mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 11:13:28 +01:00
21418c85a1
If the mask input to getV4X86ShuffleImm8 only refers to a single source element (+ undefs) then canonicalize to a full broadcast. getV4X86ShuffleImm8 defaults to inline values for undefs, which can be useful for shuffle widening/narrowing but does leave SimplifyDemanded* calls thinking the shuffle depends on unnecessary elements. I'm still investigating what we should do more generally to avoid these undemanded elements, but broadcast cases was a simpler win.
543 lines
16 KiB
LLVM
543 lines
16 KiB
LLVM
; 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.umul.fix.sat.i4 (i4, i4, i32)
|
|
declare i32 @llvm.umul.fix.sat.i32 (i32, i32, i32)
|
|
declare i64 @llvm.umul.fix.sat.i64 (i64, i64, i32)
|
|
declare <4 x i32> @llvm.umul.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: movl %esi, %eax
|
|
; X64-NEXT: movl %edi, %ecx
|
|
; X64-NEXT: imulq %rax, %rcx
|
|
; X64-NEXT: movq %rcx, %rax
|
|
; X64-NEXT: shrq $32, %rax
|
|
; X64-NEXT: shrdl $2, %eax, %ecx
|
|
; X64-NEXT: cmpl $3, %eax
|
|
; X64-NEXT: movl $-1, %eax
|
|
; X64-NEXT: cmovbel %ecx, %eax
|
|
; X64-NEXT: retq
|
|
;
|
|
; X86-LABEL: func:
|
|
; X86: # %bb.0:
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: shrdl $2, %edx, %eax
|
|
; X86-NEXT: cmpl $3, %edx
|
|
; X86-NEXT: movl $-1, %ecx
|
|
; X86-NEXT: cmoval %ecx, %eax
|
|
; X86-NEXT: retl
|
|
%tmp = call i32 @llvm.umul.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: mulq %rsi
|
|
; X64-NEXT: shrdq $2, %rdx, %rax
|
|
; X64-NEXT: cmpq $3, %rdx
|
|
; X64-NEXT: movq $-1, %rcx
|
|
; X64-NEXT: cmovaq %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: movl {{[0-9]+}}(%esp), %ecx
|
|
; 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, %ebx
|
|
; X86-NEXT: movl %ecx, %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: movl %eax, %ecx
|
|
; X86-NEXT: movl %edx, %ebp
|
|
; X86-NEXT: addl %ebx, %ebp
|
|
; X86-NEXT: adcl $0, %edi
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: mull %esi
|
|
; X86-NEXT: movl %edx, %ebx
|
|
; X86-NEXT: movl %eax, %esi
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %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 %esi, %edx
|
|
; X86-NEXT: adcl $0, %ebx
|
|
; X86-NEXT: shrdl $2, %eax, %ecx
|
|
; X86-NEXT: shrdl $2, %edx, %eax
|
|
; X86-NEXT: shrl $2, %edx
|
|
; X86-NEXT: orl %ebx, %edx
|
|
; X86-NEXT: movl $-1, %edx
|
|
; X86-NEXT: cmovnel %edx, %ecx
|
|
; X86-NEXT: cmovel %eax, %edx
|
|
; X86-NEXT: movl %ecx, %eax
|
|
; X86-NEXT: popl %esi
|
|
; X86-NEXT: popl %edi
|
|
; X86-NEXT: popl %ebx
|
|
; X86-NEXT: popl %ebp
|
|
; X86-NEXT: retl
|
|
%tmp = call i64 @llvm.umul.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: andl $15, %esi
|
|
; X64-NEXT: shlb $4, %dil
|
|
; X64-NEXT: movzbl %dil, %eax
|
|
; X64-NEXT: imull %esi, %eax
|
|
; X64-NEXT: movl %eax, %ecx
|
|
; X64-NEXT: shrb $2, %cl
|
|
; X64-NEXT: shrl $8, %eax
|
|
; X64-NEXT: movl %eax, %edx
|
|
; X64-NEXT: shlb $6, %dl
|
|
; X64-NEXT: orb %cl, %dl
|
|
; X64-NEXT: movzbl %dl, %ecx
|
|
; X64-NEXT: cmpb $3, %al
|
|
; X64-NEXT: movl $255, %eax
|
|
; X64-NEXT: cmovbel %ecx, %eax
|
|
; X64-NEXT: shrb $4, %al
|
|
; X64-NEXT: # kill: def $al killed $al killed $eax
|
|
; X64-NEXT: retq
|
|
;
|
|
; X86-LABEL: func3:
|
|
; X86: # %bb.0:
|
|
; X86-NEXT: movb {{[0-9]+}}(%esp), %al
|
|
; X86-NEXT: andb $15, %al
|
|
; X86-NEXT: movb {{[0-9]+}}(%esp), %cl
|
|
; X86-NEXT: movzbl %al, %edx
|
|
; X86-NEXT: shlb $4, %cl
|
|
; X86-NEXT: movzbl %cl, %eax
|
|
; X86-NEXT: imull %edx, %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 $3, %ah
|
|
; X86-NEXT: movl $255, %eax
|
|
; X86-NEXT: cmovbel %ecx, %eax
|
|
; X86-NEXT: shrb $4, %al
|
|
; X86-NEXT: # kill: def $al killed $al killed $eax
|
|
; X86-NEXT: retl
|
|
%tmp = call i4 @llvm.umul.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: pshufd {{.*#+}} xmm2 = xmm0[3,3,3,3]
|
|
; X64-NEXT: movd %xmm2, %ecx
|
|
; X64-NEXT: imulq %rax, %rcx
|
|
; X64-NEXT: movq %rcx, %rax
|
|
; X64-NEXT: shrq $32, %rax
|
|
; X64-NEXT: shrdl $2, %eax, %ecx
|
|
; X64-NEXT: cmpl $3, %eax
|
|
; X64-NEXT: movl $-1, %eax
|
|
; X64-NEXT: cmoval %eax, %ecx
|
|
; X64-NEXT: movd %ecx, %xmm2
|
|
; X64-NEXT: pshufd {{.*#+}} xmm3 = xmm1[2,3,2,3]
|
|
; X64-NEXT: movd %xmm3, %ecx
|
|
; X64-NEXT: pshufd {{.*#+}} xmm3 = xmm0[2,3,2,3]
|
|
; X64-NEXT: movd %xmm3, %edx
|
|
; X64-NEXT: imulq %rcx, %rdx
|
|
; X64-NEXT: movq %rdx, %rcx
|
|
; X64-NEXT: shrq $32, %rcx
|
|
; X64-NEXT: shrdl $2, %ecx, %edx
|
|
; X64-NEXT: cmpl $3, %ecx
|
|
; X64-NEXT: cmoval %eax, %edx
|
|
; X64-NEXT: movd %edx, %xmm3
|
|
; X64-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
|
|
; X64-NEXT: movd %xmm1, %ecx
|
|
; X64-NEXT: movd %xmm0, %edx
|
|
; X64-NEXT: imulq %rcx, %rdx
|
|
; X64-NEXT: movq %rdx, %rcx
|
|
; X64-NEXT: shrq $32, %rcx
|
|
; X64-NEXT: shrdl $2, %ecx, %edx
|
|
; X64-NEXT: cmpl $3, %ecx
|
|
; X64-NEXT: cmoval %eax, %edx
|
|
; X64-NEXT: movd %edx, %xmm2
|
|
; X64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,1,1]
|
|
; X64-NEXT: movd %xmm1, %ecx
|
|
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,1,1]
|
|
; X64-NEXT: movd %xmm0, %edx
|
|
; X64-NEXT: imulq %rcx, %rdx
|
|
; X64-NEXT: movq %rdx, %rcx
|
|
; X64-NEXT: shrq $32, %rcx
|
|
; X64-NEXT: shrdl $2, %ecx, %edx
|
|
; X64-NEXT: cmpl $3, %ecx
|
|
; X64-NEXT: cmoval %eax, %edx
|
|
; X64-NEXT: movd %edx, %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), %edi
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: movl %eax, %esi
|
|
; X86-NEXT: shrdl $2, %edx, %esi
|
|
; X86-NEXT: cmpl $3, %edx
|
|
; X86-NEXT: movl $-1, %ecx
|
|
; X86-NEXT: cmoval %ecx, %esi
|
|
; X86-NEXT: movl %ebp, %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: movl %eax, %ebp
|
|
; X86-NEXT: shrdl $2, %edx, %ebp
|
|
; X86-NEXT: cmpl $3, %edx
|
|
; X86-NEXT: cmoval %ecx, %ebp
|
|
; X86-NEXT: movl %ebx, %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: movl %eax, %ebx
|
|
; X86-NEXT: shrdl $2, %edx, %ebx
|
|
; X86-NEXT: cmpl $3, %edx
|
|
; X86-NEXT: cmoval %ecx, %ebx
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: shrdl $2, %edx, %eax
|
|
; X86-NEXT: cmpl $3, %edx
|
|
; X86-NEXT: cmoval %ecx, %eax
|
|
; X86-NEXT: movl %eax, 12(%edi)
|
|
; X86-NEXT: movl %ebx, 8(%edi)
|
|
; X86-NEXT: movl %ebp, 4(%edi)
|
|
; X86-NEXT: movl %esi, (%edi)
|
|
; X86-NEXT: movl %edi, %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.umul.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: movl %edi, %eax
|
|
; X64-NEXT: mull %esi
|
|
; X64-NEXT: movl $-1, %ecx
|
|
; X64-NEXT: cmovol %ecx, %eax
|
|
; X64-NEXT: retq
|
|
;
|
|
; X86-LABEL: func4:
|
|
; X86: # %bb.0:
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: movl $-1, %ecx
|
|
; X86-NEXT: cmovol %ecx, %eax
|
|
; X86-NEXT: retl
|
|
%tmp = call i32 @llvm.umul.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: movq %rdi, %rax
|
|
; X64-NEXT: mulq %rsi
|
|
; X64-NEXT: movq $-1, %rcx
|
|
; X64-NEXT: cmovoq %rcx, %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: .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), %ebp
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
|
|
; X86-NEXT: testl %esi, %esi
|
|
; X86-NEXT: setne %dl
|
|
; X86-NEXT: testl %eax, %eax
|
|
; X86-NEXT: setne %cl
|
|
; X86-NEXT: andb %dl, %cl
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: movl %eax, %edi
|
|
; X86-NEXT: seto %bl
|
|
; X86-NEXT: movl %esi, %eax
|
|
; X86-NEXT: mull %ebp
|
|
; X86-NEXT: movl %eax, %esi
|
|
; X86-NEXT: seto %ch
|
|
; X86-NEXT: orb %bl, %ch
|
|
; X86-NEXT: addl %edi, %esi
|
|
; X86-NEXT: movl %ebp, %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: addl %esi, %edx
|
|
; X86-NEXT: setb %bl
|
|
; X86-NEXT: orb %ch, %bl
|
|
; X86-NEXT: orb %cl, %bl
|
|
; X86-NEXT: movl $-1, %ecx
|
|
; X86-NEXT: cmovnel %ecx, %eax
|
|
; X86-NEXT: cmovnel %ecx, %edx
|
|
; 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.umul.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: andb $15, %sil
|
|
; X64-NEXT: shlb $4, %al
|
|
; X64-NEXT: # kill: def $al killed $al killed $eax
|
|
; X64-NEXT: mulb %sil
|
|
; X64-NEXT: movzbl %al, %ecx
|
|
; X64-NEXT: movl $255, %eax
|
|
; X64-NEXT: cmovnol %ecx, %eax
|
|
; X64-NEXT: shrb $4, %al
|
|
; X64-NEXT: # kill: def $al killed $al killed $eax
|
|
; X64-NEXT: retq
|
|
;
|
|
; X86-LABEL: func6:
|
|
; X86: # %bb.0:
|
|
; X86-NEXT: movb {{[0-9]+}}(%esp), %cl
|
|
; X86-NEXT: andb $15, %cl
|
|
; X86-NEXT: movb {{[0-9]+}}(%esp), %al
|
|
; X86-NEXT: shlb $4, %al
|
|
; X86-NEXT: mulb %cl
|
|
; X86-NEXT: movzbl %al, %ecx
|
|
; X86-NEXT: movl $255, %eax
|
|
; X86-NEXT: cmovnol %ecx, %eax
|
|
; X86-NEXT: shrb $4, %al
|
|
; X86-NEXT: # kill: def $al killed $al killed $eax
|
|
; X86-NEXT: retl
|
|
%tmp = call i4 @llvm.umul.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 = xmm0[3,3,3,3]
|
|
; X64-NEXT: movd %xmm2, %eax
|
|
; X64-NEXT: pshufd {{.*#+}} xmm2 = xmm1[3,3,3,3]
|
|
; X64-NEXT: movd %xmm2, %ecx
|
|
; X64-NEXT: mull %ecx
|
|
; X64-NEXT: movl $-1, %ecx
|
|
; X64-NEXT: cmovol %ecx, %eax
|
|
; X64-NEXT: movd %eax, %xmm2
|
|
; X64-NEXT: pshufd {{.*#+}} xmm3 = xmm0[2,3,2,3]
|
|
; X64-NEXT: movd %xmm3, %eax
|
|
; X64-NEXT: pshufd {{.*#+}} xmm3 = xmm1[2,3,2,3]
|
|
; X64-NEXT: movd %xmm3, %edx
|
|
; X64-NEXT: mull %edx
|
|
; X64-NEXT: cmovol %ecx, %eax
|
|
; X64-NEXT: movd %eax, %xmm3
|
|
; X64-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
|
|
; X64-NEXT: movd %xmm0, %eax
|
|
; X64-NEXT: movd %xmm1, %edx
|
|
; X64-NEXT: mull %edx
|
|
; X64-NEXT: cmovol %ecx, %eax
|
|
; X64-NEXT: movd %eax, %xmm2
|
|
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,1,1]
|
|
; X64-NEXT: movd %xmm0, %eax
|
|
; X64-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,1,1]
|
|
; X64-NEXT: movd %xmm0, %edx
|
|
; X64-NEXT: mull %edx
|
|
; X64-NEXT: cmovol %ecx, %eax
|
|
; X64-NEXT: movd %eax, %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), %ecx
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: movl %eax, %ebp
|
|
; X86-NEXT: movl $-1, %esi
|
|
; X86-NEXT: cmovol %esi, %ebp
|
|
; X86-NEXT: movl %ebx, %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: movl %eax, %ebx
|
|
; X86-NEXT: cmovol %esi, %ebx
|
|
; X86-NEXT: movl %edi, %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: movl %eax, %edi
|
|
; X86-NEXT: cmovol %esi, %edi
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: cmovol %esi, %eax
|
|
; X86-NEXT: movl %eax, 12(%ecx)
|
|
; X86-NEXT: movl %edi, 8(%ecx)
|
|
; X86-NEXT: movl %ebx, 4(%ecx)
|
|
; X86-NEXT: movl %ebp, (%ecx)
|
|
; 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.umul.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: mulq %rsi
|
|
; X64-NEXT: shrdq $32, %rdx, %rax
|
|
; X64-NEXT: movl $4294967295, %ecx # imm = 0xFFFFFFFF
|
|
; X64-NEXT: cmpq %rcx, %rdx
|
|
; X64-NEXT: movq $-1, %rcx
|
|
; X64-NEXT: cmovaq %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: movl {{[0-9]+}}(%esp), %ecx
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
|
|
; X86-NEXT: movl %ecx, %eax
|
|
; X86-NEXT: mull %ebp
|
|
; X86-NEXT: movl %edx, %edi
|
|
; X86-NEXT: movl %eax, %ebx
|
|
; X86-NEXT: movl %ecx, %eax
|
|
; X86-NEXT: mull %esi
|
|
; X86-NEXT: movl %edx, %ecx
|
|
; X86-NEXT: addl %ebx, %ecx
|
|
; X86-NEXT: adcl $0, %edi
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: mull %ebp
|
|
; X86-NEXT: movl %edx, %ebx
|
|
; X86-NEXT: movl %eax, %ebp
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: mull %esi
|
|
; X86-NEXT: addl %ecx, %eax
|
|
; X86-NEXT: adcl %edi, %edx
|
|
; X86-NEXT: adcl $0, %ebx
|
|
; X86-NEXT: addl %ebp, %edx
|
|
; X86-NEXT: adcl $0, %ebx
|
|
; X86-NEXT: xorl %ecx, %ecx
|
|
; X86-NEXT: cmpl $1, %ebx
|
|
; X86-NEXT: sbbl %ecx, %ecx
|
|
; X86-NEXT: notl %ecx
|
|
; X86-NEXT: orl %ecx, %eax
|
|
; X86-NEXT: orl %ecx, %edx
|
|
; X86-NEXT: popl %esi
|
|
; X86-NEXT: popl %edi
|
|
; X86-NEXT: popl %ebx
|
|
; X86-NEXT: popl %ebp
|
|
; X86-NEXT: retl
|
|
%tmp = call i64 @llvm.umul.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: mulq %rsi
|
|
; X64-NEXT: shrdq $63, %rdx, %rax
|
|
; X64-NEXT: movabsq $9223372036854775807, %rcx # imm = 0x7FFFFFFFFFFFFFFF
|
|
; X64-NEXT: cmpq %rcx, %rdx
|
|
; X64-NEXT: movq $-1, %rcx
|
|
; X64-NEXT: cmovaq %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 %esi
|
|
; X86-NEXT: movl %edx, %edi
|
|
; X86-NEXT: movl %eax, %ebx
|
|
; X86-NEXT: movl %ecx, %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: movl %edx, %ebp
|
|
; X86-NEXT: addl %ebx, %ebp
|
|
; X86-NEXT: adcl $0, %edi
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: mull %esi
|
|
; X86-NEXT: movl %edx, %ecx
|
|
; X86-NEXT: movl %eax, %ebx
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X86-NEXT: mull {{[0-9]+}}(%esp)
|
|
; X86-NEXT: addl %ebp, %eax
|
|
; X86-NEXT: adcl %edi, %edx
|
|
; X86-NEXT: adcl $0, %ecx
|
|
; X86-NEXT: addl %ebx, %edx
|
|
; X86-NEXT: adcl $0, %ecx
|
|
; X86-NEXT: shrdl $31, %edx, %eax
|
|
; X86-NEXT: movl %edx, %esi
|
|
; X86-NEXT: shrl $31, %esi
|
|
; X86-NEXT: xorl %edi, %edi
|
|
; X86-NEXT: cmpl $1, %esi
|
|
; X86-NEXT: sbbl %edi, %edi
|
|
; X86-NEXT: notl %edi
|
|
; X86-NEXT: orl %edi, %eax
|
|
; X86-NEXT: shldl $1, %edx, %ecx
|
|
; X86-NEXT: orl %edi, %ecx
|
|
; X86-NEXT: movl %ecx, %edx
|
|
; X86-NEXT: popl %esi
|
|
; X86-NEXT: popl %edi
|
|
; X86-NEXT: popl %ebx
|
|
; X86-NEXT: popl %ebp
|
|
; X86-NEXT: retl
|
|
%tmp = call i64 @llvm.umul.fix.sat.i64(i64 %x, i64 %y, i32 63)
|
|
ret i64 %tmp
|
|
}
|