llvm/test/CodeGen/X86/bf16-fast-isel.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
; RUN: llc --fast-isel < %s -mtriple=x86_64-unknown-unknown | FileCheck %s

define i8 @test_direct_call(ptr %f) nounwind {
; CHECK-LABEL: test_direct_call:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    callq foo@PLT
; CHECK-NEXT:    pextrw $0, %xmm0, %eax
; CHECK-NEXT:    shll $16, %eax
; CHECK-NEXT:    movd %eax, %xmm0
; CHECK-NEXT:    callq __truncsfbf2@PLT
; CHECK-NEXT:    callq bar@PLT
; CHECK-NEXT:    popq %rcx
; CHECK-NEXT:    retq
entry:
  %call = call bfloat @foo(ptr %f)
  %call2 = call zeroext i8 @bar(bfloat %call)
  ret i8 %call2
}

define i8 @test_fast_direct_call(ptr %f) nounwind {
; CHECK-LABEL: test_fast_direct_call:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    callq foo_fast@PLT
; CHECK-NEXT:    pextrw $0, %xmm0, %eax
; CHECK-NEXT:    shll $16, %eax
; CHECK-NEXT:    movd %eax, %xmm0
; CHECK-NEXT:    callq __truncsfbf2@PLT
; CHECK-NEXT:    callq bar@PLT
; CHECK-NEXT:    popq %rcx
; CHECK-NEXT:    retq
entry:
  %call = call fastcc bfloat @foo_fast(ptr %f)
  %call2 = call zeroext i8 @bar(bfloat %call)
  ret i8 %call2
}

define i8 @test_indirect_all(ptr %fptr, ptr %f) nounwind {
; CHECK-LABEL: test_indirect_all:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rbx
; CHECK-NEXT:    movq %rdi, %rbx
; CHECK-NEXT:    movq %rsi, %rdi
; CHECK-NEXT:    callq foo@PLT
; CHECK-NEXT:    pextrw $0, %xmm0, %eax
; CHECK-NEXT:    shll $16, %eax
; CHECK-NEXT:    movd %eax, %xmm0
; CHECK-NEXT:    callq __truncsfbf2@PLT
; CHECK-NEXT:    callq *%rbx
; CHECK-NEXT:    popq %rbx
; CHECK-NEXT:    retq
entry:
  %call = call bfloat @foo(ptr %f)
  %call2 = call zeroext i8 %fptr(bfloat %call)
  ret i8 %call2
}

define i8 @test_indirect_all2(ptr %fptr, ptr %f, i1 %cond) nounwind {
; CHECK-LABEL: test_indirect_all2:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rbp
; CHECK-NEXT:    pushq %rbx
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    movl %edx, %ebp
; CHECK-NEXT:    movq %rdi, %rbx
; CHECK-NEXT:    movq %rsi, %rdi
; CHECK-NEXT:    callq foo@PLT
; CHECK-NEXT:    testb $1, %bpl
; CHECK-NEXT:    je .LBB3_2
; CHECK-NEXT:  # %bb.1: # %exit
; CHECK-NEXT:    pextrw $0, %xmm0, %eax
; CHECK-NEXT:    shll $16, %eax
; CHECK-NEXT:    movd %eax, %xmm0
; CHECK-NEXT:    callq __truncsfbf2@PLT
; CHECK-NEXT:    callq *%rbx
; CHECK-NEXT:    jmp .LBB3_3
; CHECK-NEXT:  .LBB3_2: # %exit2
; CHECK-NEXT:    movb $3, %al
; CHECK-NEXT:  .LBB3_3: # %exit2
; CHECK-NEXT:    addq $8, %rsp
; CHECK-NEXT:    popq %rbx
; CHECK-NEXT:    popq %rbp
; CHECK-NEXT:    retq
entry:
  %call = call bfloat @foo(ptr %f)
  br i1 %cond, label %exit, label %exit2

exit:
  %call2 = call zeroext i8 %fptr(bfloat %call)
  ret i8 %call2

exit2:
  ret i8 3
}


define i8 @test_fast_indirect_all(ptr %fptr, ptr %f) nounwind {
; CHECK-LABEL: test_fast_indirect_all:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rbx
; CHECK-NEXT:    movq %rdi, %rbx
; CHECK-NEXT:    movq %rsi, %rdi
; CHECK-NEXT:    callq foo@PLT
; CHECK-NEXT:    pextrw $0, %xmm0, %eax
; CHECK-NEXT:    shll $16, %eax
; CHECK-NEXT:    movd %eax, %xmm0
; CHECK-NEXT:    callq __truncsfbf2@PLT
; CHECK-NEXT:    callq *%rbx
; CHECK-NEXT:    popq %rbx
; CHECK-NEXT:    retq
entry:
  %call = call fastcc bfloat @foo(ptr %f)
  %call2 = call zeroext i8 %fptr(bfloat %call)
  ret i8 %call2
}

declare { bfloat, bfloat } @get_bfloats()
declare void @take_bfloats({ bfloat, bfloat })

define void @call_get_bfloats() nounwind {
; CHECK-LABEL: call_get_bfloats:
; CHECK:       # %bb.0:
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    callq get_bfloats@PLT
; CHECK-NEXT:    pextrw $0, %xmm1, %eax
; CHECK-NEXT:    shll $16, %eax
; CHECK-NEXT:    movl %eax, (%rsp) # 4-byte Spill
; CHECK-NEXT:    pextrw $0, %xmm0, %eax
; CHECK-NEXT:    shll $16, %eax
; CHECK-NEXT:    movd %eax, %xmm0
; CHECK-NEXT:    callq __truncsfbf2@PLT
; CHECK-NEXT:    movd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Folded Spill
; CHECK-NEXT:    movss (%rsp), %xmm0 # 4-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq __truncsfbf2@PLT
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq take_bfloats@PLT
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    retq
  %res = call { bfloat, bfloat } @get_bfloats()
  call void @take_bfloats({ bfloat, bfloat } %res)
  ret void
}

declare bfloat @foo(ptr %f)
declare zeroext i8 @bar(bfloat)
declare fastcc bfloat @foo_fast(ptr %f)