; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i386-apple-darwin -mattr=+sse2 | FileCheck %s --check-prefix=X86
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+sse2 | FileCheck %s --check-prefix=X64
define i32 @t(ptr %ref_frame_ptr, i32 %ref_frame_stride, i32 %idxX, i32 %idxY) nounwind {
; X86-LABEL: t:
; X86: ## %bb.0: ## %entry
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: imull {{[0-9]+}}(%esp), %ecx
; X86-NEXT: addl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl (%eax,%ecx), %eax
; X86-NEXT: retl
;
; X64-LABEL: t:
; X64: ## %bb.0: ## %entry
; X64-NEXT: imull %ecx, %esi
; X64-NEXT: addl %edx, %esi
; X64-NEXT: movslq %esi, %rax
; X64-NEXT: movl (%rdi,%rax), %eax
; X64-NEXT: retq
entry:
%tmp7 = mul i32 %idxY, %ref_frame_stride ; <i32> [#uses=2]
%tmp9 = add i32 %tmp7, %idxX ; <i32> [#uses=1]
%tmp11 = getelementptr i8, ptr %ref_frame_ptr, i32 %tmp9 ; <ptr> [#uses=1]
%tmp13 = load i32, ptr %tmp11, align 4 ; <i32> [#uses=1]
%tmp18 = add i32 %idxX, 4 ; <i32> [#uses=1]
%tmp20.sum = add i32 %tmp18, %tmp7 ; <i32> [#uses=1]
%tmp21 = getelementptr i8, ptr %ref_frame_ptr, i32 %tmp20.sum ; <ptr> [#uses=1]
%tmp23 = load i16, ptr %tmp21, align 2 ; <i16> [#uses=1]
%tmp2425 = zext i16 %tmp23 to i64 ; <i64> [#uses=1]
%tmp26 = shl i64 %tmp2425, 32 ; <i64> [#uses=1]
%tmp2728 = zext i32 %tmp13 to i64 ; <i64> [#uses=1]
%tmp29 = or i64 %tmp26, %tmp2728 ; <i64> [#uses=1]
%tmp3454 = bitcast i64 %tmp29 to double ; <double> [#uses=1]
%tmp35 = insertelement <2 x double> undef, double %tmp3454, i32 0 ; <<2 x double>> [#uses=1]
%tmp36 = insertelement <2 x double> %tmp35, double 0.000000e+00, i32 1 ; <<2 x double>> [#uses=1]
%tmp42 = bitcast <2 x double> %tmp36 to <8 x i16> ; <<8 x i16>> [#uses=1]
%tmp43 = shufflevector <8 x i16> %tmp42, <8 x i16> undef, <8 x i32> < i32 0, i32 1, i32 1, i32 2, i32 4, i32 5, i32 6, i32 7 > ; <<8 x i16>> [#uses=1]
%tmp47 = bitcast <8 x i16> %tmp43 to <4 x i32> ; <<4 x i32>> [#uses=1]
%tmp48 = extractelement <4 x i32> %tmp47, i32 0 ; <i32> [#uses=1]
ret i32 %tmp48
}
; Test CSE for SDAG nodes with multiple results (UMUL_LOHI).
define i96 @square_high(i96 %x) nounwind {
; X86-LABEL: square_high:
; X86: ## %bb.0: ## %entry
; 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), %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X86-NEXT: movl %edi, %eax
; X86-NEXT: mull %edi
; X86-NEXT: movl %edx, %ecx
; X86-NEXT: movl %ebx, %eax
; X86-NEXT: mull %edi
; X86-NEXT: addl %eax, %ecx
; X86-NEXT: movl %edx, %ebp
; X86-NEXT: adcl $0, %ebp
; X86-NEXT: addl %eax, %ecx
; X86-NEXT: adcl %edx, %ebp
; X86-NEXT: setb %al
; X86-NEXT: movzbl %al, %ecx
; X86-NEXT: movl %ebx, %eax
; X86-NEXT: mull %ebx
; X86-NEXT: movl %eax, %ebx
; X86-NEXT: addl %ebp, %ebx
; X86-NEXT: adcl %edx, %ecx
; X86-NEXT: movl %esi, %eax
; X86-NEXT: mull %edi
; X86-NEXT: movl %edx, (%esp) ## 4-byte Spill
; X86-NEXT: movl %eax, %ebp
; X86-NEXT: movl %esi, %eax
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: movl %edx, %esi
; X86-NEXT: movl %eax, %edi
; X86-NEXT: addl (%esp), %edi ## 4-byte Folded Reload
; X86-NEXT: adcl $0, %esi
; X86-NEXT: addl %ebp, %ebx
; X86-NEXT: adcl %edi, %ecx
; X86-NEXT: movl %esi, %eax
; X86-NEXT: adcl $0, %eax
; X86-NEXT: setb %dl
; X86-NEXT: addl %ebp, %ebx
; X86-NEXT: adcl %ecx, %edi
; X86-NEXT: movzbl %dl, %ecx
; X86-NEXT: adcl %eax, %esi
; X86-NEXT: adcl $0, %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: mull %eax
; X86-NEXT: addl %eax, %esi
; X86-NEXT: adcl %edx, %ecx
; X86-NEXT: movl %edi, %eax
; X86-NEXT: movl %esi, %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
;
; X64-LABEL: square_high:
; X64: ## %bb.0: ## %entry
; X64-NEXT: movl %esi, %ecx
; X64-NEXT: movq %rcx, %rax
; X64-NEXT: mulq %rdi
; X64-NEXT: movq %rdx, %rsi
; X64-NEXT: movq %rax, %r8
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: mulq %rdi
; X64-NEXT: addq %r8, %rdx
; X64-NEXT: movq %rsi, %rax
; X64-NEXT: adcq $0, %rax
; X64-NEXT: addq %rdx, %r8
; X64-NEXT: adcq %rsi, %rax
; X64-NEXT: imulq %rcx, %rcx
; X64-NEXT: addq %rax, %rcx
; X64-NEXT: shrdq $32, %rcx, %r8
; X64-NEXT: shrq $32, %rcx
; X64-NEXT: movq %r8, %rax
; X64-NEXT: movq %rcx, %rdx
; X64-NEXT: retq
entry:
%conv = zext i96 %x to i192
%mul = mul nuw i192 %conv, %conv
%shr = lshr i192 %mul, 96
%conv2 = trunc i192 %shr to i96
ret i96 %conv2
}
Codebase Browser
llvm