llvm-project/llvm/test/CodeGen/X86/widen_cast-2.ll

71 lines
2.3 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse4.2 | FileCheck %s
; bitcast v14i16 to v7i32
define void @convert(<7 x i32>* %dst, <14 x i16>* %src) nounwind {
; CHECK-LABEL: convert:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: pushl %eax
; CHECK-NEXT: movl $0, (%esp)
; CHECK-NEXT: movdqa {{.*#+}} xmm0 = [1,1,1,1,1,1,1,1]
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = <1,1,1,1,1,1,u,u>
; CHECK-NEXT: cmpl $3, (%esp)
; CHECK-NEXT: jg .LBB0_3
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB0_2: # %forbody
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: movl (%esp), %eax
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %ecx
; CHECK-NEXT: shll $5, %eax
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %edx
; CHECK-NEXT: movdqa (%edx,%eax), %xmm2
; CHECK-NEXT: paddw %xmm0, %xmm2
; CHECK-NEXT: movdqa 16(%edx,%eax), %xmm3
; CHECK-NEXT: paddw %xmm1, %xmm3
; CHECK-NEXT: pextrd $2, %xmm3, 24(%ecx,%eax)
; CHECK-NEXT: pextrd $1, %xmm3, 20(%ecx,%eax)
; CHECK-NEXT: movd %xmm3, 16(%ecx,%eax)
; CHECK-NEXT: movdqa %xmm2, (%ecx,%eax)
; CHECK-NEXT: incl (%esp)
; CHECK-NEXT: cmpl $3, (%esp)
; CHECK-NEXT: jle .LBB0_2
; CHECK-NEXT: .LBB0_3: # %afterfor
; CHECK-NEXT: popl %eax
; CHECK-NEXT: retl
entry:
%dst.addr = alloca <7 x i32>*
%src.addr = alloca <14 x i16>*
%i = alloca i32, align 4
store <7 x i32>* %dst, <7 x i32>** %dst.addr
store <14 x i16>* %src, <14 x i16>** %src.addr
store i32 0, i32* %i
br label %forcond
forcond:
%tmp = load i32, i32* %i
%cmp = icmp slt i32 %tmp, 4
br i1 %cmp, label %forbody, label %afterfor
forbody:
%tmp1 = load i32, i32* %i
%tmp2 = load <7 x i32>*, <7 x i32>** %dst.addr
%arrayidx = getelementptr <7 x i32>, <7 x i32>* %tmp2, i32 %tmp1
%tmp3 = load i32, i32* %i
%tmp4 = load <14 x i16>*, <14 x i16>** %src.addr
%arrayidx5 = getelementptr <14 x i16>, <14 x i16>* %tmp4, i32 %tmp3
%tmp6 = load <14 x i16>, <14 x i16>* %arrayidx5
%add = add <14 x i16> %tmp6, < i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1 >
%conv = bitcast <14 x i16> %add to <7 x i32>
store <7 x i32> %conv, <7 x i32>* %arrayidx
br label %forinc
forinc:
%tmp7 = load i32, i32* %i
%inc = add i32 %tmp7, 1
store i32 %inc, i32* %i
br label %forcond
afterfor:
ret void
}