i32 0
Reapply fixed r241790: Fix shift legalization and lowering for big constants. Summary: If shift amount is a constant value > 64 bit it is handled incorrectly during type legalization and X86 lowering. This patch the type of shift amount argument in function DAGTypeLegalizer::ExpandShiftByConstant from unsigned to APInt. Reviewers: nadav, majnemer, sanjoy, RKSimon Subscribers: RKSimon, llvm-commits Differential Revision: http://reviews.llvm.org/D10767 llvm-svn: 241806
2015-07-09 22:58:04 +08:00
%Out = shl <2 x i256> %In, %Amt
ret <2 x i256> %Out
}
define <2 x i256> @test_srl(<2 x i256> %In) {
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-LABEL: test_srl:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0:
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: pushl %ebp
; X32-NEXT: .cfi_def_cfa_offset 8
; X32-NEXT: pushl %ebx
; X32-NEXT: .cfi_def_cfa_offset 12
; X32-NEXT: pushl %edi
; X32-NEXT: .cfi_def_cfa_offset 16
; X32-NEXT: pushl %esi
; X32-NEXT: .cfi_def_cfa_offset 20
; X32-NEXT: subl $8, %esp
; X32-NEXT: .cfi_def_cfa_offset 28
; X32-NEXT: .cfi_offset %esi, -20
; X32-NEXT: .cfi_offset %edi, -16
; X32-NEXT: .cfi_offset %ebx, -12
; X32-NEXT: .cfi_offset %ebp, -8
; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movl {{[0-9]+}}(%esp), %esi
; X32-NEXT: movl {{[0-9]+}}(%esp), %edi
; X32-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X32-NEXT: movl {{[0-9]+}}(%esp), %ebp
; X32-NEXT: movl %edx, %ecx
; X32-NEXT: shldl $28, %eax, %ecx
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X32-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: shldl $28, %esi, %eax
; X32-NEXT: movl %eax, (%esp) # 4-byte Spill
; X32-NEXT: shldl $28, %edi, %esi
; X32-NEXT: shldl $28, %ebx, %edi
; X32-NEXT: shldl $28, %ebp, %ebx
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: shldl $28, %eax, %ebp
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: shrdl $4, %eax, %ecx
; X32-NEXT: shrl $4, %edx
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movl %edx, 60(%eax)
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X32-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: movl %edx, 56(%eax)
; X32-NEXT: movl (%esp), %edx # 4-byte Reload
; X32-NEXT: movl %edx, 52(%eax)
; X32-NEXT: movl %esi, 48(%eax)
; X32-NEXT: movl %edi, 44(%eax)
; X32-NEXT: movl %ebx, 40(%eax)
; X32-NEXT: movl %ebp, 36(%eax)
; X32-NEXT: movl %ecx, 32(%eax)
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: shrl $31, %ecx
; X32-NEXT: movl %ecx, (%eax)
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-NEXT: movl $0, 28(%eax)
; X32-NEXT: movl $0, 24(%eax)
; X32-NEXT: movl $0, 20(%eax)
; X32-NEXT: movl $0, 16(%eax)
; X32-NEXT: movl $0, 12(%eax)
; X32-NEXT: movl $0, 8(%eax)
; X32-NEXT: movl $0, 4(%eax)
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: addl $8, %esp
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X32-NEXT: .cfi_def_cfa_offset 20
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: popl %esi
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X32-NEXT: .cfi_def_cfa_offset 16
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: popl %edi
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X32-NEXT: .cfi_def_cfa_offset 12
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: popl %ebx
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X32-NEXT: .cfi_def_cfa_offset 8
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: popl %ebp
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X32-NEXT: .cfi_def_cfa_offset 4
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-NEXT: retl $4
;
; X64-LABEL: test_srl:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0:
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: movq %rdi, %rax
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X64-NEXT: movq {{[0-9]+}}(%rsp), %rcx
; X64-NEXT: movq {{[0-9]+}}(%rsp), %rdx
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: movq {{[0-9]+}}(%rsp), %rsi
; X64-NEXT: shrdq $4, %rsi, %r9
; X64-NEXT: shrdq $4, %rcx, %rsi
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
; X64-NEXT: shrq $63, %r8
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: shrdq $4, %rdx, %rcx
; X64-NEXT: shrq $4, %rdx
; X64-NEXT: movq %rdx, 56(%rdi)
; X64-NEXT: movq %rcx, 48(%rdi)
; X64-NEXT: movq %rsi, 40(%rdi)
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X64-NEXT: movq %r9, 32(%rdi)
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
; X64-NEXT: movq %r8, (%rdi)
[X86][DAG] Switch X86 Target to post-legalized store merge Move store merge to happen after intrinsic lowering to allow lowered stores to be merged. Some regressions due in MergeConsecutiveStores to missing insert_subvector that are addressed in follow up patch. Reviewers: craig.topper, efriedma, RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D34559 llvm-svn: 310710
2017-08-11 21:21:35 +08:00
; X64-NEXT: xorps %xmm0, %xmm0
; X64-NEXT: movaps %xmm0, 16(%rdi)
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
; X64-NEXT: movq $0, 8(%rdi)
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X64-NEXT: retq
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
%Amt = insertelement <2 x i256> <i256 3, i256 4>, i256 255, i32 0
Reapply fixed r241790: Fix shift legalization and lowering for big constants. Summary: If shift amount is a constant value > 64 bit it is handled incorrectly during type legalization and X86 lowering. This patch the type of shift amount argument in function DAGTypeLegalizer::ExpandShiftByConstant from unsigned to APInt. Reviewers: nadav, majnemer, sanjoy, RKSimon Subscribers: RKSimon, llvm-commits Differential Revision: http://reviews.llvm.org/D10767 llvm-svn: 241806
2015-07-09 22:58:04 +08:00
%Out = lshr <2 x i256> %In, %Amt
ret <2 x i256> %Out
}
define <2 x i256> @test_sra(<2 x i256> %In) {
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-LABEL: test_sra:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X32: # %bb.0:
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: pushl %ebp
; X32-NEXT: .cfi_def_cfa_offset 8
; X32-NEXT: pushl %ebx
; X32-NEXT: .cfi_def_cfa_offset 12
; X32-NEXT: pushl %edi
; X32-NEXT: .cfi_def_cfa_offset 16
; X32-NEXT: pushl %esi
; X32-NEXT: .cfi_def_cfa_offset 20
; X32-NEXT: subl $8, %esp
; X32-NEXT: .cfi_def_cfa_offset 28
; X32-NEXT: .cfi_offset %esi, -20
; X32-NEXT: .cfi_offset %edi, -16
; X32-NEXT: .cfi_offset %ebx, -12
; X32-NEXT: .cfi_offset %ebp, -8
; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %esi
; X32-NEXT: movl {{[0-9]+}}(%esp), %edi
; X32-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X32-NEXT: movl {{[0-9]+}}(%esp), %ebp
; X32-NEXT: movl %edx, %ecx
; X32-NEXT: shldl $26, %eax, %ecx
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X32-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: shldl $26, %esi, %eax
; X32-NEXT: movl %eax, (%esp) # 4-byte Spill
; X32-NEXT: shldl $26, %edi, %esi
; X32-NEXT: shldl $26, %ebx, %edi
; X32-NEXT: shldl $26, %ebp, %ebx
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: shldl $26, %eax, %ebp
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: shrdl $6, %eax, %ecx
; X32-NEXT: sarl $6, %edx
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movl %edx, 60(%eax)
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X32-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: movl %edx, 56(%eax)
; X32-NEXT: movl (%esp), %edx # 4-byte Reload
; X32-NEXT: movl %edx, 52(%eax)
; X32-NEXT: movl %esi, 48(%eax)
; X32-NEXT: movl %edi, 44(%eax)
; X32-NEXT: movl %ebx, 40(%eax)
; X32-NEXT: movl %ebp, 36(%eax)
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-NEXT: movl %ecx, 32(%eax)
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: sarl $31, %ecx
; X32-NEXT: movl %ecx, 28(%eax)
; X32-NEXT: movl %ecx, 24(%eax)
; X32-NEXT: movl %ecx, 20(%eax)
; X32-NEXT: movl %ecx, 16(%eax)
; X32-NEXT: movl %ecx, 12(%eax)
; X32-NEXT: movl %ecx, 8(%eax)
; X32-NEXT: movl %ecx, 4(%eax)
; X32-NEXT: movl %ecx, (%eax)
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: addl $8, %esp
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X32-NEXT: .cfi_def_cfa_offset 20
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: popl %esi
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X32-NEXT: .cfi_def_cfa_offset 16
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: popl %edi
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X32-NEXT: .cfi_def_cfa_offset 12
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: popl %ebx
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X32-NEXT: .cfi_def_cfa_offset 8
[x86] preserve test intent by removing undef D43141 proposes to correct undef folding in the DAG, and this test would not survive that change. llvm-svn: 324816
2018-02-10 23:28:08 +08:00
; X32-NEXT: popl %ebp
Correct dwarf unwind information in function epilogue This patch aims to provide correct dwarf unwind information in function epilogue for X86. It consists of two parts. The first part inserts CFI instructions that set appropriate cfa offset and cfa register in emitEpilogue() in X86FrameLowering. This part is X86 specific. The second part is platform independent and ensures that: * CFI instructions do not affect code generation (they are not counted as instructions when tail duplicating or tail merging) * Unwind information remains correct when a function is modified by different passes. This is done in a late pass by analyzing information about cfa offset and cfa register in BBs and inserting additional CFI directives where necessary. Added CFIInstrInserter pass: * analyzes each basic block to determine cfa offset and register are valid at its entry and exit * verifies that outgoing cfa offset and register of predecessor blocks match incoming values of their successors * inserts additional CFI directives at basic block beginning to correct the rule for calculating CFA Having CFI instructions in function epilogue can cause incorrect CFA calculation rule for some basic blocks. This can happen if, due to basic block reordering, or the existence of multiple epilogue blocks, some of the blocks have wrong cfa offset and register values set by the epilogue block above them. CFIInstrInserter is currently run only on X86, but can be used by any target that implements support for adding CFI instructions in epilogue. Patch by Violeta Vukobrat. Differential Revision: https://reviews.llvm.org/D42848 llvm-svn: 330706
2018-04-24 18:32:08 +08:00
; X32-NEXT: .cfi_def_cfa_offset 4
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X32-NEXT: retl $4
;
; X64-LABEL: test_sra:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; X64: # %bb.0:
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: movq %rdi, %rax
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X64-NEXT: movq {{[0-9]+}}(%rsp), %rcx
; X64-NEXT: movq {{[0-9]+}}(%rsp), %rdx
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: movq {{[0-9]+}}(%rsp), %rsi
; X64-NEXT: shrdq $6, %rsi, %r9
; X64-NEXT: shrdq $6, %rcx, %rsi
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X64-NEXT: sarq $63, %r8
[X86] Handle COPYs of physregs better (regalloc hints) Enable enableMultipleCopyHints() on X86. Original Patch by @jonpa: While enabling the mischeduler for SystemZ, it was discovered that for some reason a test needed one extra seemingly needless COPY (test/CodeGen/SystemZ/call-03.ll). The handling for that is resulted in this patch, which improves the register coalescing by providing not just one copy hint, but a sorted list of copy hints. On SystemZ, this gives ~12500 less register moves on SPEC, as well as marginally less spilling. Instead of improving just the SystemZ backend, the improvement has been implemented in common-code (calculateSpillWeightAndHint(). This gives a lot of test failures, but since this should be a general improvement I hope that the involved targets will help and review the test updates. Differential Revision: https://reviews.llvm.org/D38128 llvm-svn: 342578
2018-09-20 02:59:08 +08:00
; X64-NEXT: shrdq $6, %rdx, %rcx
; X64-NEXT: sarq $6, %rdx
; X64-NEXT: movq %rdx, 56(%rdi)
; X64-NEXT: movq %rcx, 48(%rdi)
; X64-NEXT: movq %rsi, 40(%rdi)
[X86] Regenerate v2i256 shift legalization tests llvm-svn: 276692
2016-07-26 05:14:22 +08:00
; X64-NEXT: movq %r9, 32(%rdi)
; X64-NEXT: movq %r8, 24(%rdi)
; X64-NEXT: movq %r8, 16(%rdi)
; X64-NEXT: movq %r8, 8(%rdi)
; X64-NEXT: movq %r8, (%rdi)
; X64-NEXT: retq
[x86] make test immune to oversized shift simplification I'm not sure if this actually preserves the original intent of this test, but if we leave it as-is, the -1 (oversized) shift should be folded to undef and allow deleting half of the output. llvm-svn: 347501
2018-11-24 03:45:29 +08:00
%Amt = insertelement <2 x i256> <i256 5, i256 6>, i256 255, i32 0
Reapply fixed r241790: Fix shift legalization and lowering for big constants. Summary: If shift amount is a constant value > 64 bit it is handled incorrectly during type legalization and X86 lowering. This patch the type of shift amount argument in function DAGTypeLegalizer::ExpandShiftByConstant from unsigned to APInt. Reviewers: nadav, majnemer, sanjoy, RKSimon Subscribers: RKSimon, llvm-commits Differential Revision: http://reviews.llvm.org/D10767 llvm-svn: 241806
2015-07-09 22:58:04 +08:00
%Out = ashr <2 x i256> %In, %Amt
ret <2 x i256> %Out
}