[llvm] 9768a71 - [X86] Regen a couple tests so they are autogen clean [nfc]
Philip Reames via llvm-commits
llvm-commits at lists.llvm.org
Wed Jan 4 12:17:43 PST 2023
Author: Philip Reames
Date: 2023-01-04T12:17:32-08:00
New Revision: 9768a71a5ee04df88e35c02657ab29b418f5fd31
URL: https://github.com/llvm/llvm-project/commit/9768a71a5ee04df88e35c02657ab29b418f5fd31
DIFF: https://github.com/llvm/llvm-project/commit/9768a71a5ee04df88e35c02657ab29b418f5fd31.diff
LOG: [X86] Regen a couple tests so they are autogen clean [nfc]
These appear to have had 32 bit check lines manually deleted - presumably since the checks are verbose. Please don't do this! Split the test file if you want, but manually deleting test lines makes the diffs for later autogen changes really confusing.
Added:
Modified:
llvm/test/CodeGen/X86/div-rem-pair-recomposition-signed.ll
llvm/test/CodeGen/X86/div-rem-pair-recomposition-unsigned.ll
llvm/test/CodeGen/X86/shift-combine.ll
Removed:
################################################################################
diff --git a/llvm/test/CodeGen/X86/div-rem-pair-recomposition-signed.ll b/llvm/test/CodeGen/X86/div-rem-pair-recomposition-signed.ll
index 0ee08a43f265..d1045108462b 100644
--- a/llvm/test/CodeGen/X86/div-rem-pair-recomposition-signed.ll
+++ b/llvm/test/CodeGen/X86/div-rem-pair-recomposition-signed.ll
@@ -169,10 +169,499 @@ define i64 @scalar_i64(i64 %x, i64 %y, ptr %divdst) nounwind {
ret i64 %t2
}
+; X86 doesn't have __divti3, so the urem is expanded into a loop.
define i128 @scalar_i128(i128 %x, i128 %y, ptr %divdst) nounwind {
; X86-LABEL: scalar_i128:
-; X86 doesn't have __divti3, so the urem is expanded into a loop.
-; X86: udiv-do-while
+; X86: # %bb.0: # %_udiv-special-cases
+; X86-NEXT: pushl %ebp
+; X86-NEXT: pushl %ebx
+; X86-NEXT: pushl %edi
+; X86-NEXT: pushl %esi
+; X86-NEXT: subl $92, %esp
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: movl %edx, %eax
+; X86-NEXT: sarl $31, %eax
+; X86-NEXT: movl %esi, %ecx
+; X86-NEXT: sarl $31, %ecx
+; X86-NEXT: movl %eax, %edi
+; X86-NEXT: xorl %edx, %edi
+; X86-NEXT: movl %edi, %ebp
+; X86-NEXT: movl %eax, %edx
+; X86-NEXT: xorl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: movl %eax, %edi
+; X86-NEXT: xorl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: movl %eax, %ebx
+; X86-NEXT: xorl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT: subl %eax, %ebx
+; X86-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: sbbl %eax, %edi
+; X86-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: sbbl %eax, %edx
+; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: sbbl %eax, %ebp
+; X86-NEXT: movl %ebp, %edx
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %ecx, %ebx
+; X86-NEXT: xorl %esi, %ebx
+; X86-NEXT: movl %ecx, %esi
+; X86-NEXT: xorl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movl %ecx, %edi
+; X86-NEXT: xorl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: movl %ecx, %ebp
+; X86-NEXT: xorl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT: subl %ecx, %ebp
+; X86-NEXT: sbbl %ecx, %edi
+; X86-NEXT: sbbl %ecx, %esi
+; X86-NEXT: sbbl %ecx, %ebx
+; X86-NEXT: xorl %eax, %ecx
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %edi, %eax
+; X86-NEXT: orl %ebx, %eax
+; X86-NEXT: movl %ebp, %ecx
+; X86-NEXT: orl %esi, %ecx
+; X86-NEXT: orl %eax, %ecx
+; X86-NEXT: sete {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: orl %edx, %ecx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: orl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X86-NEXT: orl %ecx, %edx
+; X86-NEXT: sete {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X86-NEXT: bsrl %ebx, %eax
+; X86-NEXT: xorl $31, %eax
+; X86-NEXT: bsrl %esi, %edx
+; X86-NEXT: xorl $31, %edx
+; X86-NEXT: addl $32, %edx
+; X86-NEXT: testl %ebx, %ebx
+; X86-NEXT: cmovnel %eax, %edx
+; X86-NEXT: bsrl %edi, %eax
+; X86-NEXT: xorl $31, %eax
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: bsrl %ebp, %ebp
+; X86-NEXT: xorl $31, %ebp
+; X86-NEXT: addl $32, %ebp
+; X86-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: testl %edi, %edi
+; X86-NEXT: cmovnel %eax, %ebp
+; X86-NEXT: addl $64, %ebp
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: orl %ebx, %esi
+; X86-NEXT: cmovnel %edx, %ebp
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: bsrl %eax, %esi
+; X86-NEXT: xorl $31, %esi
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT: bsrl %ebx, %edx
+; X86-NEXT: xorl $31, %edx
+; X86-NEXT: addl $32, %edx
+; X86-NEXT: testl %eax, %eax
+; X86-NEXT: cmovnel %esi, %edx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: bsrl %eax, %edi
+; X86-NEXT: xorl $31, %edi
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: bsrl %ecx, %esi
+; X86-NEXT: xorl $31, %esi
+; X86-NEXT: addl $32, %esi
+; X86-NEXT: testl %eax, %eax
+; X86-NEXT: cmovnel %edi, %esi
+; X86-NEXT: addl $64, %esi
+; X86-NEXT: movl %ebx, %edi
+; X86-NEXT: orl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X86-NEXT: cmovnel %edx, %esi
+; X86-NEXT: xorl %edi, %edi
+; X86-NEXT: subl %esi, %ebp
+; X86-NEXT: movl $0, %ebx
+; X86-NEXT: sbbl %ebx, %ebx
+; X86-NEXT: movl $0, %eax
+; X86-NEXT: sbbl %eax, %eax
+; X86-NEXT: movl $0, %esi
+; X86-NEXT: sbbl %esi, %esi
+; X86-NEXT: movl $127, %edx
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: cmpl %ebp, %edx
+; X86-NEXT: movl $0, %edx
+; X86-NEXT: sbbl %ebx, %edx
+; X86-NEXT: movl $0, %edx
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: sbbl %eax, %edx
+; X86-NEXT: movl $0, %edx
+; X86-NEXT: sbbl %esi, %edx
+; X86-NEXT: setb %dl
+; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %dl # 1-byte Folded Reload
+; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %dl # 1-byte Folded Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: cmovnel %edi, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: cmovnel %edi, %eax
+; X86-NEXT: movl %eax, (%esp) # 4-byte Spill
+; X86-NEXT: movl %edx, %eax
+; X86-NEXT: cmovnel %edi, %eax
+; X86-NEXT: cmovel %ecx, %edi
+; X86-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: jne .LBB4_8
+; X86-NEXT: # %bb.1: # %_udiv-special-cases
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: xorl $127, %edx
+; X86-NEXT: orl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X86-NEXT: movl %ebx, %ecx
+; X86-NEXT: orl %esi, %ecx
+; X86-NEXT: orl %edx, %ecx
+; X86-NEXT: je .LBB4_8
+; X86-NEXT: # %bb.2: # %udiv-bb1
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: movl %eax, %ecx
+; X86-NEXT: xorb $127, %cl
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: movl %esi, %edx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT: shldl %cl, %esi, %eax
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X86-NEXT: shll %cl, %ebp
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %esi, %edi
+; X86-NEXT: shll %cl, %edi
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: movb %cl, %ch
+; X86-NEXT: movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
+; X86-NEXT: cmovnel %edi, %eax
+; X86-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl $0, %edx
+; X86-NEXT: cmovnel %edx, %ebp
+; X86-NEXT: cmovnel %edx, %edi
+; X86-NEXT: subb $64, %ch
+; X86-NEXT: cmovael %edx, %edi
+; X86-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: negb %ch
+; X86-NEXT: movl %esi, %ebx
+; X86-NEXT: movb %ch, %cl
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: shrdl %cl, %edx, %ebx
+; X86-NEXT: shrl %cl, %edx
+; X86-NEXT: testb $32, %ch
+; X86-NEXT: cmovnel %edx, %ebx
+; X86-NEXT: orl %ebp, %ebx
+; X86-NEXT: movb {{[-0-9]+}}(%e{{[sb]}}p), %cl # 1-byte Reload
+; X86-NEXT: addb $-64, %cl
+; X86-NEXT: movl %esi, %ebp
+; X86-NEXT: movb %cl, (%esp) # 1-byte Spill
+; X86-NEXT: shll %cl, %ebp
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: movl $0, %edi
+; X86-NEXT: cmovnel %edi, %ebp
+; X86-NEXT: movb {{[-0-9]+}}(%e{{[sb]}}p), %cl # 1-byte Reload
+; X86-NEXT: cmpb $64, %cl
+; X86-NEXT: cmovbl %ebx, %ebp
+; X86-NEXT: movl $0, %ebx
+; X86-NEXT: cmovael %ebx, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: testb $32, %ch
+; X86-NEXT: cmovnel %ebx, %edx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-NEXT: movl %edi, %eax
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT: shldl %cl, %ebx, %eax
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: cmovnel {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT: movzbl (%esp), %ecx # 1-byte Folded Reload
+; X86-NEXT: shldl %cl, %esi, %ebx
+; X86-NEXT: movl %eax, %ecx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: testb $32, (%esp) # 1-byte Folded Reload
+; X86-NEXT: cmovnel {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X86-NEXT: orl %edx, %ecx
+; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 1-byte Folded Reload
+; X86-NEXT: cmpb $64, %dl
+; X86-NEXT: cmovael %ebx, %ecx
+; X86-NEXT: testb %dl, %dl
+; X86-NEXT: cmovel %edi, %ecx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT: cmovel %esi, %ebp
+; X86-NEXT: movl %ebp, (%esp) # 4-byte Spill
+; X86-NEXT: addl $1, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT: adcl $0, %eax
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT: adcl $0, %ebx
+; X86-NEXT: adcl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT: jae .LBB4_3
+; X86-NEXT: # %bb.6:
+; X86-NEXT: xorl %ebx, %ebx
+; X86-NEXT: xorl %edx, %edx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: movl (%esp), %esi # 4-byte Reload
+; X86-NEXT: jmp .LBB4_7
+; X86-NEXT: .LBB4_3: # %udiv-preheader
+; X86-NEXT: movl %esi, %edx
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: shrdl %cl, %edi, %edx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT: shrl %cl, %esi
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %edi, %esi
+; X86-NEXT: shrl %cl, %esi
+; X86-NEXT: xorl %eax, %eax
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: cmovnel %esi, %edx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X86-NEXT: cmovnel %eax, %ebp
+; X86-NEXT: cmovnel %eax, %esi
+; X86-NEXT: xorl %eax, %eax
+; X86-NEXT: movb %cl, %ch
+; X86-NEXT: subb $64, %ch
+; X86-NEXT: cmovael %eax, %esi
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: negb %ch
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: movl %edi, %esi
+; X86-NEXT: movb %ch, %cl
+; X86-NEXT: shldl %cl, %eax, %esi
+; X86-NEXT: shll %cl, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: testb $32, %ch
+; X86-NEXT: cmovnel %eax, %esi
+; X86-NEXT: orl %ebp, %esi
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: movb %al, %cl
+; X86-NEXT: addb $-64, %cl
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X86-NEXT: movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
+; X86-NEXT: shrl %cl, %ebp
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: movl $0, %edi
+; X86-NEXT: cmovnel %edi, %ebp
+; X86-NEXT: cmpb $64, %al
+; X86-NEXT: cmovbl %esi, %ebp
+; X86-NEXT: cmovael %edi, %edx
+; X86-NEXT: xorl %esi, %esi
+; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: testb $32, %ch
+; X86-NEXT: movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: cmovnel %esi, %ecx
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT: movl %eax, %ecx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: shrdl %cl, %edx, %esi
+; X86-NEXT: testb $32, %al
+; X86-NEXT: cmovnel {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: shrdl %cl, %edx, %edi
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: cmovnel {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X86-NEXT: orl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X86-NEXT: cmpb $64, %al
+; X86-NEXT: cmovael %edi, %esi
+; X86-NEXT: testb %al, %al
+; X86-NEXT: cmovel {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: cmovel {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: addl $-1, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: adcl $-1, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: adcl $-1, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: adcl $-1, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: .p2align 4, 0x90
+; X86-NEXT: .LBB4_4: # %udiv-do-while
+; X86-NEXT: # =>This Inner Loop Header: Depth=1
+; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X86-NEXT: shldl $1, %ebp, %edi
+; X86-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT: shldl $1, %esi, %ebp
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: shldl $1, %edx, %esi
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: shldl $1, %eax, %edx
+; X86-NEXT: movl (%esp), %ebx # 4-byte Reload
+; X86-NEXT: shldl $1, %ebx, %eax
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: orl %ecx, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: shldl $1, %eax, %ebx
+; X86-NEXT: orl %ecx, %ebx
+; X86-NEXT: movl %ebx, (%esp) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT: shldl $1, %ebx, %eax
+; X86-NEXT: orl %ecx, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: addl %ebx, %ebx
+; X86-NEXT: orl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X86-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: cmpl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: sbbl %esi, %ecx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: sbbl %ebp, %ecx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: sbbl %edi, %ecx
+; X86-NEXT: sarl $31, %ecx
+; X86-NEXT: movl %ecx, %eax
+; X86-NEXT: andl $1, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %ecx, %ebx
+; X86-NEXT: andl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X86-NEXT: movl %ecx, %edi
+; X86-NEXT: andl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
+; X86-NEXT: movl %ecx, %eax
+; X86-NEXT: andl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X86-NEXT: andl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X86-NEXT: subl %ecx, %edx
+; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: sbbl %eax, %esi
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: sbbl %edi, %ebp
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: sbbl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: addl $-1, %ecx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: adcl $-1, %eax
+; X86-NEXT: adcl $-1, %ebx
+; X86-NEXT: adcl $-1, %edx
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: orl %edx, %eax
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: orl %ebx, %ecx
+; X86-NEXT: orl %eax, %ecx
+; X86-NEXT: jne .LBB4_4
+; X86-NEXT: # %bb.5:
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: movl (%esp), %esi # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT: .LBB4_7: # %udiv-loop-exit
+; X86-NEXT: shldl $1, %esi, %ecx
+; X86-NEXT: orl %edx, %ecx
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: shldl $1, %eax, %esi
+; X86-NEXT: orl %edx, %esi
+; X86-NEXT: movl %esi, (%esp) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: shldl $1, %ecx, %eax
+; X86-NEXT: orl %edx, %eax
+; X86-NEXT: addl %ecx, %ecx
+; X86-NEXT: orl %ebx, %ecx
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: .LBB4_8: # %udiv-end
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X86-NEXT: xorl %ecx, %ebp
+; X86-NEXT: movl (%esp), %esi # 4-byte Reload
+; X86-NEXT: xorl %ecx, %esi
+; X86-NEXT: xorl %ecx, %eax
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: xorl %ecx, %edx
+; X86-NEXT: subl %ecx, %edx
+; X86-NEXT: sbbl %ecx, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: sbbl %ecx, %esi
+; X86-NEXT: sbbl %ecx, %ebp
+; X86-NEXT: movl %edx, (%edi)
+; X86-NEXT: movl %eax, 4(%edi)
+; X86-NEXT: movl %esi, 8(%edi)
+; X86-NEXT: movl %ebp, 12(%edi)
+; X86-NEXT: movl %edx, %ebx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: mull %edi
+; X86-NEXT: movl %edx, %ecx
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %ebx, %edi
+; X86-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %ebx, %eax
+; X86-NEXT: mull {{[0-9]+}}(%esp)
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %edx, %ebx
+; X86-NEXT: addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X86-NEXT: adcl $0, %ecx
+; X86-NEXT: movl %edi, %eax
+; X86-NEXT: movl %esi, %edi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: mull %esi
+; X86-NEXT: addl %ebx, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: adcl %ecx, %edx
+; X86-NEXT: movl %edx, %ecx
+; X86-NEXT: setb (%esp) # 1-byte Folded Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT: movl %ebx, %eax
+; X86-NEXT: mull %esi
+; X86-NEXT: addl %ecx, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movzbl (%esp), %eax # 1-byte Folded Reload
+; X86-NEXT: adcl %eax, %edx
+; X86-NEXT: movl %edx, (%esp) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: imull %eax, %ebp
+; X86-NEXT: mull %edi
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: imull %esi, %edi
+; X86-NEXT: addl %ebp, %edi
+; X86-NEXT: addl %edx, %edi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %ebx, %edx
+; X86-NEXT: imull %eax, %edx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: imull %ecx, %ebx
+; X86-NEXT: addl %edx, %ebx
+; X86-NEXT: mull %ecx
+; X86-NEXT: addl %edx, %ebx
+; X86-NEXT: addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X86-NEXT: adcl %edi, %ebx
+; X86-NEXT: addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X86-NEXT: adcl (%esp), %ebx # 4-byte Folded Reload
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: subl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: sbbl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: sbbl %eax, %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: sbbl %ebx, %edi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %esi, (%eax)
+; X86-NEXT: movl %edx, 4(%eax)
+; X86-NEXT: movl %ecx, 8(%eax)
+; X86-NEXT: movl %edi, 12(%eax)
+; X86-NEXT: addl $92, %esp
+; X86-NEXT: popl %esi
+; X86-NEXT: popl %edi
+; X86-NEXT: popl %ebx
+; X86-NEXT: popl %ebp
+; X86-NEXT: retl $4
;
; X64-LABEL: scalar_i128:
; X64: # %bb.0:
diff --git a/llvm/test/CodeGen/X86/div-rem-pair-recomposition-unsigned.ll b/llvm/test/CodeGen/X86/div-rem-pair-recomposition-unsigned.ll
index 86dd5f32ea6f..7280b916c7f5 100644
--- a/llvm/test/CodeGen/X86/div-rem-pair-recomposition-unsigned.ll
+++ b/llvm/test/CodeGen/X86/div-rem-pair-recomposition-unsigned.ll
@@ -169,10 +169,445 @@ define i64 @scalar_i64(i64 %x, i64 %y, ptr %divdst) nounwind {
ret i64 %t2
}
+; X86 doesn't have __divti3, so the urem is expanded into a loop.
define i128 @scalar_i128(i128 %x, i128 %y, ptr %divdst) nounwind {
; X86-LABEL: scalar_i128:
-; X86 doesn't have __divti3, so the urem is expanded into a loop.
-; X86: udiv-do-while
+; X86: # %bb.0: # %_udiv-special-cases
+; X86-NEXT: pushl %ebp
+; X86-NEXT: pushl %ebx
+; X86-NEXT: pushl %edi
+; X86-NEXT: pushl %esi
+; X86-NEXT: subl $72, %esp
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: movl %ebx, %eax
+; X86-NEXT: orl %ebp, %eax
+; X86-NEXT: orl %edi, %ecx
+; X86-NEXT: orl %eax, %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: sete {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X86-NEXT: orl %edx, %ecx
+; X86-NEXT: movl %edx, %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: orl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: orl %ecx, %edx
+; X86-NEXT: sete {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
+; X86-NEXT: bsrl %ebp, %esi
+; X86-NEXT: xorl $31, %esi
+; X86-NEXT: bsrl %edi, %edx
+; X86-NEXT: xorl $31, %edx
+; X86-NEXT: addl $32, %edx
+; X86-NEXT: testl %ebp, %ebp
+; X86-NEXT: cmovnel %esi, %edx
+; X86-NEXT: bsrl %ebx, %esi
+; X86-NEXT: xorl $31, %esi
+; X86-NEXT: bsrl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: xorl $31, %ecx
+; X86-NEXT: addl $32, %ecx
+; X86-NEXT: testl %ebx, %ebx
+; X86-NEXT: cmovnel %esi, %ecx
+; X86-NEXT: addl $64, %ecx
+; X86-NEXT: orl %ebp, %edi
+; X86-NEXT: cmovnel %edx, %ecx
+; X86-NEXT: movl %eax, %ebx
+; X86-NEXT: bsrl %eax, %esi
+; X86-NEXT: xorl $31, %esi
+; X86-NEXT: bsrl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: xorl $31, %edx
+; X86-NEXT: addl $32, %edx
+; X86-NEXT: testl %eax, %eax
+; X86-NEXT: cmovnel %esi, %edx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT: bsrl %ebp, %edi
+; X86-NEXT: xorl $31, %edi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: bsrl %eax, %esi
+; X86-NEXT: xorl $31, %esi
+; X86-NEXT: addl $32, %esi
+; X86-NEXT: testl %ebp, %ebp
+; X86-NEXT: cmovnel %edi, %esi
+; X86-NEXT: addl $64, %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: orl %ebx, %edi
+; X86-NEXT: cmovnel %edx, %esi
+; X86-NEXT: xorl %ebp, %ebp
+; X86-NEXT: subl %esi, %ecx
+; X86-NEXT: movl $0, %eax
+; X86-NEXT: sbbl %eax, %eax
+; X86-NEXT: movl $0, %esi
+; X86-NEXT: sbbl %esi, %esi
+; X86-NEXT: movl $0, %edi
+; X86-NEXT: sbbl %edi, %edi
+; X86-NEXT: movl $127, %edx
+; X86-NEXT: movl %ecx, (%esp) # 4-byte Spill
+; X86-NEXT: cmpl %ecx, %edx
+; X86-NEXT: movl %eax, %ecx
+; X86-NEXT: movl $0, %edx
+; X86-NEXT: sbbl %eax, %edx
+; X86-NEXT: movl $0, %edx
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: sbbl %esi, %edx
+; X86-NEXT: movl $0, %edx
+; X86-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: sbbl %edi, %edx
+; X86-NEXT: setb %dl
+; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %dl # 1-byte Folded Reload
+; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %dl # 1-byte Folded Reload
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: cmovnel %ebp, %ebx
+; X86-NEXT: movl %ebx, %edx
+; X86-NEXT: movl %eax, %ebx
+; X86-NEXT: cmovnel %ebp, %ebx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: cmovnel %ebp, %esi
+; X86-NEXT: cmovel {{[0-9]+}}(%esp), %ebp
+; X86-NEXT: jne .LBB4_8
+; X86-NEXT: # %bb.1: # %_udiv-special-cases
+; X86-NEXT: movl (%esp), %eax # 4-byte Reload
+; X86-NEXT: xorl $127, %eax
+; X86-NEXT: orl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X86-NEXT: movl %ecx, %edi
+; X86-NEXT: orl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
+; X86-NEXT: orl %eax, %ecx
+; X86-NEXT: je .LBB4_8
+; X86-NEXT: # %bb.2: # %udiv-bb1
+; X86-NEXT: movl (%esp), %eax # 4-byte Reload
+; X86-NEXT: movl %eax, %ecx
+; X86-NEXT: xorb $127, %cl
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: shldl %cl, %edx, %ebp
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: shll %cl, %esi
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: shll %cl, %edx
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: cmovnel %edx, %ebp
+; X86-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %esi, %edi
+; X86-NEXT: movl $0, %esi
+; X86-NEXT: cmovnel %esi, %edi
+; X86-NEXT: cmovnel %esi, %edx
+; X86-NEXT: movb %cl, %ch
+; X86-NEXT: movl %ecx, %eax
+; X86-NEXT: movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
+; X86-NEXT: subb $64, %ch
+; X86-NEXT: cmovael %esi, %edx
+; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: negb %ch
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movb %ch, %cl
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: shrdl %cl, %edx, %esi
+; X86-NEXT: shrl %cl, %edx
+; X86-NEXT: testb $32, %ch
+; X86-NEXT: cmovnel %edx, %esi
+; X86-NEXT: orl %edi, %esi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: movb %al, %cl
+; X86-NEXT: addb $-64, %cl
+; X86-NEXT: movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
+; X86-NEXT: shll %cl, %edi
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: movl %edi, %ebx
+; X86-NEXT: movl $0, %eax
+; X86-NEXT: cmovnel %eax, %ebx
+; X86-NEXT: movb {{[-0-9]+}}(%e{{[sb]}}p), %cl # 1-byte Reload
+; X86-NEXT: cmpb $64, %cl
+; X86-NEXT: cmovbl %esi, %ebx
+; X86-NEXT: movl $0, %esi
+; X86-NEXT: cmovael %esi, %ebp
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: testb $32, %ch
+; X86-NEXT: cmovnel %esi, %edx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: shldl %cl, %esi, %ebp
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: movb %cl, %ch
+; X86-NEXT: cmovnel {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Folded Reload
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movb {{[-0-9]+}}(%e{{[sb]}}p), %cl # 1-byte Reload
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: shldl %cl, %esi, %eax
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: cmovnel %edi, %eax
+; X86-NEXT: orl %edx, %ebp
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: cmpb $64, %ch
+; X86-NEXT: cmovael %eax, %ebp
+; X86-NEXT: movl %ebp, %edx
+; X86-NEXT: testb %ch, %ch
+; X86-NEXT: cmovel {{[0-9]+}}(%esp), %edx
+; X86-NEXT: movl %esi, %ebp
+; X86-NEXT: cmovel %esi, %ebx
+; X86-NEXT: addl $1, (%esp) # 4-byte Folded Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT: adcl $0, %esi
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-NEXT: adcl $0, %edi
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: adcl $0, %eax
+; X86-NEXT: jae .LBB4_3
+; X86-NEXT: # %bb.6:
+; X86-NEXT: xorl %ecx, %ecx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT: xorl %eax, %eax
+; X86-NEXT: jmp .LBB4_7
+; X86-NEXT: .LBB4_3: # %udiv-preheader
+; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl (%esp), %ecx # 4-byte Reload
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: shrdl %cl, %esi, %ebp
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: shrl %cl, %edx
+; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: shrl %cl, %esi
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: movl %ecx, (%esp) # 4-byte Spill
+; X86-NEXT: cmovnel %esi, %ebp
+; X86-NEXT: movl $0, %eax
+; X86-NEXT: cmovnel %eax, %edx
+; X86-NEXT: cmovnel %eax, %esi
+; X86-NEXT: xorl %eax, %eax
+; X86-NEXT: movb %cl, %ch
+; X86-NEXT: subb $64, %ch
+; X86-NEXT: cmovael %eax, %esi
+; X86-NEXT: negb %ch
+; X86-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT: movb %ch, %cl
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: shldl %cl, %eax, %ebx
+; X86-NEXT: shll %cl, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: testb $32, %ch
+; X86-NEXT: cmovnel %eax, %ebx
+; X86-NEXT: orl %edx, %ebx
+; X86-NEXT: movl (%esp), %eax # 4-byte Reload
+; X86-NEXT: # kill: def $al killed $al killed $eax
+; X86-NEXT: addb $-64, %al
+; X86-NEXT: movb %al, %cl
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
+; X86-NEXT: shrl %cl, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: movl $0, %edx
+; X86-NEXT: cmovnel %edx, %eax
+; X86-NEXT: movl (%esp), %edx # 4-byte Reload
+; X86-NEXT: cmpb $64, %dl
+; X86-NEXT: cmovbl %ebx, %eax
+; X86-NEXT: movl $0, %ebx
+; X86-NEXT: cmovael %ebx, %ebp
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: testb $32, %ch
+; X86-NEXT: movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: cmovnel %ebx, %ecx
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT: movl %edx, %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: shrdl %cl, %edx, %ebx
+; X86-NEXT: testb $32, (%esp) # 1-byte Folded Reload
+; X86-NEXT: cmovnel {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
+; X86-NEXT: shrdl %cl, %ebp, %edx
+; X86-NEXT: testb $32, %cl
+; X86-NEXT: cmovnel {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
+; X86-NEXT: orl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X86-NEXT: movl (%esp), %ecx # 4-byte Reload
+; X86-NEXT: cmpb $64, %cl
+; X86-NEXT: cmovael %edx, %ebx
+; X86-NEXT: testb %cl, %cl
+; X86-NEXT: cmovel {{[0-9]+}}(%esp), %ebx
+; X86-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: cmovel {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: addl $-1, %ecx
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: adcl $-1, %ecx
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: adcl $-1, %ecx
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: adcl $-1, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
+; X86-NEXT: .p2align 4, 0x90
+; X86-NEXT: .LBB4_4: # %udiv-do-while
+; X86-NEXT: # =>This Inner Loop Header: Depth=1
+; X86-NEXT: movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X86-NEXT: shldl $1, %ebp, %esi
+; X86-NEXT: movl %esi, %edi
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT: shldl $1, %ebx, %ebp
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: shldl $1, %eax, %ebx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: shldl $1, %ecx, %eax
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT: shldl $1, %esi, %ecx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: orl %edx, %ecx
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: shldl $1, %ecx, %esi
+; X86-NEXT: orl %edx, %esi
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT: shldl $1, %esi, %ecx
+; X86-NEXT: orl %edx, %ecx
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: addl %esi, %esi
+; X86-NEXT: orl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: cmpl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: sbbl %ebx, %ecx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: sbbl %ebp, %ecx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: sbbl %edi, %ecx
+; X86-NEXT: sarl $31, %ecx
+; X86-NEXT: movl %ecx, %edx
+; X86-NEXT: andl $1, %edx
+; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %ecx, %esi
+; X86-NEXT: andl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movl %ecx, %edi
+; X86-NEXT: andl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: movl %ecx, %edx
+; X86-NEXT: andl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: andl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: subl %ecx, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: sbbl %edx, %ebx
+; X86-NEXT: movl %ebx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: sbbl %edi, %ebp
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: sbbl %esi, %eax
+; X86-NEXT: movl %eax, %esi
+; X86-NEXT: movl (%esp), %edx # 4-byte Reload
+; X86-NEXT: addl $-1, %edx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: adcl $-1, %ecx
+; X86-NEXT: adcl $-1, %edi
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X86-NEXT: adcl $-1, %ebp
+; X86-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: orl %ebp, %ecx
+; X86-NEXT: movl %edx, (%esp) # 4-byte Spill
+; X86-NEXT: orl %edi, %edx
+; X86-NEXT: orl %ecx, %edx
+; X86-NEXT: jne .LBB4_4
+; X86-NEXT: # %bb.5:
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
+; X86-NEXT: .LBB4_7: # %udiv-loop-exit
+; X86-NEXT: shldl $1, %ebx, %edx
+; X86-NEXT: orl %eax, %edx
+; X86-NEXT: shldl $1, %esi, %ebx
+; X86-NEXT: orl %eax, %ebx
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
+; X86-NEXT: shldl $1, %ebp, %esi
+; X86-NEXT: orl %eax, %esi
+; X86-NEXT: addl %ebp, %ebp
+; X86-NEXT: orl %ecx, %ebp
+; X86-NEXT: .LBB4_8: # %udiv-end
+; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %ebp, (%eax)
+; X86-NEXT: movl %esi, 4(%eax)
+; X86-NEXT: movl %ebx, 8(%eax)
+; X86-NEXT: movl %edx, 12(%eax)
+; X86-NEXT: movl %edx, %edi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %eax, %ecx
+; X86-NEXT: imull %esi, %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: imull %ebp, %edx
+; X86-NEXT: addl %ecx, %edx
+; X86-NEXT: movl %edx, %ecx
+; X86-NEXT: mull %ebp
+; X86-NEXT: movl %eax, (%esp) # 4-byte Spill
+; X86-NEXT: addl %edx, %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movl %esi, %eax
+; X86-NEXT: mull %ebx
+; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: imull %esi, %edi
+; X86-NEXT: movl %edi, %edx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: imull %edi, %ebx
+; X86-NEXT: addl %edx, %ebx
+; X86-NEXT: addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx # 4-byte Folded Reload
+; X86-NEXT: addl (%esp), %eax # 4-byte Folded Reload
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: adcl %ecx, %ebx
+; X86-NEXT: movl %ebp, %eax
+; X86-NEXT: mull %esi
+; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: movl %eax, (%esp) # 4-byte Spill
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: mull %esi
+; X86-NEXT: movl %edx, %ecx
+; X86-NEXT: movl %eax, %esi
+; X86-NEXT: addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X86-NEXT: adcl $0, %ecx
+; X86-NEXT: movl %ebp, %eax
+; X86-NEXT: mull %edi
+; X86-NEXT: movl %edx, %ebp
+; X86-NEXT: addl %esi, %eax
+; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
+; X86-NEXT: adcl %ecx, %ebp
+; X86-NEXT: setb %cl
+; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
+; X86-NEXT: mull %edi
+; X86-NEXT: addl %ebp, %eax
+; X86-NEXT: movzbl %cl, %ecx
+; X86-NEXT: adcl %ecx, %edx
+; X86-NEXT: addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
+; X86-NEXT: adcl %ebx, %edx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
+; X86-NEXT: subl (%esp), %ebx # 4-byte Folded Reload
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: sbbl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: sbbl %eax, %edi
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: sbbl %edx, %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: movl %ebx, (%eax)
+; X86-NEXT: movl %esi, 4(%eax)
+; X86-NEXT: movl %edi, 8(%eax)
+; X86-NEXT: movl %ecx, 12(%eax)
+; X86-NEXT: addl $72, %esp
+; X86-NEXT: popl %esi
+; X86-NEXT: popl %edi
+; X86-NEXT: popl %ebx
+; X86-NEXT: popl %ebp
+; X86-NEXT: retl $4
;
; X64-LABEL: scalar_i128:
; X64: # %bb.0:
diff --git a/llvm/test/CodeGen/X86/shift-combine.ll b/llvm/test/CodeGen/X86/shift-combine.ll
index 1795cbda1e8c..815c96540e45 100644
--- a/llvm/test/CodeGen/X86/shift-combine.ll
+++ b/llvm/test/CodeGen/X86/shift-combine.ll
@@ -671,6 +671,45 @@ define i32 @logic_tree_with_mismatching_shifts2_i32(i32 %a, i32 %b, i32 %c, i32
}
define <4 x i32> @or_tree_with_shifts_vec_i32(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d) {
+; X32-LABEL: or_tree_with_shifts_vec_i32:
+; X32: # %bb.0:
+; X32-NEXT: pushl %edi
+; X32-NEXT: .cfi_def_cfa_offset 8
+; X32-NEXT: pushl %esi
+; X32-NEXT: .cfi_def_cfa_offset 12
+; X32-NEXT: .cfi_offset %esi, -12
+; X32-NEXT: .cfi_offset %edi, -8
+; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT: orl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT: shll $16, %ecx
+; X32-NEXT: orl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT: orl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT: orl {{[0-9]+}}(%esp), %edx
+; X32-NEXT: shll $16, %edx
+; X32-NEXT: orl {{[0-9]+}}(%esp), %edx
+; X32-NEXT: orl {{[0-9]+}}(%esp), %edx
+; X32-NEXT: orl {{[0-9]+}}(%esp), %esi
+; X32-NEXT: shll $16, %esi
+; X32-NEXT: orl {{[0-9]+}}(%esp), %esi
+; X32-NEXT: orl {{[0-9]+}}(%esp), %esi
+; X32-NEXT: orl {{[0-9]+}}(%esp), %edi
+; X32-NEXT: shll $16, %edi
+; X32-NEXT: orl {{[0-9]+}}(%esp), %edi
+; X32-NEXT: orl {{[0-9]+}}(%esp), %edi
+; X32-NEXT: movl %edi, 12(%eax)
+; X32-NEXT: movl %esi, 8(%eax)
+; X32-NEXT: movl %edx, 4(%eax)
+; X32-NEXT: movl %ecx, (%eax)
+; X32-NEXT: popl %esi
+; X32-NEXT: .cfi_def_cfa_offset 8
+; X32-NEXT: popl %edi
+; X32-NEXT: .cfi_def_cfa_offset 4
+; X32-NEXT: retl $4
+;
; X64-LABEL: or_tree_with_shifts_vec_i32:
; X64: # %bb.0:
; X64-NEXT: por %xmm2, %xmm0
@@ -687,6 +726,53 @@ define <4 x i32> @or_tree_with_shifts_vec_i32(<4 x i32> %a, <4 x i32> %b, <4 x i
}
define <4 x i32> @or_tree_with_mismatching_shifts_vec_i32(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d) {
+; X32-LABEL: or_tree_with_mismatching_shifts_vec_i32:
+; X32: # %bb.0:
+; X32-NEXT: pushl %edi
+; X32-NEXT: .cfi_def_cfa_offset 8
+; X32-NEXT: pushl %esi
+; X32-NEXT: .cfi_def_cfa_offset 12
+; X32-NEXT: .cfi_offset %esi, -12
+; X32-NEXT: .cfi_offset %edi, -8
+; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X32-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X32-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT: shll $16, %eax
+; X32-NEXT: shll $17, %ecx
+; X32-NEXT: orl {{[0-9]+}}(%esp), %eax
+; X32-NEXT: orl {{[0-9]+}}(%esp), %ecx
+; X32-NEXT: orl %eax, %ecx
+; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT: shll $16, %eax
+; X32-NEXT: shll $17, %edx
+; X32-NEXT: orl {{[0-9]+}}(%esp), %eax
+; X32-NEXT: orl {{[0-9]+}}(%esp), %edx
+; X32-NEXT: orl %eax, %edx
+; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT: shll $16, %eax
+; X32-NEXT: shll $17, %esi
+; X32-NEXT: orl {{[0-9]+}}(%esp), %eax
+; X32-NEXT: orl {{[0-9]+}}(%esp), %esi
+; X32-NEXT: orl %eax, %esi
+; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT: shll $16, %eax
+; X32-NEXT: shll $17, %edi
+; X32-NEXT: orl {{[0-9]+}}(%esp), %eax
+; X32-NEXT: orl {{[0-9]+}}(%esp), %edi
+; X32-NEXT: orl %eax, %edi
+; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X32-NEXT: movl %ecx, 12(%eax)
+; X32-NEXT: movl %edx, 8(%eax)
+; X32-NEXT: movl %esi, 4(%eax)
+; X32-NEXT: movl %edi, (%eax)
+; X32-NEXT: popl %esi
+; X32-NEXT: .cfi_def_cfa_offset 8
+; X32-NEXT: popl %edi
+; X32-NEXT: .cfi_def_cfa_offset 4
+; X32-NEXT: retl $4
+;
; X64-LABEL: or_tree_with_mismatching_shifts_vec_i32:
; X64: # %bb.0:
; X64-NEXT: pslld $16, %xmm0
More information about the llvm-commits
mailing list