mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +01:00
211286ee5b
D75689 turns the faddp pattern into a shuffle with vector add. Match this new pattern in target-specific DAG combine, rather than ISel, because legalization (for v2f32) turns it into a bit of a mess. - extended to cover f16, f32, f64 and i64
103 lines
3.2 KiB
LLVM
103 lines
3.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc --mtriple aarch64 < %s | FileCheck %s
|
|
|
|
define float @faddp_2xfloat(<2 x float> %a) {
|
|
; CHECK-LABEL: faddp_2xfloat:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
|
|
; CHECK-NEXT: faddp s0, v0.2s
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%shift = shufflevector <2 x float> %a, <2 x float> undef, <2 x i32> <i32 1, i32 undef>
|
|
%0 = fadd <2 x float> %a, %shift
|
|
%1 = extractelement <2 x float> %0, i32 0
|
|
ret float %1
|
|
}
|
|
|
|
define float @faddp_4xfloat(<4 x float> %a) {
|
|
; CHECK-LABEL: faddp_4xfloat:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: faddp s0, v0.2s
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%shift = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
|
%0 = fadd <4 x float> %a, %shift
|
|
%1 = extractelement <4 x float> %0, i32 0
|
|
ret float %1
|
|
}
|
|
|
|
define float @faddp_4xfloat_commute(<4 x float> %a) {
|
|
; CHECK-LABEL: faddp_4xfloat_commute:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: faddp s0, v0.2s
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%shift = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
|
|
%0 = fadd <4 x float> %shift, %a
|
|
%1 = extractelement <4 x float> %0, i32 0
|
|
ret float %1
|
|
}
|
|
|
|
define float @faddp_2xfloat_commute(<2 x float> %a) {
|
|
; CHECK-LABEL: faddp_2xfloat_commute:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
|
|
; CHECK-NEXT: faddp s0, v0.2s
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%shift = shufflevector <2 x float> %a, <2 x float> undef, <2 x i32> <i32 1, i32 undef>
|
|
%0 = fadd <2 x float> %shift, %a
|
|
%1 = extractelement <2 x float> %0, i32 0
|
|
ret float %1
|
|
}
|
|
|
|
define double @faddp_2xdouble(<2 x double> %a) {
|
|
; CHECK-LABEL: faddp_2xdouble:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: faddp d0, v0.2d
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%shift = shufflevector <2 x double> %a, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
|
|
%0 = fadd <2 x double> %a, %shift
|
|
%1 = extractelement <2 x double> %0, i32 0
|
|
ret double %1
|
|
}
|
|
|
|
define double @faddp_2xdouble_commute(<2 x double> %a) {
|
|
; CHECK-LABEL: faddp_2xdouble_commute:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: faddp d0, v0.2d
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%shift = shufflevector <2 x double> %a, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
|
|
%0 = fadd <2 x double> %shift, %a
|
|
%1 = extractelement <2 x double> %0, i32 0
|
|
ret double %1
|
|
}
|
|
|
|
define i64 @addp_2xi64(<2 x i64> %a) {
|
|
; CHECK-LABEL: addp_2xi64:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: addp d0, v0.2d
|
|
; CHECK-NEXT: fmov x0, d0
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%shift = shufflevector <2 x i64> %a, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
|
%0 = add <2 x i64> %a, %shift
|
|
%1 = extractelement <2 x i64> %0, i32 0
|
|
ret i64 %1
|
|
}
|
|
|
|
define i64 @addp_2xi64_commute(<2 x i64> %a) {
|
|
; CHECK-LABEL: addp_2xi64_commute:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: addp d0, v0.2d
|
|
; CHECK-NEXT: fmov x0, d0
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%shift = shufflevector <2 x i64> %a, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
|
|
%0 = add <2 x i64> %shift, %a
|
|
%1 = extractelement <2 x i64> %0, i32 0
|
|
ret i64 %1
|
|
}
|