mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-12 13:30:51 +00:00
3844109d1e
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
126 lines
4.9 KiB
LLVM
126 lines
4.9 KiB
LLVM
; RUN: llc < %s -mtriple=x86_64-linux -mattr=+64bit,+sse3 -print-failed-fuse-candidates |& FileCheck %s
|
|
; CHECK: fail
|
|
; CHECK-NOT: fail
|
|
|
|
declare float @test_f(float %f)
|
|
declare double @test_d(double %f)
|
|
declare <4 x float> @test_vf(<4 x float> %f)
|
|
declare <2 x double> @test_vd(<2 x double> %f)
|
|
declare float @llvm.sqrt.f32(float)
|
|
declare double @llvm.sqrt.f64(double)
|
|
|
|
declare <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float>)
|
|
declare <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float>)
|
|
declare <4 x float> @llvm.x86.sse.rcp.ps(<4 x float>)
|
|
declare <4 x float> @llvm.x86.sse.min.ps(<4 x float>, <4 x float>)
|
|
declare <4 x float> @llvm.x86.sse.max.ps(<4 x float>, <4 x float>)
|
|
declare <4 x float> @llvm.x86.sse.cmp.ps(<4 x float>, <4 x float>, i8)
|
|
declare <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float>, <4 x float>)
|
|
declare <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float>, <4 x float>)
|
|
declare <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float>, <4 x float>)
|
|
declare <2 x double> @llvm.x86.sse2.sqrt.pd(<2 x double>)
|
|
declare <2 x double> @llvm.x86.sse2.min.pd(<2 x double>, <2 x double>)
|
|
declare <2 x double> @llvm.x86.sse2.max.pd(<2 x double>, <2 x double>)
|
|
declare <2 x double> @llvm.x86.sse2.cmp.pd(<2 x double>, <2 x double>, i8)
|
|
declare <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double>, <2 x double>)
|
|
declare <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double>, <2 x double>)
|
|
declare <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double>, <2 x double>)
|
|
|
|
define float @foo(float %f) {
|
|
%a = call float @test_f(float %f)
|
|
%t = call float @llvm.sqrt.f32(float %f)
|
|
ret float %t
|
|
}
|
|
define double @doo(double %f) {
|
|
%a = call double @test_d(double %f)
|
|
%t = call double @llvm.sqrt.f64(double %f)
|
|
ret double %t
|
|
}
|
|
define <4 x float> @a0(<4 x float> %f) {
|
|
%a = call <4 x float> @test_vf(<4 x float> %f)
|
|
%t = call <4 x float> @llvm.x86.sse.rsqrt.ps(<4 x float> %f)
|
|
ret <4 x float> %t
|
|
}
|
|
define <4 x float> @a1(<4 x float> %f) {
|
|
%a = call <4 x float> @test_vf(<4 x float> %f)
|
|
%t = call <4 x float> @llvm.x86.sse.sqrt.ps(<4 x float> %f)
|
|
ret <4 x float> %t
|
|
}
|
|
define <4 x float> @a2(<4 x float> %f) {
|
|
%a = call <4 x float> @test_vf(<4 x float> %f)
|
|
%t = call <4 x float> @llvm.x86.sse.rcp.ps(<4 x float> %f)
|
|
ret <4 x float> %t
|
|
}
|
|
define <4 x float> @b3(<4 x float> %f) {
|
|
%y = call <4 x float> @test_vf(<4 x float> %f)
|
|
%t = call <4 x float> @llvm.x86.sse.min.ps(<4 x float> %y, <4 x float> %f)
|
|
ret <4 x float> %t
|
|
}
|
|
define <4 x float> @b4(<4 x float> %f) {
|
|
%y = call <4 x float> @test_vf(<4 x float> %f)
|
|
%t = call <4 x float> @llvm.x86.sse.max.ps(<4 x float> %y, <4 x float> %f)
|
|
ret <4 x float> %t
|
|
}
|
|
define <4 x float> @b5(<4 x float> %f) {
|
|
%y = call <4 x float> @test_vf(<4 x float> %f)
|
|
%t = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %y, <4 x float> %f, i8 7)
|
|
ret <4 x float> %t
|
|
}
|
|
define <4 x float> @b6(<4 x float> %f) {
|
|
%y = call <4 x float> @test_vf(<4 x float> %f)
|
|
%t = call <4 x float> @llvm.x86.sse3.addsub.ps(<4 x float> %y, <4 x float> %f)
|
|
ret <4 x float> %t
|
|
}
|
|
define <4 x float> @b7(<4 x float> %f) {
|
|
%y = call <4 x float> @test_vf(<4 x float> %f)
|
|
%t = call <4 x float> @llvm.x86.sse3.hadd.ps(<4 x float> %y, <4 x float> %f)
|
|
ret <4 x float> %t
|
|
}
|
|
define <4 x float> @b8(<4 x float> %f) {
|
|
%y = call <4 x float> @test_vf(<4 x float> %f)
|
|
%t = call <4 x float> @llvm.x86.sse3.hsub.ps(<4 x float> %y, <4 x float> %f)
|
|
ret <4 x float> %t
|
|
}
|
|
define <2 x double> @c1(<2 x double> %f) {
|
|
%a = call <2 x double> @test_vd(<2 x double> %f)
|
|
%t = call <2 x double> @llvm.x86.sse2.sqrt.pd(<2 x double> %f)
|
|
ret <2 x double> %t
|
|
}
|
|
define <2 x double> @d3(<2 x double> %f) {
|
|
%y = call <2 x double> @test_vd(<2 x double> %f)
|
|
%t = call <2 x double> @llvm.x86.sse2.min.pd(<2 x double> %y, <2 x double> %f)
|
|
ret <2 x double> %t
|
|
}
|
|
define <2 x double> @d4(<2 x double> %f) {
|
|
%y = call <2 x double> @test_vd(<2 x double> %f)
|
|
%t = call <2 x double> @llvm.x86.sse2.max.pd(<2 x double> %y, <2 x double> %f)
|
|
ret <2 x double> %t
|
|
}
|
|
define <2 x double> @d5(<2 x double> %f) {
|
|
%y = call <2 x double> @test_vd(<2 x double> %f)
|
|
%t = call <2 x double> @llvm.x86.sse2.cmp.pd(<2 x double> %y, <2 x double> %f, i8 7)
|
|
ret <2 x double> %t
|
|
}
|
|
define <2 x double> @d6(<2 x double> %f) {
|
|
%y = call <2 x double> @test_vd(<2 x double> %f)
|
|
%t = call <2 x double> @llvm.x86.sse3.addsub.pd(<2 x double> %y, <2 x double> %f)
|
|
ret <2 x double> %t
|
|
}
|
|
define <2 x double> @d7(<2 x double> %f) {
|
|
%y = call <2 x double> @test_vd(<2 x double> %f)
|
|
%t = call <2 x double> @llvm.x86.sse3.hadd.pd(<2 x double> %y, <2 x double> %f)
|
|
ret <2 x double> %t
|
|
}
|
|
define <2 x double> @d8(<2 x double> %f) {
|
|
%y = call <2 x double> @test_vd(<2 x double> %f)
|
|
%t = call <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double> %y, <2 x double> %f)
|
|
ret <2 x double> %t
|
|
}
|
|
|
|
; This one should fail to fuse.
|
|
define <2 x double> @z0(<2 x double> %f) {
|
|
%y = call <2 x double> @test_vd(<2 x double> %f)
|
|
%t = call <2 x double> @llvm.x86.sse3.hsub.pd(<2 x double> %f, <2 x double> %y)
|
|
ret <2 x double> %t
|
|
}
|