maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[ARM] MVE patterns for VMVN, VORR and VBIC 

This add simple Q register forms of bitwise not instructions.

Differential Revision: https://reviews.llvm.org/D63983

llvm-svn: 365214
This commit is contained in:
David Green 2019-07-05 15:21:29 +00:00
parent df173bf9bc
commit 47afdaa487
2 changed files with 118 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
llvm/lib/Target/ARM/ARMInstrMVE.td
View File

@ -1530,6 +1530,15 @@ def MVE_VMVN : MVE_bit_arith<(outs MQPR:$Qd), (ins MQPR:$Qm),
let Inst{0} = 0b0;
}
let Predicates = [HasMVEInt] in {
def : Pat<(v16i8 (vnotq (v16i8 MQPR:$val1))),
(v16i8 (MVE_VMVN (v16i8 MQPR:$val1)))>;
def : Pat<(v8i16 (vnotq (v8i16 MQPR:$val1))),
(v8i16 (MVE_VMVN (v8i16 MQPR:$val1)))>;
def : Pat<(v4i32 (vnotq (v4i32 MQPR:$val1))),
(v4i32 (MVE_VMVN (v4i32 MQPR:$val1)))>;
}
class MVE_bit_ops<string iname, bits<2> bit_21_20, bit bit_28>
: MVE_bit_arith<(outs MQPR:$Qd), (ins MQPR:$Qn, MQPR:$Qm),
iname, "", "$Qd, $Qn, $Qm", ""> {
@ -1588,6 +1597,20 @@ let Predicates = [HasMVEInt] in {
(v8i16 (MVE_VEOR (v8i16 MQPR:$val1), (v8i16 MQPR:$val2)))>;
def : Pat<(v4i32 (xor (v4i32 MQPR:$val1), (v4i32 MQPR:$val2))),
(v4i32 (MVE_VEOR (v4i32 MQPR:$val1), (v4i32 MQPR:$val2)))>;
def : Pat<(v16i8 (and (v16i8 MQPR:$val1), (vnotq MQPR:$val2))),
(v16i8 (MVE_VBIC (v16i8 MQPR:$val1), (v16i8 MQPR:$val2)))>;
def : Pat<(v8i16 (and (v8i16 MQPR:$val1), (vnotq MQPR:$val2))),
(v8i16 (MVE_VBIC (v8i16 MQPR:$val1), (v8i16 MQPR:$val2)))>;
def : Pat<(v4i32 (and (v4i32 MQPR:$val1), (vnotq MQPR:$val2))),
(v4i32 (MVE_VBIC (v4i32 MQPR:$val1), (v4i32 MQPR:$val2)))>;
def : Pat<(v16i8 (or (v16i8 MQPR:$val1), (vnotq (v16i8 MQPR:$val2)))),
(v16i8 (MVE_VORN (v16i8 MQPR:$val1), (v16i8 MQPR:$val2)))>;
def : Pat<(v8i16 (or (v8i16 MQPR:$val1), (vnotq MQPR:$val2))),
(v8i16 (MVE_VORN (v8i16 MQPR:$val1), (v8i16 MQPR:$val2)))>;
def : Pat<(v4i32 (or (v4i32 MQPR:$val1), (vnotq MQPR:$val2))),
(v4i32 (MVE_VORN (v4i32 MQPR:$val1), (v4i32 MQPR:$val2)))>;
}
class MVE_bit_cmode<string iname, string suffix, bits<4> cmode, dag inOps>

95
llvm/test/CodeGen/Thumb2/mve-bitarith.ll
View File

@ -93,3 +93,98 @@ entry:
ret <4 x i32> %0
}
define arm_aapcs_vfpcc <16 x i8> @v_mvn_i8(<16 x i8> %src) {
; CHECK-LABEL: v_mvn_i8:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmvn q0, q0
; CHECK-NEXT: bx lr
entry:
%0 = xor <16 x i8> %src, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
ret <16 x i8> %0
}
define arm_aapcs_vfpcc <8 x i16> @v_mvn_i16(<8 x i16> %src) {
; CHECK-LABEL: v_mvn_i16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmvn q0, q0
; CHECK-NEXT: bx lr
entry:
%0 = xor <8 x i16> %src, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
ret <8 x i16> %0
}
define arm_aapcs_vfpcc <4 x i32> @v_mvn_i32(<4 x i32> %src) {
; CHECK-LABEL: v_mvn_i32:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmvn q0, q0
; CHECK-NEXT: bx lr
entry:
%0 = xor <4 x i32> %src, <i32 -1, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %0
}
define arm_aapcs_vfpcc <16 x i8> @v_bic_i8(<16 x i8> %src1, <16 x i8> %src2) {
; CHECK-LABEL: v_bic_i8:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vbic q0, q1, q0
; CHECK-NEXT: bx lr
entry:
%0 = xor <16 x i8> %src1, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
%1 = and <16 x i8> %src2, %0
ret <16 x i8> %1
}
define arm_aapcs_vfpcc <8 x i16> @v_bic_i16(<8 x i16> %src1, <8 x i16> %src2) {
; CHECK-LABEL: v_bic_i16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vbic q0, q1, q0
; CHECK-NEXT: bx lr
entry:
%0 = xor <8 x i16> %src1, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
%1 = and <8 x i16> %src2, %0
ret <8 x i16> %1
}
define arm_aapcs_vfpcc <4 x i32> @v_bic_i32(<4 x i32> %src1, <4 x i32> %src2) {
; CHECK-LABEL: v_bic_i32:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vbic q0, q1, q0
; CHECK-NEXT: bx lr
entry:
%0 = xor <4 x i32> %src1, <i32 -1, i32 -1, i32 -1, i32 -1>
%1 = and <4 x i32> %src2, %0
ret <4 x i32> %1
}
define arm_aapcs_vfpcc <16 x i8> @v_or_i8(<16 x i8> %src1, <16 x i8> %src2) {
; CHECK-LABEL: v_or_i8:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vorn q0, q1, q0
; CHECK-NEXT: bx lr
entry:
%0 = xor <16 x i8> %src1, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
%1 = or <16 x i8> %src2, %0
ret <16 x i8> %1
}
define arm_aapcs_vfpcc <8 x i16> @v_or_i16(<8 x i16> %src1, <8 x i16> %src2) {
; CHECK-LABEL: v_or_i16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vorn q0, q1, q0
; CHECK-NEXT: bx lr
entry:
%0 = xor <8 x i16> %src1, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
%1 = or <8 x i16> %src2, %0
ret <8 x i16> %1
}
define arm_aapcs_vfpcc <4 x i32> @v_or_i32(<4 x i32> %src1, <4 x i32> %src2) {
; CHECK-LABEL: v_or_i32:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vorn q0, q1, q0
; CHECK-NEXT: bx lr
entry:
%0 = xor <4 x i32> %src1, <i32 -1, i32 -1, i32 -1, i32 -1>
%1 = or <4 x i32> %src2, %0
ret <4 x i32> %1
}