[TableGen] Fix regunit superset calculation

Keep creating new supersets from new supersets until we reach a fixed point. For most targets this ends up with fewer regunitsets overall because it makes pruning more effective.

Author: jayfoad

llvm/test/CodeGen/X86/2011-10-19-LegelizeLoad.ll

@@ -17,21 +17,20 @@ target triple = "x86_64-unknown-linux-gnu"
 define dso_local i32 @main() nounwind uwtable {
 ; CHECK-LABEL: main:
 ; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: movl i(%rip), %esi
+; CHECK-NEXT: movl i(%rip), %edx
 ; CHECK-NEXT: movl j(%rip), %eax
-; CHECK-NEXT: movl %esi, %edx
-; CHECK-NEXT: shrl $8, %edx
+; CHECK-NEXT: movl %edx, %esi
+; CHECK-NEXT: shrl $8, %esi
 ; CHECK-NEXT: movsbl %al, %ecx
 ; CHECK-NEXT: shrl $8, %eax
 ; CHECK-NEXT: cbtw
-; CHECK-NEXT: idivb %dl
-; CHECK-NEXT: movl %eax, %edx
-; CHECK-NEXT: movl %ecx, %eax
 ; CHECK-NEXT: idivb %sil
-; CHECK-NEXT: movzbl %dl, %ecx
+; CHECK-NEXT: movzbl %al, %esi
+; CHECK-NEXT: movl %ecx, %eax
+; CHECK-NEXT: idivb %dl
 ; CHECK-NEXT: movzbl %al, %eax
 ; CHECK-NEXT: movd %eax, %xmm0
-; CHECK-NEXT: pinsrb $1, %ecx, %xmm0
+; CHECK-NEXT: pinsrb $1, %esi, %xmm0
 ; CHECK-NEXT: pextrw $0, %xmm0, res(%rip)
 ; CHECK-NEXT: xorl %eax, %eax
 ; CHECK-NEXT: retq

llvm/test/CodeGen/X86/abs.ll

@@ -487,10 +487,10 @@ define <16 x i8> @test_v16i8(<16 x i8> %a) nounwind {
 ; X86: # %bb.0:
 ; X86-NEXT: pushl %ebx
 ; X86-NEXT: subl $12, %esp
+; X86-NEXT: movb {{[0-9]+}}(%esp), %ch
 ; X86-NEXT: movb {{[0-9]+}}(%esp), %bh
 ; X86-NEXT: movb {{[0-9]+}}(%esp), %bl
 ; X86-NEXT: movb {{[0-9]+}}(%esp), %dh
-; X86-NEXT: movb {{[0-9]+}}(%esp), %ch
 ; X86-NEXT: movb {{[0-9]+}}(%esp), %ah
 ; X86-NEXT: movb {{[0-9]+}}(%esp), %dl
 ; X86-NEXT: movb {{[0-9]+}}(%esp), %cl
@@ -509,26 +509,23 @@ define <16 x i8> @test_v16i8(<16 x i8> %a) nounwind {
 ; X86-NEXT: xorb %al, %ah
 ; X86-NEXT: subb %al, %ah
 ; X86-NEXT: movb %ah, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
-; X86-NEXT: movb %ch, %al
-; X86-NEXT: sarb $7, %al
-; X86-NEXT: xorb %al, %ch
-; X86-NEXT: subb %al, %ch
-; X86-NEXT: movb %ch, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
 ; X86-NEXT: movb %dh, %al
 ; X86-NEXT: sarb $7, %al
 ; X86-NEXT: xorb %al, %dh
 ; X86-NEXT: subb %al, %dh
-; X86-NEXT: movb %dh, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
 ; X86-NEXT: movl %ebx, %eax
 ; X86-NEXT: sarb $7, %al
 ; X86-NEXT: xorb %al, %bl
 ; X86-NEXT: subb %al, %bl
-; X86-NEXT: movb %bl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
 ; X86-NEXT: movb %bh, %al
 ; X86-NEXT: sarb $7, %al
 ; X86-NEXT: xorb %al, %bh
 ; X86-NEXT: subb %al, %bh
-; X86-NEXT: movb %bh, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
+; X86-NEXT: movb %ch, %al
+; X86-NEXT: sarb $7, %al
+; X86-NEXT: xorb %al, %ch
+; X86-NEXT: subb %al, %ch
+; X86-NEXT: movb %ch, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
 ; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT: movl %ecx, %eax
 ; X86-NEXT: sarb $7, %al
@@ -547,21 +544,24 @@ define <16 x i8> @test_v16i8(<16 x i8> %a) nounwind {
 ; X86-NEXT: xorb %al, %cl
 ; X86-NEXT: subb %al, %cl
 ; X86-NEXT: movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
-; X86-NEXT: movb {{[0-9]+}}(%esp), %bh
-; X86-NEXT: movb %bh, %al
+; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl %ecx, %eax
 ; X86-NEXT: sarb $7, %al
-; X86-NEXT: xorb %al, %bh
-; X86-NEXT: subb %al, %bh
-; X86-NEXT: movb {{[0-9]+}}(%esp), %bl
-; X86-NEXT: movl %ebx, %eax
+; X86-NEXT: xorb %al, %cl
+; X86-NEXT: subb %al, %cl
+; X86-NEXT: movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
+; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl %ecx, %eax
 ; X86-NEXT: sarb $7, %al
-; X86-NEXT: xorb %al, %bl
-; X86-NEXT: subb %al, %bl
-; X86-NEXT: movb {{[0-9]+}}(%esp), %dh
-; X86-NEXT: movb %dh, %al
+; X86-NEXT: xorb %al, %cl
+; X86-NEXT: subb %al, %cl
+; X86-NEXT: movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
+; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl %ecx, %eax
 ; X86-NEXT: sarb $7, %al
-; X86-NEXT: xorb %al, %dh
-; X86-NEXT: subb %al, %dh
+; X86-NEXT: xorb %al, %cl
+; X86-NEXT: subb %al, %cl
+; X86-NEXT: movb %cl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
 ; X86-NEXT: movb {{[0-9]+}}(%esp), %ch
 ; X86-NEXT: movb %ch, %al
 ; X86-NEXT: sarb $7, %al
@@ -581,9 +581,12 @@ define <16 x i8> @test_v16i8(<16 x i8> %a) nounwind {
 ; X86-NEXT: movb %cl, 15(%eax)
 ; X86-NEXT: movb %dl, 14(%eax)
 ; X86-NEXT: movb %ch, 13(%eax)
-; X86-NEXT: movb %dh, 12(%eax)
-; X86-NEXT: movb %bl, 11(%eax)
-; X86-NEXT: movb %bh, 10(%eax)
+; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
+; X86-NEXT: movb %cl, 12(%eax)
+; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
+; X86-NEXT: movb %cl, 11(%eax)
+; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
+; X86-NEXT: movb %cl, 10(%eax)
 ; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X86-NEXT: movb %cl, 9(%eax)
 ; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
@@ -592,12 +595,9 @@ define <16 x i8> @test_v16i8(<16 x i8> %a) nounwind {
 ; X86-NEXT: movb %cl, 7(%eax)
 ; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X86-NEXT: movb %cl, 6(%eax)
-; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X86-NEXT: movb %cl, 5(%eax)
-; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X86-NEXT: movb %cl, 4(%eax)
-; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
-; X86-NEXT: movb %cl, 3(%eax)
+; X86-NEXT: movb %bh, 5(%eax)
+; X86-NEXT: movb %bl, 4(%eax)
+; X86-NEXT: movb %dh, 3(%eax)
 ; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload
 ; X86-NEXT: movb %cl, 2(%eax)
 ; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 1-byte Folded Reload