mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-08-30 05:29:47 +00:00
This is a Microsoft calling convention that supports both x86 and x86_64 subtargets. It passes vector and floating point arguments in XMM0-XMM5, and passes them indirectly once they are consumed. Homogenous vector aggregates of up to four elements can be passed in sequential vector registers, but this part is not implemented in LLVM and will be handled in Clang. On 32-bit x86, it is similar to fastcall in that it uses ecx:edx as integer register parameters and is callee cleanup. On x86_64, it delegates to the normal win64 calling convention. Reviewers: majnemer Differential Revision: http://reviews.llvm.org/D5943 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@220745 91177308-0d34-0410-b5e6-96231b3b80d8
94 lines
2.5 KiB
LLVM
94 lines
2.5 KiB
LLVM
; RUN: llc -mtriple=i686-pc-win32 -mattr=+sse2 < %s | FileCheck %s --check-prefix=CHECK --check-prefix=X86
|
|
; RUN: llc -mtriple=x86_64-pc-win32 < %s | FileCheck %s --check-prefix=CHECK --check-prefix=X64
|
|
|
|
; Test integer arguments.
|
|
|
|
define x86_vectorcallcc i32 @test_int_1() {
|
|
ret i32 0
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}test_int_1@@0:
|
|
; CHECK: xorl %eax, %eax
|
|
|
|
define x86_vectorcallcc i32 @test_int_2(i32 inreg %a) {
|
|
ret i32 %a
|
|
}
|
|
|
|
; X86-LABEL: {{^}}test_int_2@@4:
|
|
; X64-LABEL: {{^}}test_int_2@@8:
|
|
; CHECK: movl %ecx, %eax
|
|
|
|
define x86_vectorcallcc i32 @test_int_3(i64 inreg %a) {
|
|
%at = trunc i64 %a to i32
|
|
ret i32 %at
|
|
}
|
|
|
|
; X86-LABEL: {{^}}test_int_3@@8:
|
|
; X64-LABEL: {{^}}test_int_3@@8:
|
|
; CHECK: movl %ecx, %eax
|
|
|
|
define x86_vectorcallcc i32 @test_int_4(i32 inreg %a, i32 inreg %b) {
|
|
%s = add i32 %a, %b
|
|
ret i32 %s
|
|
}
|
|
|
|
; X86-LABEL: {{^}}test_int_4@@8:
|
|
; X86: leal (%ecx,%edx), %eax
|
|
|
|
; X64-LABEL: {{^}}test_int_4@@16:
|
|
; X64: leal (%rcx,%rdx), %eax
|
|
|
|
define x86_vectorcallcc i32 @"\01test_int_5"(i32, i32) {
|
|
ret i32 0
|
|
}
|
|
; CHECK-LABEL: {{^}}test_int_5:
|
|
|
|
define x86_vectorcallcc double @test_fp_1(double %a, double %b) {
|
|
ret double %b
|
|
}
|
|
; CHECK-LABEL: {{^}}test_fp_1@@16:
|
|
; CHECK: movaps %xmm1, %xmm0
|
|
|
|
define x86_vectorcallcc double @test_fp_2(
|
|
double, double, double, double, double, double, double %r) {
|
|
ret double %r
|
|
}
|
|
; CHECK-LABEL: {{^}}test_fp_2@@56:
|
|
; CHECK: movsd {{[0-9]+\(%[re]sp\)}}, %xmm0
|
|
|
|
define x86_vectorcallcc {double, double, double, double} @test_fp_3() {
|
|
ret {double, double, double, double}
|
|
{ double 0.0, double 0.0, double 0.0, double 0.0 }
|
|
}
|
|
; CHECK-LABEL: {{^}}test_fp_3@@0:
|
|
; CHECK: xorps %xmm0
|
|
; CHECK: xorps %xmm1
|
|
; CHECK: xorps %xmm2
|
|
; CHECK: xorps %xmm3
|
|
|
|
; FIXME: Returning via x87 isn't compatible, but its hard to structure the
|
|
; tablegen any other way.
|
|
define x86_vectorcallcc {double, double, double, double, double} @test_fp_4() {
|
|
ret {double, double, double, double, double}
|
|
{ double 0.0, double 0.0, double 0.0, double 0.0, double 0.0 }
|
|
}
|
|
; CHECK-LABEL: {{^}}test_fp_4@@0:
|
|
; CHECK: fldz
|
|
; CHECK: xorps %xmm0
|
|
; CHECK: xorps %xmm1
|
|
; CHECK: xorps %xmm2
|
|
; CHECK: xorps %xmm3
|
|
|
|
define x86_vectorcallcc <16 x i8> @test_vec_1(<16 x i8> %a, <16 x i8> %b) {
|
|
ret <16 x i8> %b
|
|
}
|
|
; CHECK-LABEL: {{^}}test_vec_1@@32:
|
|
; CHECK: movaps %xmm1, %xmm0
|
|
|
|
define x86_vectorcallcc <16 x i8> @test_vec_2(
|
|
double, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> %r) {
|
|
ret <16 x i8> %r
|
|
}
|
|
; CHECK-LABEL: {{^}}test_vec_2@@104:
|
|
; CHECK: movaps (%{{[re]}}cx), %xmm0
|