llvm/test/CodeGen/X86/fp-trunc.ll
Michael Kuperstein 5440f2198d [X86] ABI change for x86-32: pass 3 vector arguments in-register instead of 4, except on Darwin.
This changes the ABI used on 32-bit x86 for passing vector arguments. 
Historically, clang passes the first 4 vector arguments in-register, and additional vector arguments on the stack, regardless of platform. That is different from the behavior of gcc, icc, and msvc, all of which pass only the first 3 arguments in-register.
The 3-register convention is documented, unofficially, in Agner's calling convention guide, and, officially, in the recently released version 1.0 of the i386 psABI.

Darwin is kept as is because the OS X ABI Function Call Guide explicitly documents the current (4-register) behavior.

This fixes PR21510

Differential revision: http://reviews.llvm.org/D9644

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@237682 91177308-0d34-0410-b5e6-96231b3b80d8
2015-05-19 11:06:56 +00:00

85 lines
2.3 KiB
LLVM

; RUN: llc < %s -march=x86 -mcpu=corei7 | FileCheck %s
; RUN: llc < %s -march=x86 -mcpu=core-avx-i | FileCheck %s --check-prefix=AVX
target triple = "i686-pc-linux-gnu"
define <1 x float> @test1(<1 x double> %x) nounwind {
; CHECK-LABEL: test1:
; CHECK: # BB#0:
; CHECK-NEXT: pushl %eax
; CHECK-NEXT: movsd {{[0-9]+}}(%esp), %xmm0
; CHECK-NEXT: cvtsd2ss %xmm0, %xmm0
; CHECK-NEXT: movss %xmm0, (%esp)
; CHECK-NEXT: flds (%esp)
; CHECK-NEXT: popl %eax
; CHECK-NEXT: retl
;
; AVX-LABEL: test1:
; AVX: # BB#0:
; AVX-NEXT: pushl %eax
; AVX-NEXT: vmovsd {{[0-9]+}}(%esp), %xmm0
; AVX-NEXT: vcvtsd2ss %xmm0, %xmm0, %xmm0
; AVX-NEXT: vmovss %xmm0, (%esp)
; AVX-NEXT: flds (%esp)
; AVX-NEXT: popl %eax
; AVX-NEXT: retl
%y = fptrunc <1 x double> %x to <1 x float>
ret <1 x float> %y
}
define <2 x float> @test2(<2 x double> %x) nounwind {
; CHECK-LABEL: test2:
; CHECK: # BB#0:
; CHECK-NEXT: cvtpd2ps %xmm0, %xmm0
; CHECK-NEXT: retl
;
; AVX-LABEL: test2:
; AVX: # BB#0:
; AVX-NEXT: vcvtpd2ps %xmm0, %xmm0
; AVX-NEXT: retl
%y = fptrunc <2 x double> %x to <2 x float>
ret <2 x float> %y
}
define <4 x float> @test3(<4 x double> %x) nounwind {
; CHECK-LABEL: test3:
; CHECK: # BB#0:
; CHECK-NEXT: cvtpd2ps %xmm1, %xmm1
; CHECK-NEXT: cvtpd2ps %xmm0, %xmm0
; CHECK-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; CHECK-NEXT: retl
;
; AVX-LABEL: test3:
; AVX: # BB#0:
; AVX-NEXT: vcvtpd2psy %ymm0, %xmm0
; AVX-NEXT: vzeroupper
; AVX-NEXT: retl
%y = fptrunc <4 x double> %x to <4 x float>
ret <4 x float> %y
}
define <8 x float> @test4(<8 x double> %x) nounwind {
; CHECK-LABEL: test4:
; CHECK: # BB#0:
; CHECK-NEXT: subl $12, %esp
; CHECK-NEXT: cvtpd2ps %xmm1, %xmm1
; CHECK-NEXT: cvtpd2ps %xmm0, %xmm0
; CHECK-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; CHECK-NEXT: cvtpd2ps %xmm2, %xmm1
; CHECK-NEXT: cvtpd2ps 16(%esp), %xmm2
; CHECK-NEXT: unpcklpd {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; CHECK-NEXT: addl $12, %esp
; CHECK-NEXT: retl
;
; AVX-LABEL: test4:
; AVX: # BB#0:
; AVX-NEXT: vcvtpd2psy %ymm0, %xmm0
; AVX-NEXT: vcvtpd2psy %ymm1, %xmm1
; AVX-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX-NEXT: retl
%y = fptrunc <8 x double> %x to <8 x float>
ret <8 x float> %y
}