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

[ARM] Regenerate mve-vabd.ll test. NFC

This commit is contained in:
David Green 2020-08-20 12:24:27 +01:00
parent 835cfa5def
commit b7603cb128
1 changed files with 141 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

116
llvm/test/CodeGen/Thumb2/mve-vabd.ll
View File

@ -3,7 +3,7 @@
; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve.fp %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MVEFP ; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve.fp %s -o - | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-MVEFP
define arm_aapcs_vfpcc void @vabd_v4f32(<4 x float> %x, <4 x float> %y, <4 x float>* %z) { define arm_aapcs_vfpcc void @vabd_v4f32(<4 x float> %x, <4 x float> %y, <4 x float>* %z) {
; CHECK-MVE-LABEL: vabd_v4f32 ; CHECK-MVE-LABEL: vabd_v4f32:
; CHECK-MVE: @ %bb.0: @ %entry ; CHECK-MVE: @ %bb.0: @ %entry
; CHECK-MVE-NEXT: .save {r4, r5, r6, r7, lr} ; CHECK-MVE-NEXT: .save {r4, r5, r6, r7, lr}
; CHECK-MVE-NEXT: push {r4, r5, r6, r7, lr} ; CHECK-MVE-NEXT: push {r4, r5, r6, r7, lr}
@ -19,12 +19,35 @@ define arm_aapcs_vfpcc void @vabd_v4f32(<4 x float> %x, <4 x float> %y, <4 x flo
; CHECK-MVE-NEXT: bl __aeabi_fsub ; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: mov r5, r0 ; CHECK-MVE-NEXT: mov r5, r0
; CHECK-MVE-NEXT: vmov r0, s21 ; CHECK-MVE-NEXT: vmov r0, s21
; CHECK-MVE-NEXT: vmov r1, s17
; CHECK-MVEFP-LABEL: vabd_v4f32 ; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: mov r6, r0
; CHECK-MVE-NEXT: vmov r0, s22
; CHECK-MVE-NEXT: vmov r1, s18
; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: mov r7, r0
; CHECK-MVE-NEXT: vmov r0, s23
; CHECK-MVE-NEXT: vmov r1, s19
; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: bic r0, r0, #-2147483648
; CHECK-MVE-NEXT: vmov s3, r0
; CHECK-MVE-NEXT: bic r0, r7, #-2147483648
; CHECK-MVE-NEXT: vmov s2, r0
; CHECK-MVE-NEXT: bic r0, r6, #-2147483648
; CHECK-MVE-NEXT: vmov s1, r0
; CHECK-MVE-NEXT: bic r0, r5, #-2147483648
; CHECK-MVE-NEXT: vmov s0, r0
; CHECK-MVE-NEXT: vstrw.32 q0, [r4]
; CHECK-MVE-NEXT: vpop {d8, d9, d10, d11}
; CHECK-MVE-NEXT: add sp, #4
; CHECK-MVE-NEXT: pop {r4, r5, r6, r7, pc}
;
; CHECK-MVEFP-LABEL: vabd_v4f32:
; CHECK-MVEFP: @ %bb.0: @ %entry ; CHECK-MVEFP: @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT: vabd.f32 q0, q0, q1 ; CHECK-MVEFP-NEXT: vabd.f32 q0, q0, q1
; CHECK-MVEFP-NEXT: vstrw.32 q0, [r0] ; CHECK-MVEFP-NEXT: vstrw.32 q0, [r0]
; CHECK-MVEFP-NEXT: bx lr ; CHECK-MVEFP-NEXT: bx lr
entry: entry:
%0 = fsub <4 x float> %x, %y %0 = fsub <4 x float> %x, %y
%1 = call <4 x float> @llvm.fabs.v4f32(<4 x float> %0) %1 = call <4 x float> @llvm.fabs.v4f32(<4 x float> %0)
@ -33,7 +56,7 @@ entry:
} }
define arm_aapcs_vfpcc void @vabd_v8f16(<8 x half> %x, <8 x half> %y, <8 x half>* %z) { define arm_aapcs_vfpcc void @vabd_v8f16(<8 x half> %x, <8 x half> %y, <8 x half>* %z) {
; CHECK-MVE-LABEL: vabd_v8f16 ; CHECK-MVE-LABEL: vabd_v8f16:
; CHECK-MVE: @ %bb.0: @ %entry ; CHECK-MVE: @ %bb.0: @ %entry
; CHECK-MVE-NEXT: .save {r4, r5, r6, lr} ; CHECK-MVE-NEXT: .save {r4, r5, r6, lr}
; CHECK-MVE-NEXT: push {r4, r5, r6, lr} ; CHECK-MVE-NEXT: push {r4, r5, r6, lr}
@ -46,12 +69,93 @@ define arm_aapcs_vfpcc void @vabd_v8f16(<8 x half> %x, <8 x half> %y, <8 x half>
; CHECK-MVE-NEXT: bl __aeabi_h2f ; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r5, r0 ; CHECK-MVE-NEXT: mov r5, r0
; CHECK-MVE-NEXT: vmov.u16 r0, q4[1] ; CHECK-MVE-NEXT: vmov.u16 r0, q4[1]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVEFP-LABEL: vabd_v8f16 ; CHECK-MVE-NEXT: mov r1, r5
; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: mov r5, r0
; CHECK-MVE-NEXT: vmov.u16 r0, q5[0]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r6, r0
; CHECK-MVE-NEXT: vmov.u16 r0, q4[0]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r1, r6
; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: bic r0, r0, #-2147483648
; CHECK-MVE-NEXT: bl __aeabi_f2h
; CHECK-MVE-NEXT: vmov.16 q6[0], r0
; CHECK-MVE-NEXT: bic r0, r5, #-2147483648
; CHECK-MVE-NEXT: bl __aeabi_f2h
; CHECK-MVE-NEXT: vmov.16 q6[1], r0
; CHECK-MVE-NEXT: vmov.u16 r0, q5[2]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r5, r0
; CHECK-MVE-NEXT: vmov.u16 r0, q4[2]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r1, r5
; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: bic r0, r0, #-2147483648
; CHECK-MVE-NEXT: bl __aeabi_f2h
; CHECK-MVE-NEXT: vmov.16 q6[2], r0
; CHECK-MVE-NEXT: vmov.u16 r0, q5[3]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r5, r0
; CHECK-MVE-NEXT: vmov.u16 r0, q4[3]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r1, r5
; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: bic r0, r0, #-2147483648
; CHECK-MVE-NEXT: bl __aeabi_f2h
; CHECK-MVE-NEXT: vmov.16 q6[3], r0
; CHECK-MVE-NEXT: vmov.u16 r0, q5[4]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r5, r0
; CHECK-MVE-NEXT: vmov.u16 r0, q4[4]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r1, r5
; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: bic r0, r0, #-2147483648
; CHECK-MVE-NEXT: bl __aeabi_f2h
; CHECK-MVE-NEXT: vmov.16 q6[4], r0
; CHECK-MVE-NEXT: vmov.u16 r0, q5[5]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r5, r0
; CHECK-MVE-NEXT: vmov.u16 r0, q4[5]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r1, r5
; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: bic r0, r0, #-2147483648
; CHECK-MVE-NEXT: bl __aeabi_f2h
; CHECK-MVE-NEXT: vmov.16 q6[5], r0
; CHECK-MVE-NEXT: vmov.u16 r0, q5[6]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r5, r0
; CHECK-MVE-NEXT: vmov.u16 r0, q4[6]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r1, r5
; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: bic r0, r0, #-2147483648
; CHECK-MVE-NEXT: bl __aeabi_f2h
; CHECK-MVE-NEXT: vmov.16 q6[6], r0
; CHECK-MVE-NEXT: vmov.u16 r0, q5[7]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r5, r0
; CHECK-MVE-NEXT: vmov.u16 r0, q4[7]
; CHECK-MVE-NEXT: bl __aeabi_h2f
; CHECK-MVE-NEXT: mov r1, r5
; CHECK-MVE-NEXT: bl __aeabi_fsub
; CHECK-MVE-NEXT: bic r0, r0, #-2147483648
; CHECK-MVE-NEXT: bl __aeabi_f2h
; CHECK-MVE-NEXT: vmov.16 q6[7], r0
; CHECK-MVE-NEXT: vstrw.32 q6, [r4]
; CHECK-MVE-NEXT: vpop {d8, d9, d10, d11, d12, d13}
; CHECK-MVE-NEXT: pop {r4, r5, r6, pc}
;
; CHECK-MVEFP-LABEL: vabd_v8f16:
; CHECK-MVEFP: @ %bb.0: @ %entry ; CHECK-MVEFP: @ %bb.0: @ %entry
; CHECK-MVEFP-NEXT: vabd.f16 q0, q0, q1 ; CHECK-MVEFP-NEXT: vabd.f16 q0, q0, q1
; CHECK-MVEFP-NEXT: vstrw.32 q0, [r0] ; CHECK-MVEFP-NEXT: vstrw.32 q0, [r0]
; CHECK-MVEFP-NEXT: bx lr ; CHECK-MVEFP-NEXT: bx lr
entry: entry:
%0 = fsub <8 x half> %x, %y %0 = fsub <8 x half> %x, %y
%1 = call <8 x half> @llvm.fabs.v8f16(<8 x half> %0) %1 = call <8 x half> @llvm.fabs.v8f16(<8 x half> %0)