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

[ARM] Fix MVE VCMPr f16 pattern 

This patterns seemed to be using the f32 instruction, not f16. Fix it to
use the correct one.

Differential Revision: https://reviews.llvm.org/D76841
This commit is contained in:
David Green 2020-03-27 07:24:15 +00:00
parent 8f4ab8c7d7
commit 8689f98e9b
2 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/ARM/ARMInstrMVE.td
View File

@ -4101,7 +4101,7 @@ multiclass unpred_vcmpf_z<PatLeaf fc> {
(v4i1 (MVE_VCMPf32r (v4f32 MQPR:$v1), ZR, fc))>;
def : Pat<(v8i1 (and (v8i1 VCCR:$p1), (v8i1 (ARMvcmpz (v8f16 MQPR:$v1), fc)))),
(v8i1 (MVE_VCMPf32r (v8f16 MQPR:$v1), ZR, fc, ARMVCCThen, VCCR:$p1))>;
(v8i1 (MVE_VCMPf16r (v8f16 MQPR:$v1), ZR, fc, ARMVCCThen, VCCR:$p1))>;
def : Pat<(v4i1 (and (v4i1 VCCR:$p1), (v4i1 (ARMvcmpz (v4f32 MQPR:$v1), fc)))),
(v4i1 (MVE_VCMPf32r (v4f32 MQPR:$v1), ZR, fc, ARMVCCThen, VCCR:$p1))>;
}

16
llvm/test/CodeGen/Thumb2/mve-vcmpfz.ll
View File

@ -1010,7 +1010,7 @@ define arm_aapcs_vfpcc <8 x half> @vcmp_one_v8f16(<8 x half> %src, <8 x half> %a
; CHECK-MVEFP-LABEL: vcmp_one_v8f16:
; CHECK-MVEFP: @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT: vpt.f16 ge, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f32 le, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f16 le, q0, zr
; CHECK-MVEFP-NEXT: vpnot
; CHECK-MVEFP-NEXT: vpsel q0, q1, q2
; CHECK-MVEFP-NEXT: bx lr
@ -1628,7 +1628,7 @@ define arm_aapcs_vfpcc <8 x half> @vcmp_ueq_v8f16(<8 x half> %src, <8 x half> %a
; CHECK-MVEFP-LABEL: vcmp_ueq_v8f16:
; CHECK-MVEFP: @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT: vpt.f16 ge, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f32 le, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f16 le, q0, zr
; CHECK-MVEFP-NEXT: vpsel q0, q1, q2
; CHECK-MVEFP-NEXT: bx lr
entry:
@ -2353,7 +2353,7 @@ define arm_aapcs_vfpcc <8 x half> @vcmp_ord_v8f16(<8 x half> %src, <8 x half> %a
; CHECK-MVEFP-LABEL: vcmp_ord_v8f16:
; CHECK-MVEFP: @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT: vpt.f16 ge, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f32 lt, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f16 lt, q0, zr
; CHECK-MVEFP-NEXT: vpnot
; CHECK-MVEFP-NEXT: vpsel q0, q1, q2
; CHECK-MVEFP-NEXT: bx lr
@ -2475,7 +2475,7 @@ define arm_aapcs_vfpcc <8 x half> @vcmp_uno_v8f16(<8 x half> %src, <8 x half> %a
; CHECK-MVEFP-LABEL: vcmp_uno_v8f16:
; CHECK-MVEFP: @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT: vpt.f16 ge, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f32 lt, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f16 lt, q0, zr
; CHECK-MVEFP-NEXT: vpsel q0, q1, q2
; CHECK-MVEFP-NEXT: bx lr
entry:
@ -3495,7 +3495,7 @@ define arm_aapcs_vfpcc <8 x half> @vcmp_r_one_v8f16(<8 x half> %src, <8 x half>
; CHECK-MVEFP-LABEL: vcmp_r_one_v8f16:
; CHECK-MVEFP: @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT: vpt.f16 le, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f32 ge, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f16 ge, q0, zr
; CHECK-MVEFP-NEXT: vpnot
; CHECK-MVEFP-NEXT: vpsel q0, q1, q2
; CHECK-MVEFP-NEXT: bx lr
@ -4113,7 +4113,7 @@ define arm_aapcs_vfpcc <8 x half> @vcmp_r_ueq_v8f16(<8 x half> %src, <8 x half>
; CHECK-MVEFP-LABEL: vcmp_r_ueq_v8f16:
; CHECK-MVEFP: @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT: vpt.f16 le, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f32 ge, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f16 ge, q0, zr
; CHECK-MVEFP-NEXT: vpsel q0, q1, q2
; CHECK-MVEFP-NEXT: bx lr
entry:
@ -4838,7 +4838,7 @@ define arm_aapcs_vfpcc <8 x half> @vcmp_r_ord_v8f16(<8 x half> %src, <8 x half>
; CHECK-MVEFP-LABEL: vcmp_r_ord_v8f16:
; CHECK-MVEFP: @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT: vpt.f16 le, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f32 gt, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f16 gt, q0, zr
; CHECK-MVEFP-NEXT: vpnot
; CHECK-MVEFP-NEXT: vpsel q0, q1, q2
; CHECK-MVEFP-NEXT: bx lr
@ -4960,7 +4960,7 @@ define arm_aapcs_vfpcc <8 x half> @vcmp_r_uno_v8f16(<8 x half> %src, <8 x half>
; CHECK-MVEFP-LABEL: vcmp_r_uno_v8f16:
; CHECK-MVEFP: @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT: vpt.f16 le, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f32 gt, q0, zr
; CHECK-MVEFP-NEXT: vcmpt.f16 gt, q0, zr
; CHECK-MVEFP-NEXT: vpsel q0, q1, q2
; CHECK-MVEFP-NEXT: bx lr
entry: