maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/sse-intel-ocl.ll

94 lines
3.8 KiB
LLVM
Raw Normal View History

Special calling conventions for Intel OpenCL built-in library. llvm-svn: 166566
2012-10-24 22:46:16 +08:00
; RUN: llc < %s -mtriple=i386-pc-win32 -mcpu=nehalem | FileCheck -check-prefix=WIN32 %s
; RUN: llc < %s -mtriple=x86_64-win32 -mcpu=nehalem | FileCheck -check-prefix=WIN64 %s
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=nehalem | FileCheck -check-prefix=NOT_WIN %s
declare <16 x float> @func_float16_ptr(<16 x float>, <16 x float> *)
declare <16 x float> @func_float16(<16 x float>, <16 x float>)
; WIN64: testf16_inp
; WIN64: addps {{.*}}, {{%xmm[0-3]}}
; WIN64: addps {{.*}}, {{%xmm[0-3]}}
; WIN64: addps {{.*}}, {{%xmm[0-3]}}
; WIN64: addps {{.*}}, {{%xmm[0-3]}}
; WIN64: leaq {{.*}}(%rsp), %rcx
; WIN64: call
; WIN64: ret
; WIN32: testf16_inp
; WIN32: movl %eax, (%esp)
; WIN32: addps {{.*}}, {{%xmm[0-3]}}
; WIN32: addps {{.*}}, {{%xmm[0-3]}}
; WIN32: addps {{.*}}, {{%xmm[0-3]}}
; WIN32: addps {{.*}}, {{%xmm[0-3]}}
; WIN32: call
; WIN32: ret
; NOT_WIN: testf16_inp
; NOT_WIN: addps {{.*}}, {{%xmm[0-3]}}
; NOT_WIN: addps {{.*}}, {{%xmm[0-3]}}
; NOT_WIN: addps {{.*}}, {{%xmm[0-3]}}
; NOT_WIN: addps {{.*}}, {{%xmm[0-3]}}
; NOT_WIN: leaq {{.*}}(%rsp), %rdi
; NOT_WIN: call
; NOT_WIN: ret
;test calling conventions - input parameters
define <16 x float> @testf16_inp(<16 x float> %a, <16 x float> %b) nounwind {
%y = alloca <16 x float>, align 16
%x = fadd <16 x float> %a, %b
%1 = call intel_ocl_bicc <16 x float> @func_float16_ptr(<16 x float> %x, <16 x float>* %y)
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%2 = load <16 x float>, <16 x float>* %y, align 16
Special calling conventions for Intel OpenCL built-in library. llvm-svn: 166566
2012-10-24 22:46:16 +08:00
%3 = fadd <16 x float> %2, %1
ret <16 x float> %3
}
;test calling conventions - preserved registers
; preserved xmm6-xmm15
; WIN64: testf16_regs
; WIN64: call
; WIN64: addps {{%xmm[6-9]}}, {{.*}}
; WIN64: addps {{%xmm[6-9]}}, {{.*}}
; WIN64: ret
; preserved xmm8-xmm15
; NOT_WIN: testf16_regs
; NOT_WIN: call
; NOT_WIN: addps {{%xmm([8-9]|1[0-1])}}, {{.*}}
; NOT_WIN: addps {{%xmm([8-9]|1[0-1])}}, {{.*}}
; NOT_WIN: addps {{%xmm([8-9]|1[0-1])}}, {{.*}}
; NOT_WIN: addps {{%xmm([8-9]|1[0-1])}}, {{.*}}
; NOT_WIN: ret
define <16 x float> @testf16_regs(<16 x float> %a, <16 x float> %b) nounwind {
%y = alloca <16 x float>, align 16
%x = fadd <16 x float> %a, %b
%1 = call intel_ocl_bicc <16 x float> @func_float16_ptr(<16 x float> %x, <16 x float>* %y)
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%2 = load <16 x float>, <16 x float>* %y, align 16
Special calling conventions for Intel OpenCL built-in library. llvm-svn: 166566
2012-10-24 22:46:16 +08:00
%3 = fadd <16 x float> %1, %b
%4 = fadd <16 x float> %2, %3
ret <16 x float> %4
}
; test calling conventions - prolog and epilog
; NOT_WIN: movaps {{%xmm([8-9]|1[0-5])}}, {{.*(%rsp).*}} ## 16-byte Spill
; NOT_WIN: movaps {{%xmm([8-9]|1[0-5])}}, {{.*(%rsp).*}} ## 16-byte Spill
; NOT_WIN: movaps {{%xmm([8-9]|1[0-5])}}, {{.*(%rsp).*}} ## 16-byte Spill
; NOT_WIN: movaps {{%xmm([8-9]|1[0-5])}}, {{.*(%rsp).*}} ## 16-byte Spill
; NOT_WIN: movaps {{%xmm([8-9]|1[0-5])}}, {{.*(%rsp).*}} ## 16-byte Spill
; NOT_WIN: movaps {{%xmm([8-9]|1[0-5])}}, {{.*(%rsp).*}} ## 16-byte Spill
; NOT_WIN: movaps {{%xmm([8-9]|1[0-5])}}, {{.*(%rsp).*}} ## 16-byte Spill
; NOT_WIN: movaps {{%xmm([8-9]|1[0-5])}}, {{.*(%rsp).*}} ## 16-byte Spill
; NOT_WIN: call
; NOT_WIN: movaps {{.*(%rsp).*}}, {{%xmm([8-9]|1[0-5])}} ## 16-byte Reload
; NOT_WIN: movaps {{.*(%rsp).*}}, {{%xmm([8-9]|1[0-5])}} ## 16-byte Reload
; NOT_WIN: movaps {{.*(%rsp).*}}, {{%xmm([8-9]|1[0-5])}} ## 16-byte Reload
; NOT_WIN: movaps {{.*(%rsp).*}}, {{%xmm([8-9]|1[0-5])}} ## 16-byte Reload
; NOT_WIN: movaps {{.*(%rsp).*}}, {{%xmm([8-9]|1[0-5])}} ## 16-byte Reload
; NOT_WIN: movaps {{.*(%rsp).*}}, {{%xmm([8-9]|1[0-5])}} ## 16-byte Reload
; NOT_WIN: movaps {{.*(%rsp).*}}, {{%xmm([8-9]|1[0-5])}} ## 16-byte Reload
; NOT_WIN: movaps {{.*(%rsp).*}}, {{%xmm([8-9]|1[0-5])}} ## 16-byte Reload
define intel_ocl_bicc <16 x float> @test_prolog_epilog(<16 x float> %a, <16 x float> %b) nounwind {
%c = call <16 x float> @func_float16(<16 x float> %a, <16 x float> %b)
ret <16 x float> %c
}