; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-linux | FileCheck %s --check-prefix=X64
; RUN: llc < %s -mtriple=i686 -mattr=cmov | FileCheck %s --check-prefix=X86
declare i4 @llvm.smul.fix.sat.i4 (i4, i4, i32)
declare i32 @llvm.smul.fix.sat.i32 (i32, i32, i32)
declare i64 @llvm.smul.fix.sat.i64 (i64, i64, i32)
declare <4 x i32> @llvm.smul.fix.sat.v4i32(<4 x i32>, <4 x i32>, i32)
define i32 @func(i32 %x, i32 %y) nounwind {
; X64-LABEL: func:
; X64: # %bb.0:
; X64-NEXT: movslq %esi, %rax
; X64-NEXT: movslq %edi, %rcx
; X64-NEXT: imulq %rax, %rcx
; X64-NEXT: movq %rcx, %rax
; X64-NEXT: shrq $32, %rax
; X64-NEXT: shrdl $2, %eax, %ecx
; X64-NEXT: cmpl $2, %eax
; X64-NEXT: movl $2147483647, %edx # imm = 0x7FFFFFFF
; X64-NEXT: cmovll %ecx, %edx
; X64-NEXT: cmpl $-2, %eax
; X64-NEXT: movl $-2147483648, %eax # imm = 0x80000000
; X64-NEXT: cmovgel %edx, %eax
; X64-NEXT: retq
;
; X86-LABEL: func:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: imull {{[0-9]+}}(%esp)
; X86-NEXT: shrdl $2, %edx, %eax
; X86-NEXT: cmpl $2, %edx
; X86-NEXT: movl $2147483647, %ecx # imm = 0x7FFFFFFF
; X86-NEXT: cmovgel %ecx, %eax
; X86-NEXT: cmpl $-2, %edx
; X86-NEXT: movl $-2147483648, %ecx # imm = 0x80000000
; X86-NEXT: cmovll %ecx, %eax
; X86-NEXT: retl
%tmp = call i32 @llvm.smul.fix.sat.i32(i32 %x, i32 %y, i32 2)
ret i32 %tmp
}
define i64 @func2(i64 %x, i64 %y) nounwind {
; X64-LABEL: func2:
; X64: # %bb.0:
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: imulq %rsi
; X64-NEXT: shrdq $2, %rdx, %rax
; X64-NEXT: cmpq $2, %rdx
; X64-NEXT: movabsq $9223372036854775807, %rcx # imm = 0x7FFFFFFFFFFFFFFF
; X64-NEXT: cmovgeq %rcx, %rax
; X64-NEXT: cmpq $-2, %rdx
; X64-NEXT: movabsq $-9223372036854775808, %rcx # imm = 0x8000000000000000
; X64-NEXT: cmovlq %rcx, %rax
; X64-NEXT: retq
;
; X86-LABEL: func2:
; X86: # %bb.0:
; X86-NEXT: pushl %ebp
; X86-NEXT: pushl %ebx
; X86-NEXT: pushl %edi
; X86-NEXT: pushl %esi
; X86-NEXT: subl $8, %esp
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull %esi
; X86-NEXT: movl %edx, %edi
; X86-NEXT: movl %eax, %ebp
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull %ebx
; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-NEXT: addl %edx, %ebp
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: adcl $0, %edi
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: imull %esi
; X86-NEXT: movl %edx, %esi
; X86-NEXT: movl %eax, (%esp) # 4-byte Spill
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull %ebx
; X86-NEXT: movl %eax, %ebx
; X86-NEXT: addl %ebp, %ebx
; X86-NEXT: adcl %edi, %edx
; X86-NEXT: adcl $0, %esi
; X86-NEXT: addl (%esp), %edx # 4-byte Folded Reload
; X86-NEXT: adcl $0, %esi
; X86-NEXT: movl %edx, %edi
; X86-NEXT: subl {{[0-9]+}}(%esp), %edi
; X86-NEXT: movl %esi, %ebp
; X86-NEXT: sbbl $0, %ebp
; X86-NEXT: testl %ecx, %ecx
; X86-NEXT: cmovnsl %esi, %ebp
; X86-NEXT: cmovnsl %edx, %edi
; X86-NEXT: movl %edi, %ecx
; X86-NEXT: subl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %ebp, %edx
; X86-NEXT: sbbl $0, %edx
; X86-NEXT: cmpl $0, {{[0-9]+}}(%esp)
; X86-NEXT: cmovnsl %ebp, %edx
; X86-NEXT: cmovnsl %edi, %ecx
; X86-NEXT: testl %edx, %edx
; X86-NEXT: setg %ah
; X86-NEXT: sete (%esp) # 1-byte Folded Spill
; X86-NEXT: cmpl $2, %ecx
; X86-NEXT: setae %al
; X86-NEXT: andb (%esp), %al # 1-byte Folded Reload
; X86-NEXT: orb %ah, %al
; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %ebp # 4-byte Reload
; X86-NEXT: shrdl $2, %ebx, %ebp
; X86-NEXT: shrdl $2, %ecx, %ebx
; X86-NEXT: testb %al, %al
; X86-NEXT: movl $2147483647, %esi # imm = 0x7FFFFFFF
; X86-NEXT: cmovel %ebx, %esi
; X86-NEXT: movl $-1, %edi
; X86-NEXT: cmovel %ebp, %edi
; X86-NEXT: cmpl $-1, %edx
; X86-NEXT: setl %dl
; X86-NEXT: sete %al
; X86-NEXT: cmpl $-2, %ecx
; X86-NEXT: setb %cl
; X86-NEXT: andb %al, %cl
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: orb %dl, %cl
; X86-NEXT: cmovel %edi, %eax
; X86-NEXT: movl $-2147483648, %edx # imm = 0x80000000
; X86-NEXT: cmovel %esi, %edx
; X86-NEXT: addl $8, %esp
; X86-NEXT: popl %esi
; X86-NEXT: popl %edi
; X86-NEXT: popl %ebx
; X86-NEXT: popl %ebp
; X86-NEXT: retl
%tmp = call i64 @llvm.smul.fix.sat.i64(i64 %x, i64 %y, i32 2)
ret i64 %tmp
}
define i4 @func3(i4 %x, i4 %y) nounwind {
; X64-LABEL: func3:
; X64: # %bb.0:
; X64-NEXT: shlb $4, %sil
; X64-NEXT: sarb $4, %sil
; X64-NEXT: shlb $4, %dil
; X64-NEXT: movsbl %dil, %eax
; X64-NEXT: movsbl %sil, %ecx
; X64-NEXT: imull %eax, %ecx
; X64-NEXT: movl %ecx, %eax
; X64-NEXT: shrb $2, %al
; X64-NEXT: shrl $8, %ecx
; X64-NEXT: movl %ecx, %edx
; X64-NEXT: shlb $6, %dl
; X64-NEXT: orb %al, %dl
; X64-NEXT: movzbl %dl, %eax
; X64-NEXT: cmpb $2, %cl
; X64-NEXT: movl $127, %edx
; X64-NEXT: cmovll %eax, %edx
; X64-NEXT: cmpb $-2, %cl
; X64-NEXT: movl $128, %eax
; X64-NEXT: cmovgel %edx, %eax
; X64-NEXT: sarb $4, %al
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
;
; X86-LABEL: func3:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shlb $4, %al
; X86-NEXT: sarb $4, %al
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: shlb $4, %cl
; X86-NEXT: movsbl %cl, %ecx
; X86-NEXT: movsbl %al, %eax
; X86-NEXT: imull %ecx, %eax
; X86-NEXT: movb %ah, %cl
; X86-NEXT: shlb $6, %cl
; X86-NEXT: shrb $2, %al
; X86-NEXT: orb %cl, %al
; X86-NEXT: movzbl %al, %ecx
; X86-NEXT: cmpb $2, %ah
; X86-NEXT: movl $127, %edx
; X86-NEXT: cmovll %ecx, %edx
; X86-NEXT: cmpb $-2, %ah
; X86-NEXT: movl $128, %eax
; X86-NEXT: cmovgel %edx, %eax
; X86-NEXT: sarb $4, %al
; X86-NEXT: # kill: def $al killed $al killed $eax
; X86-NEXT: retl
%tmp = call i4 @llvm.smul.fix.sat.i4(i4 %x, i4 %y, i32 2)
ret i4 %tmp
}
define <4 x i32> @vec(<4 x i32> %x, <4 x i32> %y) nounwind {
; X64-LABEL: vec:
; X64: # %bb.0:
; X64-NEXT: pshufd {{.*#+}} xmm2 = xmm1[3,3,3,3]
; X64-NEXT: movd %xmm2, %eax
; X64-NEXT: cltq
; X64-NEXT: pshufd {{.*#+}} xmm2 = xmm0[3,3,3,3]
; X64-NEXT: movd %xmm2, %ecx
; X64-NEXT: movslq %ecx, %rdx
; X64-NEXT: imulq %rax, %rdx
; X64-NEXT: movq %rdx, %rcx
; X64-NEXT: shrq $32, %rcx
; X64-NEXT: shrdl $2, %ecx, %edx
; X64-NEXT: cmpl $2, %ecx
; X64-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF
; X64-NEXT: cmovgel %eax, %edx
; X64-NEXT: cmpl $-2, %ecx
; X64-NEXT: movl $-2147483648, %ecx # imm = 0x80000000
; X64-NEXT: cmovll %ecx, %edx
; X64-NEXT: movd %edx, %xmm2
; X64-NEXT: pshufd {{.*#+}} xmm3 = xmm1[2,3,2,3]
; X64-NEXT: movd %xmm3, %edx
; X64-NEXT: movslq %edx, %rdx
; X64-NEXT: pshufd {{.*#+}} xmm3 = xmm0[2,3,2,3]
; X64-NEXT: movd %xmm3, %esi
; X64-NEXT: movslq %esi, %rsi
; X64-NEXT: imulq %rdx, %rsi
; X64-NEXT: movq %rsi, %rdx
; X64-NEXT: shrq $32, %rdx
; X64-NEXT: shrdl $2, %edx, %esi
; X64-NEXT: cmpl $2, %edx
; X64-NEXT: cmovgel %eax, %esi
; X64-NEXT: cmpl $-2, %edx
; X64-NEXT: cmovll %ecx, %esi
; X64-NEXT: movd %esi, %xmm3
; X64-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
; X64-NEXT: movd %xmm1, %edx
; X64-NEXT: movslq %edx, %rdx
; X64-NEXT: movd %xmm0, %esi
; X64-NEXT: movslq %esi, %rsi
; X64-NEXT: imulq %rdx, %rsi
; X64-NEXT: movq %rsi, %rdx
; X64-NEXT: shrq $32, %rdx
; X64-NEXT: shrdl $2, %edx, %esi
; X64-NEXT: cmpl $2, %edx
; X64-NEXT: cmovgel %eax, %esi
; X64-NEXT: cmpl $-2, %edx
; X64-NEXT: cmovll %ecx, %esi
; X64-NEXT: movd %esi, %xmm2
; X64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,1,1]
; X64-NEXT: movd %xmm1, %edx
; X64-NEXT: movslq %edx, %rdx
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,1,1]
; X64-NEXT: movd %xmm0, %esi
; X64-NEXT: movslq %esi, %rsi
; X64-NEXT: imulq %rdx, %rsi
; X64-NEXT: movq %rsi, %rdx
; X64-NEXT: shrq $32, %rdx
; X64-NEXT: shrdl $2, %edx, %esi
; X64-NEXT: cmpl $2, %edx
; X64-NEXT: cmovgel %eax, %esi
; X64-NEXT: cmpl $-2, %edx
; X64-NEXT: cmovll %ecx, %esi
; X64-NEXT: movd %esi, %xmm0
; X64-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
; X64-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
; X64-NEXT: movdqa %xmm2, %xmm0
; X64-NEXT: retq
;
; X86-LABEL: vec:
; X86: # %bb.0:
; X86-NEXT: pushl %ebp
; X86-NEXT: pushl %ebx
; X86-NEXT: pushl %edi
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: imull {{[0-9]+}}(%esp)
; X86-NEXT: movl %eax, %ecx
; X86-NEXT: shrdl $2, %edx, %ecx
; X86-NEXT: cmpl $2, %edx
; X86-NEXT: movl $2147483647, %ebp # imm = 0x7FFFFFFF
; X86-NEXT: cmovgel %ebp, %ecx
; X86-NEXT: cmpl $-2, %edx
; X86-NEXT: movl $-2147483648, %esi # imm = 0x80000000
; X86-NEXT: cmovll %esi, %ecx
; X86-NEXT: movl %edi, %eax
; X86-NEXT: imull {{[0-9]+}}(%esp)
; X86-NEXT: movl %eax, %edi
; X86-NEXT: shrdl $2, %edx, %edi
; X86-NEXT: cmpl $2, %edx
; X86-NEXT: cmovgel %ebp, %edi
; X86-NEXT: cmpl $-2, %edx
; X86-NEXT: cmovll %esi, %edi
; X86-NEXT: movl %ebx, %eax
; X86-NEXT: imull {{[0-9]+}}(%esp)
; X86-NEXT: movl %eax, %ebx
; X86-NEXT: shrdl $2, %edx, %ebx
; X86-NEXT: cmpl $2, %edx
; X86-NEXT: cmovgel %ebp, %ebx
; X86-NEXT: cmpl $-2, %edx
; X86-NEXT: cmovll %esi, %ebx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: imull {{[0-9]+}}(%esp)
; X86-NEXT: shrdl $2, %edx, %eax
; X86-NEXT: cmpl $2, %edx
; X86-NEXT: cmovgel %ebp, %eax
; X86-NEXT: cmpl $-2, %edx
; X86-NEXT: cmovll %esi, %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl %eax, 12(%edx)
; X86-NEXT: movl %ebx, 8(%edx)
; X86-NEXT: movl %edi, 4(%edx)
; X86-NEXT: movl %ecx, (%edx)
; X86-NEXT: movl %edx, %eax
; X86-NEXT: popl %esi
; X86-NEXT: popl %edi
; X86-NEXT: popl %ebx
; X86-NEXT: popl %ebp
; X86-NEXT: retl $4
%tmp = call <4 x i32> @llvm.smul.fix.sat.v4i32(<4 x i32> %x, <4 x i32> %y, i32 2)
ret <4 x i32> %tmp
}
; These result in regular integer multiplication
define i32 @func4(i32 %x, i32 %y) nounwind {
; X64-LABEL: func4:
; X64: # %bb.0:
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: movl %edi, %ecx
; X64-NEXT: xorl %esi, %ecx
; X64-NEXT: sets %al
; X64-NEXT: addl $2147483647, %eax # imm = 0x7FFFFFFF
; X64-NEXT: imull %esi, %edi
; X64-NEXT: cmovnol %edi, %eax
; X64-NEXT: retq
;
; X86-LABEL: func4:
; X86: # %bb.0:
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: xorl %ecx, %ecx
; X86-NEXT: movl %eax, %esi
; X86-NEXT: xorl %edx, %esi
; X86-NEXT: sets %cl
; X86-NEXT: addl $2147483647, %ecx # imm = 0x7FFFFFFF
; X86-NEXT: imull %edx, %eax
; X86-NEXT: cmovol %ecx, %eax
; X86-NEXT: popl %esi
; X86-NEXT: retl
%tmp = call i32 @llvm.smul.fix.sat.i32(i32 %x, i32 %y, i32 0)
ret i32 %tmp
}
define i64 @func5(i64 %x, i64 %y) {
; X64-LABEL: func5:
; X64: # %bb.0:
; X64-NEXT: xorl %ecx, %ecx
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: xorq %rsi, %rax
; X64-NEXT: sets %cl
; X64-NEXT: movabsq $9223372036854775807, %rax # imm = 0x7FFFFFFFFFFFFFFF
; X64-NEXT: addq %rcx, %rax
; X64-NEXT: imulq %rsi, %rdi
; X64-NEXT: cmovnoq %rdi, %rax
; X64-NEXT: retq
;
; X86-LABEL: func5:
; X86: # %bb.0:
; X86-NEXT: pushl %ebp
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: pushl %ebx
; X86-NEXT: .cfi_def_cfa_offset 12
; X86-NEXT: pushl %edi
; X86-NEXT: .cfi_def_cfa_offset 16
; X86-NEXT: pushl %esi
; X86-NEXT: .cfi_def_cfa_offset 20
; X86-NEXT: subl $12, %esp
; X86-NEXT: .cfi_def_cfa_offset 32
; X86-NEXT: .cfi_offset %esi, -20
; X86-NEXT: .cfi_offset %edi, -16
; X86-NEXT: .cfi_offset %ebx, -12
; X86-NEXT: .cfi_offset %ebp, -8
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %ecx, %edx
; X86-NEXT: sarl $31, %edx
; X86-NEXT: movl %esi, %ebx
; X86-NEXT: movl %esi, %ebp
; X86-NEXT: imull %edx, %ebx
; X86-NEXT: mull %edx
; X86-NEXT: movl %edx, %esi
; X86-NEXT: movl %eax, %edi
; X86-NEXT: addl %eax, %esi
; X86-NEXT: addl %ebx, %esi
; X86-NEXT: movl %ebp, %eax
; X86-NEXT: sarl $31, %eax
; X86-NEXT: movl %eax, %ebp
; X86-NEXT: imull %ecx, %ebp
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: movl %edx, %ebx
; X86-NEXT: addl %ebp, %ebx
; X86-NEXT: addl %eax, %ebx
; X86-NEXT: addl %edi, %eax
; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-NEXT: adcl %esi, %ebx
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
; X86-NEXT: movl %ebp, %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-NEXT: mull %edi
; X86-NEXT: movl %edx, %esi
; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull %edi
; X86-NEXT: movl %edx, %edi
; X86-NEXT: addl %eax, %esi
; X86-NEXT: adcl $0, %edi
; X86-NEXT: movl %ebp, %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: mull %edx
; X86-NEXT: movl %edx, %ebp
; X86-NEXT: addl %eax, %esi
; X86-NEXT: adcl %edi, %ebp
; X86-NEXT: setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: addl %ebp, %eax
; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 1-byte Folded Reload
; X86-NEXT: adcl %edi, %edx
; X86-NEXT: addl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Folded Reload
; X86-NEXT: adcl %ebx, %edx
; X86-NEXT: movl %esi, %ebx
; X86-NEXT: sarl $31, %ebx
; X86-NEXT: xorl %ebx, %edx
; X86-NEXT: xorl %eax, %ebx
; X86-NEXT: xorl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: sarl $31, %ecx
; X86-NEXT: movl %ecx, %edi
; X86-NEXT: xorl $2147483647, %edi # imm = 0x7FFFFFFF
; X86-NEXT: orl %edx, %ebx
; X86-NEXT: notl %ecx
; X86-NEXT: cmovel {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Folded Reload
; X86-NEXT: cmovel %esi, %edi
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: movl %edi, %edx
; X86-NEXT: addl $12, %esp
; X86-NEXT: .cfi_def_cfa_offset 20
; X86-NEXT: popl %esi
; X86-NEXT: .cfi_def_cfa_offset 16
; X86-NEXT: popl %edi
; X86-NEXT: .cfi_def_cfa_offset 12
; X86-NEXT: popl %ebx
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: popl %ebp
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl
%tmp = call i64 @llvm.smul.fix.sat.i64(i64 %x, i64 %y, i32 0)
ret i64 %tmp
}
define i4 @func6(i4 %x, i4 %y) nounwind {
; X64-LABEL: func6:
; X64: # %bb.0:
; X64-NEXT: movl %edi, %eax
; X64-NEXT: shlb $4, %sil
; X64-NEXT: sarb $4, %sil
; X64-NEXT: shlb $4, %al
; X64-NEXT: xorl %ecx, %ecx
; X64-NEXT: movl %eax, %edx
; X64-NEXT: xorb %sil, %dl
; X64-NEXT: sets %cl
; X64-NEXT: addl $127, %ecx
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: imulb %sil
; X64-NEXT: movzbl %al, %eax
; X64-NEXT: cmovol %ecx, %eax
; X64-NEXT: sarb $4, %al
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
;
; X86-LABEL: func6:
; X86: # %bb.0:
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: shlb $4, %cl
; X86-NEXT: sarb $4, %cl
; X86-NEXT: movzbl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shlb $4, %al
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: movb %al, %ah
; X86-NEXT: xorb %cl, %ah
; X86-NEXT: sets %dl
; X86-NEXT: addl $127, %edx
; X86-NEXT: imulb %cl
; X86-NEXT: movzbl %al, %eax
; X86-NEXT: cmovol %edx, %eax
; X86-NEXT: sarb $4, %al
; X86-NEXT: # kill: def $al killed $al killed $eax
; X86-NEXT: retl
%tmp = call i4 @llvm.smul.fix.sat.i4(i4 %x, i4 %y, i32 0)
ret i4 %tmp
}
define <4 x i32> @vec2(<4 x i32> %x, <4 x i32> %y) nounwind {
; X64-LABEL: vec2:
; X64: # %bb.0:
; X64-NEXT: pshufd {{.*#+}} xmm2 = xmm1[3,3,3,3]
; X64-NEXT: movd %xmm2, %eax
; X64-NEXT: pshufd {{.*#+}} xmm2 = xmm0[3,3,3,3]
; X64-NEXT: movd %xmm2, %ecx
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: movl %ecx, %esi
; X64-NEXT: xorl %eax, %esi
; X64-NEXT: sets %dl
; X64-NEXT: addl $2147483647, %edx # imm = 0x7FFFFFFF
; X64-NEXT: imull %eax, %ecx
; X64-NEXT: cmovol %edx, %ecx
; X64-NEXT: movd %ecx, %xmm2
; X64-NEXT: pshufd {{.*#+}} xmm3 = xmm1[2,3,2,3]
; X64-NEXT: movd %xmm3, %eax
; X64-NEXT: pshufd {{.*#+}} xmm3 = xmm0[2,3,2,3]
; X64-NEXT: movd %xmm3, %ecx
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: movl %ecx, %esi
; X64-NEXT: xorl %eax, %esi
; X64-NEXT: sets %dl
; X64-NEXT: addl $2147483647, %edx # imm = 0x7FFFFFFF
; X64-NEXT: imull %eax, %ecx
; X64-NEXT: cmovol %edx, %ecx
; X64-NEXT: movd %ecx, %xmm3
; X64-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
; X64-NEXT: movd %xmm1, %eax
; X64-NEXT: movd %xmm0, %ecx
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: movl %ecx, %esi
; X64-NEXT: xorl %eax, %esi
; X64-NEXT: sets %dl
; X64-NEXT: addl $2147483647, %edx # imm = 0x7FFFFFFF
; X64-NEXT: imull %eax, %ecx
; X64-NEXT: cmovol %edx, %ecx
; X64-NEXT: movd %ecx, %xmm2
; X64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,1,1]
; X64-NEXT: movd %xmm1, %eax
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,1,1]
; X64-NEXT: movd %xmm0, %ecx
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: movl %ecx, %esi
; X64-NEXT: xorl %eax, %esi
; X64-NEXT: sets %dl
; X64-NEXT: addl $2147483647, %edx # imm = 0x7FFFFFFF
; X64-NEXT: imull %eax, %ecx
; X64-NEXT: cmovol %edx, %ecx
; X64-NEXT: movd %ecx, %xmm0
; X64-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
; X64-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
; X64-NEXT: movdqa %xmm2, %xmm0
; X64-NEXT: retq
;
; X86-LABEL: vec2:
; X86: # %bb.0:
; X86-NEXT: pushl %ebp
; X86-NEXT: pushl %ebx
; X86-NEXT: pushl %edi
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: movl %ecx, %edx
; X86-NEXT: xorl %edi, %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: sets %al
; X86-NEXT: addl $2147483647, %eax # imm = 0x7FFFFFFF
; X86-NEXT: imull %edi, %ecx
; X86-NEXT: cmovol %eax, %ecx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: movl %edx, %edi
; X86-NEXT: xorl %ebx, %edi
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-NEXT: sets %al
; X86-NEXT: addl $2147483647, %eax # imm = 0x7FFFFFFF
; X86-NEXT: imull %ebx, %edx
; X86-NEXT: cmovol %eax, %edx
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: movl %edi, %ebx
; X86-NEXT: xorl %esi, %ebx
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X86-NEXT: sets %al
; X86-NEXT: addl $2147483647, %eax # imm = 0x7FFFFFFF
; X86-NEXT: imull %esi, %edi
; X86-NEXT: cmovol %eax, %edi
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: movl %ebx, %esi
; X86-NEXT: xorl %ebp, %esi
; X86-NEXT: sets %al
; X86-NEXT: addl $2147483647, %eax # imm = 0x7FFFFFFF
; X86-NEXT: imull %ebp, %ebx
; X86-NEXT: cmovol %eax, %ebx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl %ebx, 12(%eax)
; X86-NEXT: movl %edi, 8(%eax)
; X86-NEXT: movl %edx, 4(%eax)
; X86-NEXT: movl %ecx, (%eax)
; X86-NEXT: popl %esi
; X86-NEXT: popl %edi
; X86-NEXT: popl %ebx
; X86-NEXT: popl %ebp
; X86-NEXT: retl $4
%tmp = call <4 x i32> @llvm.smul.fix.sat.v4i32(<4 x i32> %x, <4 x i32> %y, i32 0)
ret <4 x i32> %tmp
}
define i64 @func7(i64 %x, i64 %y) nounwind {
; X64-LABEL: func7:
; X64: # %bb.0:
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: imulq %rsi
; X64-NEXT: shrdq $32, %rdx, %rax
; X64-NEXT: cmpq $2147483647, %rdx # imm = 0x7FFFFFFF
; X64-NEXT: movabsq $9223372036854775807, %rcx # imm = 0x7FFFFFFFFFFFFFFF
; X64-NEXT: cmovgq %rcx, %rax
; X64-NEXT: cmpq $-2147483648, %rdx # imm = 0x80000000
; X64-NEXT: movabsq $-9223372036854775808, %rcx # imm = 0x8000000000000000
; X64-NEXT: cmovlq %rcx, %rax
; X64-NEXT: retq
;
; X86-LABEL: func7:
; X86: # %bb.0:
; X86-NEXT: pushl %ebp
; X86-NEXT: pushl %ebx
; X86-NEXT: pushl %edi
; X86-NEXT: pushl %esi
; X86-NEXT: pushl %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: movl %edx, %edi
; X86-NEXT: movl %eax, %ebp
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: addl %edx, %ebp
; X86-NEXT: adcl $0, %edi
; X86-NEXT: movl %esi, %eax
; X86-NEXT: imull {{[0-9]+}}(%esp)
; X86-NEXT: movl %edx, %ebx
; X86-NEXT: movl %eax, %ecx
; X86-NEXT: movl %esi, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: addl %ebp, %eax
; X86-NEXT: adcl %edi, %edx
; X86-NEXT: adcl $0, %ebx
; X86-NEXT: addl %ecx, %edx
; X86-NEXT: adcl $0, %ebx
; X86-NEXT: movl %edx, %ecx
; X86-NEXT: subl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %ebx, %esi
; X86-NEXT: sbbl $0, %esi
; X86-NEXT: cmpl $0, {{[0-9]+}}(%esp)
; X86-NEXT: cmovnsl %ebx, %esi
; X86-NEXT: cmovsl %ecx, %edx
; X86-NEXT: movl %edx, %edi
; X86-NEXT: subl {{[0-9]+}}(%esp), %edi
; X86-NEXT: movl %esi, %ecx
; X86-NEXT: sbbl $0, %ecx
; X86-NEXT: cmpl $0, {{[0-9]+}}(%esp)
; X86-NEXT: cmovnsl %esi, %ecx
; X86-NEXT: cmovsl %edi, %edx
; X86-NEXT: testl %edx, %edx
; X86-NEXT: setns {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
; X86-NEXT: sets %bh
; X86-NEXT: testl %ecx, %ecx
; X86-NEXT: setg {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
; X86-NEXT: sete %bl
; X86-NEXT: andb %bh, %bl
; X86-NEXT: orb {{[-0-9]+}}(%e{{[sb]}}p), %bl # 1-byte Folded Reload
; X86-NEXT: movl $2147483647, %esi # imm = 0x7FFFFFFF
; X86-NEXT: cmovnel %esi, %edx
; X86-NEXT: movl $-1, %esi
; X86-NEXT: cmovnel %esi, %eax
; X86-NEXT: cmpl $-1, %ecx
; X86-NEXT: setl %cl
; X86-NEXT: sete %ch
; X86-NEXT: andb {{[-0-9]+}}(%e{{[sb]}}p), %ch # 1-byte Folded Reload
; X86-NEXT: xorl %esi, %esi
; X86-NEXT: orb %cl, %ch
; X86-NEXT: cmovnel %esi, %eax
; X86-NEXT: movl $-2147483648, %ecx # imm = 0x80000000
; X86-NEXT: cmovnel %ecx, %edx
; X86-NEXT: addl $4, %esp
; X86-NEXT: popl %esi
; X86-NEXT: popl %edi
; X86-NEXT: popl %ebx
; X86-NEXT: popl %ebp
; X86-NEXT: retl
%tmp = call i64 @llvm.smul.fix.sat.i64(i64 %x, i64 %y, i32 32)
ret i64 %tmp
}
define i64 @func8(i64 %x, i64 %y) nounwind {
; X64-LABEL: func8:
; X64: # %bb.0:
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: imulq %rsi
; X64-NEXT: shrdq $63, %rdx, %rax
; X64-NEXT: movabsq $4611686018427387903, %rcx # imm = 0x3FFFFFFFFFFFFFFF
; X64-NEXT: cmpq %rcx, %rdx
; X64-NEXT: movabsq $9223372036854775807, %rcx # imm = 0x7FFFFFFFFFFFFFFF
; X64-NEXT: cmovgq %rcx, %rax
; X64-NEXT: movabsq $-4611686018427387904, %rcx # imm = 0xC000000000000000
; X64-NEXT: cmpq %rcx, %rdx
; X64-NEXT: movabsq $-9223372036854775808, %rcx # imm = 0x8000000000000000
; X64-NEXT: cmovlq %rcx, %rax
; X64-NEXT: retq
;
; X86-LABEL: func8:
; X86: # %bb.0:
; X86-NEXT: pushl %ebp
; X86-NEXT: pushl %ebx
; X86-NEXT: pushl %edi
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: movl %edx, %edi
; X86-NEXT: movl %eax, %ebp
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: addl %edx, %ebp
; X86-NEXT: adcl $0, %edi
; X86-NEXT: movl %esi, %eax
; X86-NEXT: imull {{[0-9]+}}(%esp)
; X86-NEXT: movl %edx, %ebx
; X86-NEXT: movl %eax, %ecx
; X86-NEXT: movl %esi, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: addl %ebp, %eax
; X86-NEXT: adcl %edx, %edi
; X86-NEXT: adcl $0, %ebx
; X86-NEXT: addl %ecx, %edi
; X86-NEXT: adcl $0, %ebx
; X86-NEXT: movl %edi, %edx
; X86-NEXT: subl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl %ebx, %ebp
; X86-NEXT: sbbl $0, %ebp
; X86-NEXT: testl %esi, %esi
; X86-NEXT: cmovnsl %ebx, %ebp
; X86-NEXT: cmovnsl %edi, %edx
; X86-NEXT: movl %edx, %esi
; X86-NEXT: subl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl %ebp, %ecx
; X86-NEXT: sbbl $0, %ecx
; X86-NEXT: cmpl $0, {{[0-9]+}}(%esp)
; X86-NEXT: cmovnsl %ebp, %ecx
; X86-NEXT: cmovnsl %edx, %esi
; X86-NEXT: shrdl $31, %esi, %eax
; X86-NEXT: shrdl $31, %ecx, %esi
; X86-NEXT: cmpl $1073741824, %ecx # imm = 0x40000000
; X86-NEXT: movl $2147483647, %edi # imm = 0x7FFFFFFF
; X86-NEXT: cmovll %esi, %edi
; X86-NEXT: movl $-1, %edx
; X86-NEXT: cmovgel %edx, %eax
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: cmpl $-1073741824, %ecx # imm = 0xC0000000
; X86-NEXT: cmovll %edx, %eax
; X86-NEXT: movl $-2147483648, %edx # imm = 0x80000000
; X86-NEXT: cmovgel %edi, %edx
; X86-NEXT: popl %esi
; X86-NEXT: popl %edi
; X86-NEXT: popl %ebx
; X86-NEXT: popl %ebp
; X86-NEXT: retl
%tmp = call i64 @llvm.smul.fix.sat.i64(i64 %x, i64 %y, i32 63)
ret i64 %tmp
}
Codebase Browser
llvm