1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
llvm-mirror/test/CodeGen/X86/mul128.ll
Nikita Popov 97d9074f99 [SDAG] Fold umul_lohi with 0 or 1 multiplicand
These can turn up during multiplication legalization. In principle
these should also apply to smul_lohi, but I wasn't able to figure
out how to produce those with the necessary operands.

Differential Revision: https://reviews.llvm.org/D66380

llvm-svn: 369864
2019-08-25 08:04:22 +00:00

137 lines
4.2 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s --check-prefix=X64
; RUN: llc < %s -mtriple=i386-unknown | FileCheck %s --check-prefix=X86
define i128 @foo(i128 %t, i128 %u) {
; X64-LABEL: foo:
; X64: # %bb.0:
; X64-NEXT: movq %rdx, %r8
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: imulq %rdi, %rcx
; X64-NEXT: mulq %rdx
; X64-NEXT: addq %rcx, %rdx
; X64-NEXT: imulq %r8, %rsi
; X64-NEXT: addq %rsi, %rdx
; X64-NEXT: retq
;
; X86-LABEL: foo:
; 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 $8, %esp
; X86-NEXT: .cfi_def_cfa_offset 28
; 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), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: imull %edx, %esi
; X86-NEXT: movl %edi, %eax
; X86-NEXT: mull %edx
; X86-NEXT: movl %eax, %ebx
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: imull %edi, %ecx
; X86-NEXT: addl %edx, %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: addl %esi, %ecx
; X86-NEXT: movl %eax, %esi
; X86-NEXT: imull {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
; X86-NEXT: mull %ebp
; X86-NEXT: addl %esi, %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-NEXT: imull %ebp, %edi
; X86-NEXT: addl %edx, %edi
; X86-NEXT: addl %ebx, %eax
; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-NEXT: adcl %ecx, %edi
; X86-NEXT: movl %ebp, %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: mull %ecx
; X86-NEXT: movl %edx, %ebx
; X86-NEXT: movl %eax, (%esp) # 4-byte Spill
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: mull %ecx
; X86-NEXT: movl %edx, %esi
; X86-NEXT: movl %eax, %ecx
; X86-NEXT: addl %ebx, %ecx
; X86-NEXT: adcl $0, %esi
; X86-NEXT: movl %ebp, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: movl %edx, %ebx
; X86-NEXT: movl %eax, %ebp
; X86-NEXT: addl %ecx, %ebp
; X86-NEXT: adcl %esi, %ebx
; X86-NEXT: setb %cl
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: addl %ebx, %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 %edi, %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl (%esp), %esi # 4-byte Reload
; X86-NEXT: movl %esi, (%ecx)
; X86-NEXT: movl %ebp, 4(%ecx)
; X86-NEXT: movl %eax, 8(%ecx)
; X86-NEXT: movl %edx, 12(%ecx)
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: addl $8, %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 $4
%k = mul i128 %t, %u
ret i128 %k
}
@aaa = external global i128
@bbb = external global i128
define void @PR13897() nounwind {
; X64-LABEL: PR13897:
; X64: # %bb.0: # %"0x0"
; X64-NEXT: movl {{.*}}(%rip), %ecx
; X64-NEXT: movabsq $4294967297, %rdx # imm = 0x100000001
; X64-NEXT: movq %rcx, %rax
; X64-NEXT: mulq %rdx
; X64-NEXT: addq %rcx, %rdx
; X64-NEXT: shlq $32, %rcx
; X64-NEXT: addq %rcx, %rdx
; X64-NEXT: movq %rax, {{.*}}(%rip)
; X64-NEXT: movq %rdx, aaa+{{.*}}(%rip)
; X64-NEXT: retq
;
; X86-LABEL: PR13897:
; X86: # %bb.0: # %"0x0"
; X86-NEXT: movl bbb, %eax
; X86-NEXT: movl %eax, aaa+12
; X86-NEXT: movl %eax, aaa+8
; X86-NEXT: movl %eax, aaa+4
; X86-NEXT: movl %eax, aaa
; X86-NEXT: retl
"0x0":
%0 = load i128, i128* @bbb
%1 = and i128 %0, 4294967295
%2 = shl i128 %0, 96
%3 = mul i128 %1, 18446744078004518913
%4 = add i128 %3, %2
store i128 %4, i128* @aaa
ret void
}