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/i256-add.ll

136 lines
4.3 KiB
LLVM
Raw Normal View History

Check full codegen in CodeGen/X86/i256-add.ll NFC llvm-svn: 294756
2017-02-11 00:34:17 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i386-unknown | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s --check-prefix=X64
Add a testcase for i256 add. i256 isn't fully supported in codegen right now, but add and subtract work. llvm-svn: 57260
2008-10-08 04:39:12 +08:00
Revert "In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled." This reverts commit r293893 which is miscompiling lua on ARM and bootstrapping for x86-windows. llvm-svn: 293915
2017-02-03 02:24:55 +08:00
define void @add(i256* %p, i256* %q) nounwind {
Check full codegen in CodeGen/X86/i256-add.ll NFC llvm-svn: 294756
2017-02-11 00:34:17 +08:00
; X32-LABEL: add:
; X32: # BB#0:
; X32-NEXT: pushl %ebp
; X32-NEXT: pushl %ebx
; X32-NEXT: pushl %edi
; X32-NEXT: pushl %esi
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X32-NEXT: subl $12, %esp
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
[SDAG] Teach Chain Analysis about BaseIndexOffset addressing. While we use BaseIndexOffset in FindBetterNeighborChains to appropriately realize they're almost the same address and should be improved concurrently we do not use it in isAlias using the non-index understanding FindBaseOffset instead. Adding a BaseIndexOffset check in isAlias like should allow indexed stores to be merged. FindBaseOffset to be excised in subsequent patch. Reviewers: jyknight, aditya_nandakumar, bogner Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D31987 llvm-svn: 301187
2017-04-24 23:37:20 +08:00
; X32-NEXT: movl 8(%ecx), %edi
; X32-NEXT: movl (%ecx), %edx
; X32-NEXT: movl 4(%ecx), %ebx
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X32-NEXT: movl 28(%eax), %esi
; X32-NEXT: movl %esi, {{[0-9]+}}(%esp) # 4-byte Spill
; X32-NEXT: movl 24(%eax), %ebp
[SDAG] Teach Chain Analysis about BaseIndexOffset addressing. While we use BaseIndexOffset in FindBetterNeighborChains to appropriately realize they're almost the same address and should be improved concurrently we do not use it in isAlias using the non-index understanding FindBaseOffset instead. Adding a BaseIndexOffset check in isAlias like should allow indexed stores to be merged. FindBaseOffset to be excised in subsequent patch. Reviewers: jyknight, aditya_nandakumar, bogner Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D31987 llvm-svn: 301187
2017-04-24 23:37:20 +08:00
; X32-NEXT: addl (%eax), %edx
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X32-NEXT: movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
[SDAG] Teach Chain Analysis about BaseIndexOffset addressing. While we use BaseIndexOffset in FindBetterNeighborChains to appropriately realize they're almost the same address and should be improved concurrently we do not use it in isAlias using the non-index understanding FindBaseOffset instead. Adding a BaseIndexOffset check in isAlias like should allow indexed stores to be merged. FindBaseOffset to be excised in subsequent patch. Reviewers: jyknight, aditya_nandakumar, bogner Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D31987 llvm-svn: 301187
2017-04-24 23:37:20 +08:00
; X32-NEXT: adcl 4(%eax), %ebx
; X32-NEXT: adcl 8(%eax), %edi
; X32-NEXT: movl %edi, (%esp) # 4-byte Spill
; X32-NEXT: movl 20(%eax), %edi
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X32-NEXT: movl 12(%eax), %edx
[SDAG] Teach Chain Analysis about BaseIndexOffset addressing. While we use BaseIndexOffset in FindBetterNeighborChains to appropriately realize they're almost the same address and should be improved concurrently we do not use it in isAlias using the non-index understanding FindBaseOffset instead. Adding a BaseIndexOffset check in isAlias like should allow indexed stores to be merged. FindBaseOffset to be excised in subsequent patch. Reviewers: jyknight, aditya_nandakumar, bogner Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D31987 llvm-svn: 301187
2017-04-24 23:37:20 +08:00
; X32-NEXT: movl 16(%eax), %esi
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X32-NEXT: adcl 12(%ecx), %edx
[SDAG] Teach Chain Analysis about BaseIndexOffset addressing. While we use BaseIndexOffset in FindBetterNeighborChains to appropriately realize they're almost the same address and should be improved concurrently we do not use it in isAlias using the non-index understanding FindBaseOffset instead. Adding a BaseIndexOffset check in isAlias like should allow indexed stores to be merged. FindBaseOffset to be excised in subsequent patch. Reviewers: jyknight, aditya_nandakumar, bogner Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D31987 llvm-svn: 301187
2017-04-24 23:37:20 +08:00
; X32-NEXT: adcl 16(%ecx), %esi
; X32-NEXT: adcl 20(%ecx), %edi
; X32-NEXT: movl %ebp, %eax
; X32-NEXT: adcl 24(%ecx), %eax
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %ebp # 4-byte Reload
; X32-NEXT: adcl %ebp, 28(%ecx)
[SDAG] Teach Chain Analysis about BaseIndexOffset addressing. While we use BaseIndexOffset in FindBetterNeighborChains to appropriately realize they're almost the same address and should be improved concurrently we do not use it in isAlias using the non-index understanding FindBaseOffset instead. Adding a BaseIndexOffset check in isAlias like should allow indexed stores to be merged. FindBaseOffset to be excised in subsequent patch. Reviewers: jyknight, aditya_nandakumar, bogner Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D31987 llvm-svn: 301187
2017-04-24 23:37:20 +08:00
; X32-NEXT: movl (%esp), %ebp # 4-byte Reload
; X32-NEXT: movl %ebp, 8(%ecx)
; X32-NEXT: movl %ebx, 4(%ecx)
; X32-NEXT: movl {{[0-9]+}}(%esp), %ebx # 4-byte Reload
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X32-NEXT: movl %ebx, (%ecx)
; X32-NEXT: movl %edx, 12(%ecx)
[SDAG] Teach Chain Analysis about BaseIndexOffset addressing. While we use BaseIndexOffset in FindBetterNeighborChains to appropriately realize they're almost the same address and should be improved concurrently we do not use it in isAlias using the non-index understanding FindBaseOffset instead. Adding a BaseIndexOffset check in isAlias like should allow indexed stores to be merged. FindBaseOffset to be excised in subsequent patch. Reviewers: jyknight, aditya_nandakumar, bogner Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D31987 llvm-svn: 301187
2017-04-24 23:37:20 +08:00
; X32-NEXT: movl %esi, 16(%ecx)
; X32-NEXT: movl %edi, 20(%ecx)
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X32-NEXT: movl %eax, 24(%ecx)
; X32-NEXT: addl $12, %esp
Check full codegen in CodeGen/X86/i256-add.ll NFC llvm-svn: 294756
2017-02-11 00:34:17 +08:00
; X32-NEXT: popl %esi
; X32-NEXT: popl %edi
; X32-NEXT: popl %ebx
; X32-NEXT: popl %ebp
; X32-NEXT: retl
;
; X64-LABEL: add:
; X64: # BB#0:
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X64-NEXT: movq 16(%rdi), %rax
; X64-NEXT: movq (%rdi), %rcx
; X64-NEXT: movq 8(%rdi), %rdx
In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled. Recommiting with compiler time improvements Recommitting after fixup of 32-bit aliasing sign offset bug in DAGCombiner. * Simplify Consecutive Merge Store Candidate Search Now that address aliasing is much less conservative, push through simplified store merging search and chain alias analysis which only checks for parallel stores through the chain subgraph. This is cleaner as the separation of non-interfering loads/stores from the store-merging logic. When merging stores search up the chain through a single load, and finds all possible stores by looking down from through a load and a TokenFactor to all stores visited. This improves the quality of the output SelectionDAG and the output Codegen (save perhaps for some ARM cases where we correctly constructs wider loads, but then promotes them to float operations which appear but requires more expensive constant generation). Some minor peephole optimizations to deal with improved SubDAG shapes (listed below) Additional Minor Changes: 1. Finishes removing unused AliasLoad code 2. Unifies the chain aggregation in the merged stores across code paths 3. Re-add the Store node to the worklist after calling SimplifyDemandedBits. 4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is arbitrary, but seems sufficient to not cause regressions in tests. 5. Remove Chain dependencies of Memory operations on CopyfromReg nodes as these are captured by data dependence 6. Forward loads-store values through tokenfactors containing {CopyToReg,CopyFromReg} Values. 7. Peephole to convert buildvector of extract_vector_elt to extract_subvector if possible (see CodeGen/AArch64/store-merge.ll) 8. Store merging for the ARM target is restricted to 32-bit as some in some contexts invalid 64-bit operations are being generated. This can be removed once appropriate checks are added. This finishes the change Matt Arsenault started in r246307 and jyknight's original patch. Many tests required some changes as memory operations are now reorderable, improving load-store forwarding. One test in particular is worth noting: CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store forwarding converts a load-store pair into a parallel store and a memory-realized bitcast of the same value. However, because we lose the sharing of the explicit and implicit store values we must create another local store. A similar transformation happens before SelectionDAG as well. Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle llvm-svn: 297695
2017-03-14 08:34:14 +08:00
; X64-NEXT: movq 24(%rsi), %r8
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X64-NEXT: addq (%rsi), %rcx
; X64-NEXT: adcq 8(%rsi), %rdx
; X64-NEXT: adcq 16(%rsi), %rax
In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled. Recommiting with compiler time improvements Recommitting after fixup of 32-bit aliasing sign offset bug in DAGCombiner. * Simplify Consecutive Merge Store Candidate Search Now that address aliasing is much less conservative, push through simplified store merging search and chain alias analysis which only checks for parallel stores through the chain subgraph. This is cleaner as the separation of non-interfering loads/stores from the store-merging logic. When merging stores search up the chain through a single load, and finds all possible stores by looking down from through a load and a TokenFactor to all stores visited. This improves the quality of the output SelectionDAG and the output Codegen (save perhaps for some ARM cases where we correctly constructs wider loads, but then promotes them to float operations which appear but requires more expensive constant generation). Some minor peephole optimizations to deal with improved SubDAG shapes (listed below) Additional Minor Changes: 1. Finishes removing unused AliasLoad code 2. Unifies the chain aggregation in the merged stores across code paths 3. Re-add the Store node to the worklist after calling SimplifyDemandedBits. 4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is arbitrary, but seems sufficient to not cause regressions in tests. 5. Remove Chain dependencies of Memory operations on CopyfromReg nodes as these are captured by data dependence 6. Forward loads-store values through tokenfactors containing {CopyToReg,CopyFromReg} Values. 7. Peephole to convert buildvector of extract_vector_elt to extract_subvector if possible (see CodeGen/AArch64/store-merge.ll) 8. Store merging for the ARM target is restricted to 32-bit as some in some contexts invalid 64-bit operations are being generated. This can be removed once appropriate checks are added. This finishes the change Matt Arsenault started in r246307 and jyknight's original patch. Many tests required some changes as memory operations are now reorderable, improving load-store forwarding. One test in particular is worth noting: CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store forwarding converts a load-store pair into a parallel store and a memory-realized bitcast of the same value. However, because we lose the sharing of the explicit and implicit store values we must create another local store. A similar transformation happens before SelectionDAG as well. Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle llvm-svn: 297695
2017-03-14 08:34:14 +08:00
; X64-NEXT: adcq %r8, 24(%rdi)
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X64-NEXT: movq %rax, 16(%rdi)
[SDAG] Teach Chain Analysis about BaseIndexOffset addressing. While we use BaseIndexOffset in FindBetterNeighborChains to appropriately realize they're almost the same address and should be improved concurrently we do not use it in isAlias using the non-index understanding FindBaseOffset instead. Adding a BaseIndexOffset check in isAlias like should allow indexed stores to be merged. FindBaseOffset to be excised in subsequent patch. Reviewers: jyknight, aditya_nandakumar, bogner Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D31987 llvm-svn: 301187
2017-04-24 23:37:20 +08:00
; X64-NEXT: movq %rdx, 8(%rdi)
; X64-NEXT: movq %rcx, (%rdi)
Check full codegen in CodeGen/X86/i256-add.ll NFC llvm-svn: 294756
2017-02-11 00:34:17 +08:00
; X64-NEXT: retq
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%a = load i256, i256* %p
%b = load i256, i256* %q
Add a testcase for i256 add. i256 isn't fully supported in codegen right now, but add and subtract work. llvm-svn: 57260
2008-10-08 04:39:12 +08:00
%c = add i256 %a, %b
Revert "In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled." This reverts commit r293893 which is miscompiling lua on ARM and bootstrapping for x86-windows. llvm-svn: 293915
2017-02-03 02:24:55 +08:00
store i256 %c, i256* %p
Add a testcase for i256 add. i256 isn't fully supported in codegen right now, but add and subtract work. llvm-svn: 57260
2008-10-08 04:39:12 +08:00
ret void
}
Revert "In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled." This reverts commit r293893 which is miscompiling lua on ARM and bootstrapping for x86-windows. llvm-svn: 293915
2017-02-03 02:24:55 +08:00
define void @sub(i256* %p, i256* %q) nounwind {
Check full codegen in CodeGen/X86/i256-add.ll NFC llvm-svn: 294756
2017-02-11 00:34:17 +08:00
; X32-LABEL: sub:
; X32: # BB#0:
; X32-NEXT: pushl %ebp
; X32-NEXT: pushl %ebx
; X32-NEXT: pushl %edi
; X32-NEXT: pushl %esi
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X32-NEXT: subl $8, %esp
; X32-NEXT: movl {{[0-9]+}}(%esp), %esi
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: movl 16(%ecx), %eax
; X32-NEXT: movl 12(%ecx), %edx
; X32-NEXT: movl 8(%ecx), %edi
; X32-NEXT: movl (%ecx), %ebx
; X32-NEXT: movl 4(%ecx), %ebp
; X32-NEXT: subl (%esi), %ebx
; X32-NEXT: sbbl 4(%esi), %ebp
; X32-NEXT: sbbl 8(%esi), %edi
; X32-NEXT: sbbl 12(%esi), %edx
; X32-NEXT: movl %edx, {{[0-9]+}}(%esp) # 4-byte Spill
; X32-NEXT: sbbl 16(%esi), %eax
; X32-NEXT: movl %eax, (%esp) # 4-byte Spill
; X32-NEXT: movl 20(%ecx), %edx
; X32-NEXT: sbbl 20(%esi), %edx
; X32-NEXT: movl 24(%ecx), %eax
; X32-NEXT: sbbl 24(%esi), %eax
; X32-NEXT: movl 28(%esi), %esi
; X32-NEXT: sbbl %esi, 28(%ecx)
; X32-NEXT: movl %edi, 8(%ecx)
[SDAG] Teach Chain Analysis about BaseIndexOffset addressing. While we use BaseIndexOffset in FindBetterNeighborChains to appropriately realize they're almost the same address and should be improved concurrently we do not use it in isAlias using the non-index understanding FindBaseOffset instead. Adding a BaseIndexOffset check in isAlias like should allow indexed stores to be merged. FindBaseOffset to be excised in subsequent patch. Reviewers: jyknight, aditya_nandakumar, bogner Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D31987 llvm-svn: 301187
2017-04-24 23:37:20 +08:00
; X32-NEXT: movl %ebp, 4(%ecx)
; X32-NEXT: movl %ebx, (%ecx)
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X32-NEXT: movl {{[0-9]+}}(%esp), %esi # 4-byte Reload
; X32-NEXT: movl %esi, 12(%ecx)
; X32-NEXT: movl (%esp), %esi # 4-byte Reload
; X32-NEXT: movl %esi, 16(%ecx)
; X32-NEXT: movl %edx, 20(%ecx)
; X32-NEXT: movl %eax, 24(%ecx)
; X32-NEXT: addl $8, %esp
Check full codegen in CodeGen/X86/i256-add.ll NFC llvm-svn: 294756
2017-02-11 00:34:17 +08:00
; X32-NEXT: popl %esi
; X32-NEXT: popl %edi
; X32-NEXT: popl %ebx
; X32-NEXT: popl %ebp
; X32-NEXT: retl
;
; X64-LABEL: sub:
; X64: # BB#0:
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X64-NEXT: movq 16(%rdi), %rax
; X64-NEXT: movq (%rdi), %rcx
; X64-NEXT: movq 8(%rdi), %rdx
In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled. Recommiting with compiler time improvements Recommitting after fixup of 32-bit aliasing sign offset bug in DAGCombiner. * Simplify Consecutive Merge Store Candidate Search Now that address aliasing is much less conservative, push through simplified store merging search and chain alias analysis which only checks for parallel stores through the chain subgraph. This is cleaner as the separation of non-interfering loads/stores from the store-merging logic. When merging stores search up the chain through a single load, and finds all possible stores by looking down from through a load and a TokenFactor to all stores visited. This improves the quality of the output SelectionDAG and the output Codegen (save perhaps for some ARM cases where we correctly constructs wider loads, but then promotes them to float operations which appear but requires more expensive constant generation). Some minor peephole optimizations to deal with improved SubDAG shapes (listed below) Additional Minor Changes: 1. Finishes removing unused AliasLoad code 2. Unifies the chain aggregation in the merged stores across code paths 3. Re-add the Store node to the worklist after calling SimplifyDemandedBits. 4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is arbitrary, but seems sufficient to not cause regressions in tests. 5. Remove Chain dependencies of Memory operations on CopyfromReg nodes as these are captured by data dependence 6. Forward loads-store values through tokenfactors containing {CopyToReg,CopyFromReg} Values. 7. Peephole to convert buildvector of extract_vector_elt to extract_subvector if possible (see CodeGen/AArch64/store-merge.ll) 8. Store merging for the ARM target is restricted to 32-bit as some in some contexts invalid 64-bit operations are being generated. This can be removed once appropriate checks are added. This finishes the change Matt Arsenault started in r246307 and jyknight's original patch. Many tests required some changes as memory operations are now reorderable, improving load-store forwarding. One test in particular is worth noting: CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store forwarding converts a load-store pair into a parallel store and a memory-realized bitcast of the same value. However, because we lose the sharing of the explicit and implicit store values we must create another local store. A similar transformation happens before SelectionDAG as well. Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle llvm-svn: 297695
2017-03-14 08:34:14 +08:00
; X64-NEXT: movq 24(%rsi), %r8
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X64-NEXT: subq (%rsi), %rcx
; X64-NEXT: sbbq 8(%rsi), %rdx
; X64-NEXT: sbbq 16(%rsi), %rax
In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled. Recommiting with compiler time improvements Recommitting after fixup of 32-bit aliasing sign offset bug in DAGCombiner. * Simplify Consecutive Merge Store Candidate Search Now that address aliasing is much less conservative, push through simplified store merging search and chain alias analysis which only checks for parallel stores through the chain subgraph. This is cleaner as the separation of non-interfering loads/stores from the store-merging logic. When merging stores search up the chain through a single load, and finds all possible stores by looking down from through a load and a TokenFactor to all stores visited. This improves the quality of the output SelectionDAG and the output Codegen (save perhaps for some ARM cases where we correctly constructs wider loads, but then promotes them to float operations which appear but requires more expensive constant generation). Some minor peephole optimizations to deal with improved SubDAG shapes (listed below) Additional Minor Changes: 1. Finishes removing unused AliasLoad code 2. Unifies the chain aggregation in the merged stores across code paths 3. Re-add the Store node to the worklist after calling SimplifyDemandedBits. 4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is arbitrary, but seems sufficient to not cause regressions in tests. 5. Remove Chain dependencies of Memory operations on CopyfromReg nodes as these are captured by data dependence 6. Forward loads-store values through tokenfactors containing {CopyToReg,CopyFromReg} Values. 7. Peephole to convert buildvector of extract_vector_elt to extract_subvector if possible (see CodeGen/AArch64/store-merge.ll) 8. Store merging for the ARM target is restricted to 32-bit as some in some contexts invalid 64-bit operations are being generated. This can be removed once appropriate checks are added. This finishes the change Matt Arsenault started in r246307 and jyknight's original patch. Many tests required some changes as memory operations are now reorderable, improving load-store forwarding. One test in particular is worth noting: CodeGen/PowerPC/ppc64-align-long-double.ll - Improved load-store forwarding converts a load-store pair into a parallel store and a memory-realized bitcast of the same value. However, because we lose the sharing of the explicit and implicit store values we must create another local store. A similar transformation happens before SelectionDAG as well. Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle llvm-svn: 297695
2017-03-14 08:34:14 +08:00
; X64-NEXT: sbbq %r8, 24(%rdi)
Recommitting Craig Topper's patch now that r296476 has been recommitted. When checking if chain node is foldable, make sure the intermediate nodes have a single use across all results not just the result that was used to reach the chain node. This recovers a test case that was severely broken by r296476, my making sure we don't create ADD/ADC that loads and stores when there is also a flag dependency. llvm-svn: 297698
2017-03-14 09:42:23 +08:00
; X64-NEXT: movq %rax, 16(%rdi)
[SDAG] Teach Chain Analysis about BaseIndexOffset addressing. While we use BaseIndexOffset in FindBetterNeighborChains to appropriately realize they're almost the same address and should be improved concurrently we do not use it in isAlias using the non-index understanding FindBaseOffset instead. Adding a BaseIndexOffset check in isAlias like should allow indexed stores to be merged. FindBaseOffset to be excised in subsequent patch. Reviewers: jyknight, aditya_nandakumar, bogner Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D31987 llvm-svn: 301187
2017-04-24 23:37:20 +08:00
; X64-NEXT: movq %rdx, 8(%rdi)
; X64-NEXT: movq %rcx, (%rdi)
Check full codegen in CodeGen/X86/i256-add.ll NFC llvm-svn: 294756
2017-02-11 00:34:17 +08:00
; X64-NEXT: retq
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%a = load i256, i256* %p
%b = load i256, i256* %q
Add a testcase for i256 add. i256 isn't fully supported in codegen right now, but add and subtract work. llvm-svn: 57260
2008-10-08 04:39:12 +08:00
%c = sub i256 %a, %b
Revert "In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled." This reverts commit r293893 which is miscompiling lua on ARM and bootstrapping for x86-windows. llvm-svn: 293915
2017-02-03 02:24:55 +08:00
store i256 %c, i256* %p
Add a testcase for i256 add. i256 isn't fully supported in codegen right now, but add and subtract work. llvm-svn: 57260
2008-10-08 04:39:12 +08:00
ret void
}