llvm-6502/test/CodeGen/X86/v2f32.ll
Bill Wendling 3844109d1e --- Merging r127731 into '.':
U    test/CodeGen/X86/byval2.ll
U    test/CodeGen/X86/byval4.ll
U    test/CodeGen/X86/byval.ll
U    test/CodeGen/X86/byval3.ll
U    test/CodeGen/X86/byval5.ll
--- Merging r127732 into '.':
U    test/CodeGen/X86/stdarg.ll
U    test/CodeGen/X86/fold-mul-lohi.ll
U    test/CodeGen/X86/scalar-min-max-fill-operand.ll
U    test/CodeGen/X86/tailcallbyval64.ll
U    test/CodeGen/X86/stride-reuse.ll
U    test/CodeGen/X86/sse-align-3.ll
U    test/CodeGen/X86/sse-commute.ll
U    test/CodeGen/X86/stride-nine-with-base-reg.ll
U    test/CodeGen/X86/coalescer-commute2.ll
U    test/CodeGen/X86/sse-align-7.ll
U    test/CodeGen/X86/sse_reload_fold.ll
U    test/CodeGen/X86/sse-align-0.ll
--- Merging r127733 into '.':
U    test/CodeGen/X86/peep-vector-extract-concat.ll
U    test/CodeGen/X86/pmulld.ll
U    test/CodeGen/X86/widen_load-0.ll
U    test/CodeGen/X86/v2f32.ll
U    test/CodeGen/X86/apm.ll
U    test/CodeGen/X86/h-register-store.ll
U    test/CodeGen/X86/h-registers-0.ll
--- Merging r127734 into '.':
U    test/CodeGen/X86/2007-01-08-X86-64-Pointer.ll
U    test/CodeGen/X86/convert-2-addr-3-addr-inc64.ll
U    test/CodeGen/X86/avoid-lea-scale2.ll
U    test/CodeGen/X86/lea-3.ll
U    test/CodeGen/X86/vec_set-8.ll
U    test/CodeGen/X86/i64-mem-copy.ll
U    test/CodeGen/X86/x86-64-malloc.ll
U    test/CodeGen/X86/mmx-copy-gprs.ll
U    test/CodeGen/X86/vec_shuffle-17.ll
U    test/CodeGen/X86/2007-07-18-Vector-Extract.ll
--- Merging r127775 into '.':
U    test/CodeGen/X86/constant-pool-remat-0.ll
--- Merging r127872 into '.':
U    utils/lit/lit/TestingConfig.py
U    lib/Support/raw_ostream.cpp



git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_29@128258 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-25 06:22:54 +00:00

116 lines
2.7 KiB
LLVM

; RUN: llc < %s -mtriple=x86_64-linux -mcpu=penryn -asm-verbose=0 -o - | FileCheck %s -check-prefix=X64
; RUN: llc < %s -mtriple=x86_64-win32 -mcpu=penryn -asm-verbose=0 -o - | FileCheck %s -check-prefix=W64
; RUN: llc < %s -mcpu=yonah -march=x86 -asm-verbose=0 -o - | FileCheck %s -check-prefix=X32
; PR7518
define void @test1(<2 x float> %Q, float *%P2) nounwind {
%a = extractelement <2 x float> %Q, i32 0
%b = extractelement <2 x float> %Q, i32 1
%c = fadd float %a, %b
store float %c, float* %P2
ret void
; X64: test1:
; X64-NEXT: pshufd $1, %xmm0, %xmm1
; X64-NEXT: addss %xmm0, %xmm1
; X64-NEXT: movss %xmm1, (%rdi)
; X64-NEXT: ret
; W64: test1:
; W64-NEXT: movdqa (%rcx), %xmm0
; W64-NEXT: pshufd $1, %xmm0, %xmm1
; W64-NEXT: addss %xmm0, %xmm1
; W64-NEXT: movss %xmm1, (%rdx)
; W64-NEXT: ret
; X32: test1:
; X32-NEXT: pshufd $1, %xmm0, %xmm1
; X32-NEXT: addss %xmm0, %xmm1
; X32-NEXT: movl 4(%esp), %eax
; X32-NEXT: movss %xmm1, (%eax)
; X32-NEXT: ret
}
define <2 x float> @test2(<2 x float> %Q, <2 x float> %R, <2 x float> *%P) nounwind {
%Z = fadd <2 x float> %Q, %R
ret <2 x float> %Z
; X64: test2:
; X64-NEXT: addps %xmm1, %xmm0
; X64-NEXT: ret
; W64: test2:
; W64-NEXT: movaps (%rcx), %xmm0
; W64-NEXT: addps (%rdx), %xmm0
; W64-NEXT: ret
; X32: test2:
; X32: addps %xmm1, %xmm0
}
define <2 x float> @test3(<4 x float> %A) nounwind {
%B = shufflevector <4 x float> %A, <4 x float> undef, <2 x i32> <i32 0, i32 1>
%C = fadd <2 x float> %B, %B
ret <2 x float> %C
; X64: test3:
; X64-NEXT: addps %xmm0, %xmm0
; X64-NEXT: ret
; W64: test3:
; W64-NEXT: movaps (%rcx), %xmm0
; W64-NEXT: addps %xmm0, %xmm0
; W64-NEXT: ret
; X32: test3:
; X32-NEXT: addps %xmm0, %xmm0
; X32-NEXT: ret
}
define <2 x float> @test4(<2 x float> %A) nounwind {
%C = fadd <2 x float> %A, %A
ret <2 x float> %C
; X64: test4:
; X64-NEXT: addps %xmm0, %xmm0
; X64-NEXT: ret
; W64: test4:
; W64-NEXT: movaps (%rcx), %xmm0
; W64-NEXT: addps %xmm0, %xmm0
; W64-NEXT: ret
; X32: test4:
; X32-NEXT: addps %xmm0, %xmm0
; X32-NEXT: ret
}
define <4 x float> @test5(<4 x float> %A) nounwind {
%B = shufflevector <4 x float> %A, <4 x float> undef, <2 x i32> <i32 0, i32 1>
%C = fadd <2 x float> %B, %B
br label %BB
BB:
%D = fadd <2 x float> %C, %C
%E = shufflevector <2 x float> %D, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
ret <4 x float> %E
; X64: test5:
; X64-NEXT: addps %xmm0, %xmm0
; X64-NEXT: addps %xmm0, %xmm0
; X64-NEXT: ret
; W64: test5:
; W64-NEXT: movaps (%rcx), %xmm0
; W64-NEXT: addps %xmm0, %xmm0
; W64-NEXT: addps %xmm0, %xmm0
; W64-NEXT: ret
; X32: test5:
; X32-NEXT: addps %xmm0, %xmm0
; X32-NEXT: addps %xmm0, %xmm0
; X32-NEXT: ret
}