forked from OSchip/llvm-project
[ARM] i16 insert-of-extract to VINS pattern
This adds another tablegen fold that converts an i16 odd-lane-insert of an even-lane-extract into a VINS. We extract the existing f32 value from the destination register and VINS the new value into it. The rest of the backend then is able to optimize the INSERT_SUBREG / COPY_TO_REGCLASS / EXTRACT_SUBREG. Differential Revision: https://reviews.llvm.org/D95456
This commit is contained in:
parent
0c42d87ea8
commit
1b435eb8f3
|
@ -1878,6 +1878,14 @@ let Predicates = [HasMVEInt] in {
|
|||
(MVE_VMOV_from_lane_u16 MQPR:$src, imm:$lane)>;
|
||||
def : Pat<(ARMvgetlaneu (v8f16 MQPR:$src), imm:$lane),
|
||||
(MVE_VMOV_from_lane_u16 MQPR:$src, imm:$lane)>;
|
||||
// For i16's inserts being extracted from low lanes, then may use VINS.
|
||||
def : Pat<(ARMinsertelt (v8i16 MQPR:$src1),
|
||||
(ARMvgetlaneu (v8i16 MQPR:$src2), imm_even:$extlane),
|
||||
imm_odd:$inslane),
|
||||
(COPY_TO_REGCLASS (INSERT_SUBREG (v4f32 (COPY_TO_REGCLASS MQPR:$src1, MQPR)),
|
||||
(VINSH (EXTRACT_SUBREG MQPR:$src1, (SSubReg_f16_reg imm_odd:$inslane)),
|
||||
(EXTRACT_SUBREG MQPR:$src2, (SSubReg_f16_reg imm_even:$extlane))),
|
||||
(SSubReg_f16_reg imm_odd:$inslane)), MQPR)>;
|
||||
|
||||
def : Pat<(v16i8 (scalar_to_vector GPR:$src)),
|
||||
(MVE_VMOV_to_lane_8 (v16i8 (IMPLICIT_DEF)), rGPR:$src, (i32 0))>;
|
||||
|
|
|
@ -376,49 +376,48 @@ define arm_aapcs_vfpcc <8 x i16> @shuffle3step_i16(<32 x i16> %src) {
|
|||
; CHECK-NEXT: vmov.16 q4[7], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[7]
|
||||
; CHECK-NEXT: vmov.16 q3[5], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[2]
|
||||
; CHECK-NEXT: vmov.f32 s15, s19
|
||||
; CHECK-NEXT: vmov.16 q4[0], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[5]
|
||||
; CHECK-NEXT: vmov.16 q4[1], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[0]
|
||||
; CHECK-NEXT: vmov.16 q4[2], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[3]
|
||||
; CHECK-NEXT: vmov.16 q4[3], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q2[4]
|
||||
; CHECK-NEXT: vmov.16 q6[6], r0
|
||||
; CHECK-NEXT: vmov.16 q5[6], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[2]
|
||||
; CHECK-NEXT: vmov.16 q6[0], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[5]
|
||||
; CHECK-NEXT: vmov.16 q6[1], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[0]
|
||||
; CHECK-NEXT: vmov.16 q6[2], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[3]
|
||||
; CHECK-NEXT: vmov.16 q6[3], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q2[7]
|
||||
; CHECK-NEXT: vmov.16 q6[7], r0
|
||||
; CHECK-NEXT: vmov.f32 s18, s7
|
||||
; CHECK-NEXT: vmov.f32 s26, s8
|
||||
; CHECK-NEXT: vmov q5, q6
|
||||
; CHECK-NEXT: vmov r1, s16
|
||||
; CHECK-NEXT: vmovnb.i32 q5, q4
|
||||
; CHECK-NEXT: vmov r0, s22
|
||||
; CHECK-NEXT: vmov q5[2], q5[0], r1, r0
|
||||
; CHECK-NEXT: vmov r0, s27
|
||||
; CHECK-NEXT: vmov r1, s17
|
||||
; CHECK-NEXT: vmov q5[3], q5[1], r1, r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q2[0]
|
||||
; CHECK-NEXT: vmov.16 q4[5], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[5]
|
||||
; CHECK-NEXT: vmovx.f16 s19, s9
|
||||
; CHECK-NEXT: vins.f16 s19, s11
|
||||
; CHECK-NEXT: vmov.16 q5[7], r0
|
||||
; CHECK-NEXT: vmov.f32 s26, s7
|
||||
; CHECK-NEXT: vmov.f32 s22, s8
|
||||
; CHECK-NEXT: vmov.f32 s15, s19
|
||||
; CHECK-NEXT: vmov q4, q5
|
||||
; CHECK-NEXT: vmovnb.i32 q4, q6
|
||||
; CHECK-NEXT: vmov r1, s24
|
||||
; CHECK-NEXT: vmov r0, s18
|
||||
; CHECK-NEXT: vmov q4[2], q4[0], r1, r0
|
||||
; CHECK-NEXT: vmov r0, s23
|
||||
; CHECK-NEXT: vins.f16 s22, s8
|
||||
; CHECK-NEXT: vmov r1, s25
|
||||
; CHECK-NEXT: vmovx.f16 s23, s9
|
||||
; CHECK-NEXT: vmov q4[3], q4[1], r1, r0
|
||||
; CHECK-NEXT: vins.f16 s23, s11
|
||||
; CHECK-NEXT: vmovx.f16 s8, s0
|
||||
; CHECK-NEXT: vins.f16 s8, s2
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[5]
|
||||
; CHECK-NEXT: vmovx.f16 s9, s3
|
||||
; CHECK-NEXT: vmov q0, q4
|
||||
; CHECK-NEXT: vmov q0, q5
|
||||
; CHECK-NEXT: vins.f16 s9, s5
|
||||
; CHECK-NEXT: vmov.16 q2[4], r0
|
||||
; CHECK-NEXT: vmovnb.i32 q0, q2
|
||||
; CHECK-NEXT: vmov r1, s8
|
||||
; CHECK-NEXT: vmov r0, s2
|
||||
; CHECK-NEXT: vmov q0[2], q0[0], r1, r0
|
||||
; CHECK-NEXT: vmov r0, s19
|
||||
; CHECK-NEXT: vmov r0, s23
|
||||
; CHECK-NEXT: vmov r1, s9
|
||||
; CHECK-NEXT: vmov q0[3], q0[1], r1, r0
|
||||
; CHECK-NEXT: vadd.i16 q0, q3, q0
|
||||
; CHECK-NEXT: vadd.i16 q0, q0, q5
|
||||
; CHECK-NEXT: vadd.i16 q0, q0, q4
|
||||
; CHECK-NEXT: vpop {d8, d9, d10, d11, d12, d13}
|
||||
; CHECK-NEXT: bx lr
|
||||
entry:
|
||||
|
|
|
@ -377,12 +377,11 @@ define void @vld3_v8i16(<24 x i16> *%src, <8 x i16> *%dst) {
|
|||
; CHECK-NEXT: vins.f16 s20, s10
|
||||
; CHECK-NEXT: vmovx.f16 s21, s11
|
||||
; CHECK-NEXT: vins.f16 s21, s5
|
||||
; CHECK-NEXT: vmov.16 q5[4], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[0]
|
||||
; CHECK-NEXT: vmov.16 q1[5], r0
|
||||
; CHECK-NEXT: vmov r2, s20
|
||||
; CHECK-NEXT: vins.f16 s6, s0
|
||||
; CHECK-NEXT: vmovx.f16 s7, s1
|
||||
; CHECK-NEXT: vmov.16 q5[4], r0
|
||||
; CHECK-NEXT: vins.f16 s7, s3
|
||||
; CHECK-NEXT: vmov r2, s20
|
||||
; CHECK-NEXT: vmov q0, q1
|
||||
; CHECK-NEXT: vmovnb.i32 q0, q5
|
||||
; CHECK-NEXT: vmov r0, s2
|
||||
|
@ -411,132 +410,130 @@ define void @vld3_v16i16(<48 x i16> *%src, <16 x i16> *%dst) {
|
|||
; CHECK: @ %bb.0: @ %entry
|
||||
; CHECK-NEXT: .vsave {d8, d9, d10, d11, d12, d13, d14, d15}
|
||||
; CHECK-NEXT: vpush {d8, d9, d10, d11, d12, d13, d14, d15}
|
||||
; CHECK-NEXT: vldrw.u32 q3, [r0, #48]
|
||||
; CHECK-NEXT: vldrw.u32 q2, [r0, #64]
|
||||
; CHECK-NEXT: vldrw.u32 q4, [r0, #80]
|
||||
; CHECK-NEXT: vldrw.u32 q0, [r0, #16]
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[0]
|
||||
; CHECK-NEXT: vmov.16 q1[0], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[3]
|
||||
; CHECK-NEXT: vmov.16 q1[1], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[6]
|
||||
; CHECK-NEXT: vmov.16 q1[2], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[1]
|
||||
; CHECK-NEXT: vmov.16 q1[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[4]
|
||||
; CHECK-NEXT: vmov.16 q1[4], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q4[2]
|
||||
; CHECK-NEXT: vmov.16 q5[6], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q4[5]
|
||||
; CHECK-NEXT: vmov.16 q5[7], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[7]
|
||||
; CHECK-NEXT: vmov.16 q1[5], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q4[4]
|
||||
; CHECK-NEXT: vmov.16 q6[6], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[2]
|
||||
; CHECK-NEXT: vmov.f32 s7, s23
|
||||
; CHECK-NEXT: vmov.16 q5[0], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[5]
|
||||
; CHECK-NEXT: vmov.16 q5[1], r2
|
||||
; CHECK-NEXT: vldrw.u32 q2, [r0, #48]
|
||||
; CHECK-NEXT: vldrw.u32 q0, [r0, #64]
|
||||
; CHECK-NEXT: vldrw.u32 q3, [r0, #80]
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[0]
|
||||
; CHECK-NEXT: vmov.16 q5[2], r2
|
||||
; CHECK-NEXT: vmov.16 q1[0], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[3]
|
||||
; CHECK-NEXT: vmov.16 q5[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q4[7]
|
||||
; CHECK-NEXT: vmov.16 q6[7], r2
|
||||
; CHECK-NEXT: vmov.f32 s22, s11
|
||||
; CHECK-NEXT: vmov.f32 s26, s16
|
||||
; CHECK-NEXT: vmov q7, q6
|
||||
; CHECK-NEXT: vmov r3, s20
|
||||
; CHECK-NEXT: vmovnb.i32 q7, q5
|
||||
; CHECK-NEXT: vmov r12, s27
|
||||
; CHECK-NEXT: vmov r2, s30
|
||||
; CHECK-NEXT: vmov q6[2], q6[0], r3, r2
|
||||
; CHECK-NEXT: vmov r2, s21
|
||||
; CHECK-NEXT: vmov q6[3], q6[1], r2, r12
|
||||
; CHECK-NEXT: vmov.u16 r2, q4[0]
|
||||
; CHECK-NEXT: vmov.16 q5[5], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[5]
|
||||
; CHECK-NEXT: vmovx.f16 s23, s17
|
||||
; CHECK-NEXT: vins.f16 s23, s19
|
||||
; CHECK-NEXT: vmovx.f16 s16, s12
|
||||
; CHECK-NEXT: vins.f16 s16, s14
|
||||
; CHECK-NEXT: vmovx.f16 s17, s15
|
||||
; CHECK-NEXT: vins.f16 s17, s9
|
||||
; CHECK-NEXT: vmov q2, q5
|
||||
; CHECK-NEXT: vmov.16 q4[4], r2
|
||||
; CHECK-NEXT: vmovnb.i32 q2, q4
|
||||
; CHECK-NEXT: vmov r3, s16
|
||||
; CHECK-NEXT: vmov r2, s10
|
||||
; CHECK-NEXT: vmov q2[2], q2[0], r3, r2
|
||||
; CHECK-NEXT: vmov r2, s23
|
||||
; CHECK-NEXT: vmov r3, s17
|
||||
; CHECK-NEXT: vldrw.u32 q5, [r0, #32]
|
||||
; CHECK-NEXT: vmov q2[3], q2[1], r3, r2
|
||||
; CHECK-NEXT: vadd.i16 q1, q1, q2
|
||||
; CHECK-NEXT: vldrw.u32 q2, [r0]
|
||||
; CHECK-NEXT: vmov.u16 r0, q5[4]
|
||||
; CHECK-NEXT: vadd.i16 q1, q1, q6
|
||||
; CHECK-NEXT: vmov.16 q1[1], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[6]
|
||||
; CHECK-NEXT: vmov.16 q1[2], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[1]
|
||||
; CHECK-NEXT: vmov.16 q1[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[4]
|
||||
; CHECK-NEXT: vmov.16 q1[4], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[2]
|
||||
; CHECK-NEXT: vmov.16 q4[6], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[5]
|
||||
; CHECK-NEXT: vmov.16 q4[7], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[7]
|
||||
; CHECK-NEXT: vmov.16 q1[5], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[4]
|
||||
; CHECK-NEXT: vmov.16 q5[6], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[2]
|
||||
; CHECK-NEXT: vmov.16 q6[6], r0
|
||||
; CHECK-NEXT: vmov.16 q6[0], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[5]
|
||||
; CHECK-NEXT: vmov.16 q6[1], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[0]
|
||||
; CHECK-NEXT: vmov.16 q6[2], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[3]
|
||||
; CHECK-NEXT: vmov.16 q6[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[7]
|
||||
; CHECK-NEXT: vmov.16 q5[7], r2
|
||||
; CHECK-NEXT: vmov.f32 s26, s3
|
||||
; CHECK-NEXT: vmov.f32 s22, s12
|
||||
; CHECK-NEXT: vmov.f32 s7, s19
|
||||
; CHECK-NEXT: vmov q4, q5
|
||||
; CHECK-NEXT: vmovnb.i32 q4, q6
|
||||
; CHECK-NEXT: vmov r3, s24
|
||||
; CHECK-NEXT: vmov r2, s18
|
||||
; CHECK-NEXT: vmov q4[2], q4[0], r3, r2
|
||||
; CHECK-NEXT: vmov r2, s23
|
||||
; CHECK-NEXT: vins.f16 s22, s12
|
||||
; CHECK-NEXT: vmov r3, s25
|
||||
; CHECK-NEXT: vmovx.f16 s23, s13
|
||||
; CHECK-NEXT: vmov q4[3], q4[1], r3, r2
|
||||
; CHECK-NEXT: vins.f16 s23, s15
|
||||
; CHECK-NEXT: vmovx.f16 s12, s8
|
||||
; CHECK-NEXT: vins.f16 s12, s10
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[5]
|
||||
; CHECK-NEXT: vmovx.f16 s13, s11
|
||||
; CHECK-NEXT: vldrw.u32 q2, [r0]
|
||||
; CHECK-NEXT: vins.f16 s13, s1
|
||||
; CHECK-NEXT: vmov q0, q5
|
||||
; CHECK-NEXT: vmov.16 q3[4], r2
|
||||
; CHECK-NEXT: vmovnb.i32 q0, q3
|
||||
; CHECK-NEXT: vmov r3, s12
|
||||
; CHECK-NEXT: vmov r2, s2
|
||||
; CHECK-NEXT: vmov q0[2], q0[0], r3, r2
|
||||
; CHECK-NEXT: vmov r2, s23
|
||||
; CHECK-NEXT: vmov r3, s13
|
||||
; CHECK-NEXT: vldrw.u32 q5, [r0, #32]
|
||||
; CHECK-NEXT: vmov q0[3], q0[1], r3, r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[2]
|
||||
; CHECK-NEXT: vadd.i16 q0, q1, q0
|
||||
; CHECK-NEXT: vldrw.u32 q1, [r0, #16]
|
||||
; CHECK-NEXT: vmov.16 q3[0], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[5]
|
||||
; CHECK-NEXT: vmov.u16 r0, q5[4]
|
||||
; CHECK-NEXT: vmov.16 q3[1], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[0]
|
||||
; CHECK-NEXT: vmov.u16 r2, q1[0]
|
||||
; CHECK-NEXT: vmov.16 q6[6], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q5[7]
|
||||
; CHECK-NEXT: vmov.16 q3[2], r2
|
||||
; CHECK-NEXT: vmov.16 q6[7], r0
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[3]
|
||||
; CHECK-NEXT: vmov.u16 r2, q1[3]
|
||||
; CHECK-NEXT: vmov.16 q3[3], r2
|
||||
; CHECK-NEXT: vmov.f32 s26, s20
|
||||
; CHECK-NEXT: vmov.f32 s14, s3
|
||||
; CHECK-NEXT: vadd.i16 q0, q0, q4
|
||||
; CHECK-NEXT: vmov.f32 s14, s7
|
||||
; CHECK-NEXT: vmov q4, q6
|
||||
; CHECK-NEXT: vmovnb.i32 q4, q3
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[0]
|
||||
; CHECK-NEXT: vmovnb.i32 q4, q3
|
||||
; CHECK-NEXT: vmov r3, s27
|
||||
; CHECK-NEXT: vmov r0, s18
|
||||
; CHECK-NEXT: vmov.16 q4[0], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[3]
|
||||
; CHECK-NEXT: vmov r3, s27
|
||||
; CHECK-NEXT: vstrw.32 q0, [r1, #16]
|
||||
; CHECK-NEXT: vmov.16 q4[1], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[6]
|
||||
; CHECK-NEXT: vmov.16 q4[2], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[1]
|
||||
; CHECK-NEXT: vmov.u16 r2, q1[1]
|
||||
; CHECK-NEXT: vmov.16 q4[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[4]
|
||||
; CHECK-NEXT: vmov.u16 r2, q1[4]
|
||||
; CHECK-NEXT: vmov.16 q4[4], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q5[2]
|
||||
; CHECK-NEXT: vmov.16 q7[6], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q5[5]
|
||||
; CHECK-NEXT: vmov.16 q7[7], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[7]
|
||||
; CHECK-NEXT: vmov.u16 r2, q1[7]
|
||||
; CHECK-NEXT: vmov.16 q4[5], r2
|
||||
; CHECK-NEXT: vmov r2, s12
|
||||
; CHECK-NEXT: vmov q6[2], q6[0], r2, r0
|
||||
; CHECK-NEXT: vmov r0, s13
|
||||
; CHECK-NEXT: vins.f16 s14, s20
|
||||
; CHECK-NEXT: vmov q6[3], q6[1], r0, r3
|
||||
; CHECK-NEXT: vmov.u16 r0, q5[0]
|
||||
; CHECK-NEXT: vmov.16 q3[5], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[5]
|
||||
; CHECK-NEXT: vmovx.f16 s15, s21
|
||||
; CHECK-NEXT: vmov.f32 s19, s31
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[5]
|
||||
; CHECK-NEXT: vins.f16 s15, s23
|
||||
; CHECK-NEXT: vmovx.f16 s20, s8
|
||||
; CHECK-NEXT: vins.f16 s20, s10
|
||||
; CHECK-NEXT: vstrw.32 q1, [r1, #16]
|
||||
; CHECK-NEXT: vmov.f32 s19, s31
|
||||
; CHECK-NEXT: vmovx.f16 s21, s11
|
||||
; CHECK-NEXT: vins.f16 s21, s1
|
||||
; CHECK-NEXT: vmov q0, q3
|
||||
; CHECK-NEXT: vins.f16 s21, s5
|
||||
; CHECK-NEXT: vmov q1, q3
|
||||
; CHECK-NEXT: vmov.16 q5[4], r0
|
||||
; CHECK-NEXT: vmovnb.i32 q0, q5
|
||||
; CHECK-NEXT: vmovnb.i32 q1, q5
|
||||
; CHECK-NEXT: vmov r2, s20
|
||||
; CHECK-NEXT: vmov r0, s2
|
||||
; CHECK-NEXT: vmov q0[2], q0[0], r2, r0
|
||||
; CHECK-NEXT: vmov r0, s6
|
||||
; CHECK-NEXT: vmov q1[2], q1[0], r2, r0
|
||||
; CHECK-NEXT: vmov r0, s15
|
||||
; CHECK-NEXT: vmov r2, s21
|
||||
; CHECK-NEXT: vmov q0[3], q0[1], r2, r0
|
||||
; CHECK-NEXT: vadd.i16 q0, q4, q0
|
||||
; CHECK-NEXT: vadd.i16 q0, q0, q6
|
||||
; CHECK-NEXT: vstrw.32 q0, [r1]
|
||||
; CHECK-NEXT: vmov q1[3], q1[1], r2, r0
|
||||
; CHECK-NEXT: vadd.i16 q1, q4, q1
|
||||
; CHECK-NEXT: vadd.i16 q1, q1, q6
|
||||
; CHECK-NEXT: vstrw.32 q1, [r1]
|
||||
; CHECK-NEXT: vpop {d8, d9, d10, d11, d12, d13, d14, d15}
|
||||
; CHECK-NEXT: bx lr
|
||||
entry:
|
||||
|
@ -647,8 +644,6 @@ define void @vld3_v8i8(<24 x i8> *%src, <8 x i8> *%dst) {
|
|||
; CHECK-NEXT: vmov.16 q2[3], r0
|
||||
; CHECK-NEXT: vmov.u8 r0, q1[13]
|
||||
; CHECK-NEXT: vmov.16 q2[4], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[0]
|
||||
; CHECK-NEXT: vmov.16 q2[5], r0
|
||||
; CHECK-NEXT: vmov.u8 r0, q1[0]
|
||||
; CHECK-NEXT: vmov.16 q3[0], r0
|
||||
; CHECK-NEXT: vmov.u8 r0, q1[3]
|
||||
|
@ -660,13 +655,14 @@ define void @vld3_v8i8(<24 x i8> *%src, <8 x i8> *%dst) {
|
|||
; CHECK-NEXT: vmov.u8 r0, q1[12]
|
||||
; CHECK-NEXT: vmov.16 q3[4], r0
|
||||
; CHECK-NEXT: vmov.u8 r0, q1[15]
|
||||
; CHECK-NEXT: vins.f16 s10, s0
|
||||
; CHECK-NEXT: vmov.16 q3[5], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[2]
|
||||
; CHECK-NEXT: vmovx.f16 s11, s1
|
||||
; CHECK-NEXT: vmov.16 q3[6], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[5]
|
||||
; CHECK-NEXT: vins.f16 s11, s3
|
||||
; CHECK-NEXT: vmov.16 q3[7], r0
|
||||
; CHECK-NEXT: vins.f16 s11, s3
|
||||
; CHECK-NEXT: vmov.u8 r0, q1[2]
|
||||
; CHECK-NEXT: vadd.i16 q2, q3, q2
|
||||
; CHECK-NEXT: vmov.16 q3[0], r0
|
||||
|
|
|
@ -416,15 +416,14 @@ define void @vst3_v8i16(<8 x i16> *%src, <24 x i16> *%dst) {
|
|||
; CHECK-NEXT: vmov.16 q5[0], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q3[5]
|
||||
; CHECK-NEXT: vmov.16 q5[1], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q2[6]
|
||||
; CHECK-NEXT: vmov.16 q5[3], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q2[7]
|
||||
; CHECK-NEXT: vins.f16 s21, s11
|
||||
; CHECK-NEXT: vmov.f32 s17, s25
|
||||
; CHECK-NEXT: vmov.16 q5[6], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q3[7]
|
||||
; CHECK-NEXT: vmov r2, s7
|
||||
; CHECK-NEXT: vmov.f32 s18, s26
|
||||
; CHECK-NEXT: vmov.16 q5[7], r0
|
||||
; CHECK-NEXT: vmov.f32 s18, s26
|
||||
; CHECK-NEXT: vdup.32 q6, r2
|
||||
; CHECK-NEXT: vmov.f32 s22, s15
|
||||
; CHECK-NEXT: vmov.u16 r2, q6[2]
|
||||
|
@ -442,16 +441,16 @@ define void @vst3_v8i16(<8 x i16> *%src, <24 x i16> *%dst) {
|
|||
; CHECK-NEXT: vmov.u16 r0, q2[5]
|
||||
; CHECK-NEXT: vmov.16 q2[2], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[3]
|
||||
; CHECK-NEXT: vmov.f32 s21, s29
|
||||
; CHECK-NEXT: vmov.16 q2[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[4]
|
||||
; CHECK-NEXT: vmov.16 q2[4], r2
|
||||
; CHECK-NEXT: vmov.f32 s22, s30
|
||||
; CHECK-NEXT: vmov.f32 s21, s29
|
||||
; CHECK-NEXT: vmov.16 q2[5], r0
|
||||
; CHECK-NEXT: vstrw.32 q5, [r1, #32]
|
||||
; CHECK-NEXT: vmov.f32 s22, s30
|
||||
; CHECK-NEXT: vmov.f32 s1, s9
|
||||
; CHECK-NEXT: vstrw.32 q4, [r1]
|
||||
; CHECK-NEXT: vstrw.32 q5, [r1, #32]
|
||||
; CHECK-NEXT: vmov.f32 s2, s10
|
||||
; CHECK-NEXT: vstrw.32 q4, [r1]
|
||||
; CHECK-NEXT: vstrw.32 q0, [r1, #16]
|
||||
; CHECK-NEXT: vpop {d8, d9, d10, d11, d12, d13, d14, d15}
|
||||
; CHECK-NEXT: bx lr
|
||||
|
@ -476,174 +475,172 @@ define void @vst3_v16i16(<16 x i16> *%src, <48 x i16> *%dst) {
|
|||
; CHECK-NEXT: vpush {d8, d9, d10, d11, d12, d13, d14, d15}
|
||||
; CHECK-NEXT: .pad #160
|
||||
; CHECK-NEXT: sub sp, #160
|
||||
; CHECK-NEXT: vldrw.u32 q0, [r0, #16]
|
||||
; CHECK-NEXT: vldrw.u32 q7, [r0, #48]
|
||||
; CHECK-NEXT: vldrw.u32 q1, [r0, #32]
|
||||
; CHECK-NEXT: vmov.f64 d4, d0
|
||||
; CHECK-NEXT: vmov.u16 r2, q7[1]
|
||||
; CHECK-NEXT: vstrw.32 q0, [sp, #128] @ 16-byte Spill
|
||||
; CHECK-NEXT: vstrw.32 q1, [sp, #16] @ 16-byte Spill
|
||||
; CHECK-NEXT: vins.f16 s8, s28
|
||||
; CHECK-NEXT: vldrw.u32 q1, [r0, #16]
|
||||
; CHECK-NEXT: vldrw.u32 q0, [r0, #48]
|
||||
; CHECK-NEXT: vmov.f64 d4, d2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[1]
|
||||
; CHECK-NEXT: vmov q6, q0
|
||||
; CHECK-NEXT: vstrw.32 q1, [sp, #128] @ 16-byte Spill
|
||||
; CHECK-NEXT: vstrw.32 q6, [sp, #32] @ 16-byte Spill
|
||||
; CHECK-NEXT: vins.f16 s8, s0
|
||||
; CHECK-NEXT: vmov.16 q2[4], r2
|
||||
; CHECK-NEXT: vmov.f32 s11, s1
|
||||
; CHECK-NEXT: vins.f16 s11, s29
|
||||
; CHECK-NEXT: vmov q4, q2
|
||||
; CHECK-NEXT: vmov.f32 s17, s0
|
||||
; CHECK-NEXT: vmov.f32 s11, s5
|
||||
; CHECK-NEXT: vins.f16 s11, s1
|
||||
; CHECK-NEXT: vldrw.u32 q0, [r0, #80]
|
||||
; CHECK-NEXT: vmov.u16 r2, q4[3]
|
||||
; CHECK-NEXT: vstrw.32 q4, [sp, #80] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.f32 s9, s4
|
||||
; CHECK-NEXT: vmov r3, s0
|
||||
; CHECK-NEXT: vmov q2, q0
|
||||
; CHECK-NEXT: vmov q1, q0
|
||||
; CHECK-NEXT: vdup.32 q0, r3
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[3]
|
||||
; CHECK-NEXT: vmov.u16 r3, q0[2]
|
||||
; CHECK-NEXT: vmov.16 q3[2], r3
|
||||
; CHECK-NEXT: vmov.16 q3[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q4[4]
|
||||
; CHECK-NEXT: vmov.16 q3[4], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[5]
|
||||
; CHECK-NEXT: vldrw.u32 q0, [r0]
|
||||
; CHECK-NEXT: vmov.16 q3[5], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q1[1]
|
||||
; CHECK-NEXT: vstrw.32 q3, [sp, #96] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.f64 d12, d0
|
||||
; CHECK-NEXT: vstrw.32 q0, [sp, #144] @ 16-byte Spill
|
||||
; CHECK-NEXT: vins.f16 s24, s4
|
||||
; CHECK-NEXT: vmov.16 q6[4], r2
|
||||
; CHECK-NEXT: vmov.f32 s27, s1
|
||||
; CHECK-NEXT: vins.f16 s27, s5
|
||||
; CHECK-NEXT: vmov.f32 s25, s0
|
||||
; CHECK-NEXT: vldrw.u32 q0, [r0, #64]
|
||||
; CHECK-NEXT: vmov.u16 r2, q6[3]
|
||||
; CHECK-NEXT: vmov r0, s0
|
||||
; CHECK-NEXT: vmov q5, q0
|
||||
; CHECK-NEXT: vdup.32 q0, r0
|
||||
; CHECK-NEXT: vstrw.32 q5, [sp, #112] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[2]
|
||||
; CHECK-NEXT: vmov.16 q3[2], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q6[4]
|
||||
; CHECK-NEXT: vmov.16 q3[3], r2
|
||||
; CHECK-NEXT: vmov.16 q3[4], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[5]
|
||||
; CHECK-NEXT: vmov.16 q3[5], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[5]
|
||||
; CHECK-NEXT: vmov.16 q4[0], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q5[5]
|
||||
; CHECK-NEXT: vldrw.u32 q0, [sp, #144] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.16 q4[1], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[6]
|
||||
; CHECK-NEXT: vstrw.32 q3, [sp, #64] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.16 q4[3], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[7]
|
||||
; CHECK-NEXT: vmov r2, s3
|
||||
; CHECK-NEXT: vmov.16 q4[6], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q5[7]
|
||||
; CHECK-NEXT: vdup.32 q0, r2
|
||||
; CHECK-NEXT: vmov.16 q4[7], r0
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[2]
|
||||
; CHECK-NEXT: vmov.f32 s18, s23
|
||||
; CHECK-NEXT: vmov.16 q1[2], r2
|
||||
; CHECK-NEXT: vmov.u16 r0, q4[3]
|
||||
; CHECK-NEXT: vmov q3, q2
|
||||
; CHECK-NEXT: vmov.16 q1[3], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q4[4]
|
||||
; CHECK-NEXT: vmov.16 q1[4], r0
|
||||
; CHECK-NEXT: vstrw.32 q2, [sp, #96] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.16 q2[2], r3
|
||||
; CHECK-NEXT: vmov.16 q2[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[4]
|
||||
; CHECK-NEXT: vldrw.u32 q3, [r0, #32]
|
||||
; CHECK-NEXT: vmov.16 q2[4], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[5]
|
||||
; CHECK-NEXT: vldrw.u32 q0, [r0, #64]
|
||||
; CHECK-NEXT: vmov.16 q2[5], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[5]
|
||||
; CHECK-NEXT: vmov.16 q5[0], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[5]
|
||||
; CHECK-NEXT: vmov.16 q5[1], r2
|
||||
; CHECK-NEXT: vstrw.32 q2, [sp, #112] @ 16-byte Spill
|
||||
; CHECK-NEXT: vldrw.u32 q2, [r0]
|
||||
; CHECK-NEXT: vins.f16 s21, s15
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[7]
|
||||
; CHECK-NEXT: vstrw.32 q0, [sp, #144] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.16 q5[6], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[7]
|
||||
; CHECK-NEXT: vmov.16 q5[7], r2
|
||||
; CHECK-NEXT: vmov r0, s11
|
||||
; CHECK-NEXT: vmov.f32 s22, s3
|
||||
; CHECK-NEXT: vdup.32 q0, r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[2]
|
||||
; CHECK-NEXT: vmov.u16 r2, q5[3]
|
||||
; CHECK-NEXT: vmov.16 q4[2], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q5[4]
|
||||
; CHECK-NEXT: vmov.16 q4[3], r2
|
||||
; CHECK-NEXT: vstrw.32 q2, [sp, #48] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.16 q4[4], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[5]
|
||||
; CHECK-NEXT: vmov.16 q1[5], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q7[5]
|
||||
; CHECK-NEXT: vstrw.32 q1, [sp, #48] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.16 q1[0], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q2[5]
|
||||
; CHECK-NEXT: vmov q0, q2
|
||||
; CHECK-NEXT: vmov.16 q4[5], r0
|
||||
; CHECK-NEXT: vmov.f64 d14, d0
|
||||
; CHECK-NEXT: vmov.u16 r0, q3[1]
|
||||
; CHECK-NEXT: vstrw.32 q4, [sp, #80] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov q4, q1
|
||||
; CHECK-NEXT: vstrw.32 q4, [sp, #16] @ 16-byte Spill
|
||||
; CHECK-NEXT: vins.f16 s28, s12
|
||||
; CHECK-NEXT: vmov.16 q7[4], r0
|
||||
; CHECK-NEXT: vmov.f32 s31, s1
|
||||
; CHECK-NEXT: vins.f16 s31, s13
|
||||
; CHECK-NEXT: vrev32.16 q3, q3
|
||||
; CHECK-NEXT: vmov.f32 s29, s0
|
||||
; CHECK-NEXT: vldrw.u32 q0, [sp, #144] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.u16 r0, q7[3]
|
||||
; CHECK-NEXT: vstrw.32 q3, [sp] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.16 q1[1], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q7[6]
|
||||
; CHECK-NEXT: vmov.16 q1[3], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q7[7]
|
||||
; CHECK-NEXT: vmov.16 q1[6], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q2[7]
|
||||
; CHECK-NEXT: vldrw.u32 q2, [sp, #128] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.16 q1[7], r0
|
||||
; CHECK-NEXT: vmov.f32 s6, s15
|
||||
; CHECK-NEXT: vmov r2, s11
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[3]
|
||||
; CHECK-NEXT: vmov r2, s0
|
||||
; CHECK-NEXT: vdup.32 q0, r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[2]
|
||||
; CHECK-NEXT: vmov.16 q5[2], r2
|
||||
; CHECK-NEXT: vmov.16 q5[3], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[4]
|
||||
; CHECK-NEXT: vmov.16 q5[4], r0
|
||||
; CHECK-NEXT: vmov.16 q2[2], r2
|
||||
; CHECK-NEXT: vmov.16 q2[3], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q7[4]
|
||||
; CHECK-NEXT: vmov.16 q2[4], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[5]
|
||||
; CHECK-NEXT: vmov.16 q5[5], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q3[2]
|
||||
; CHECK-NEXT: vrev32.16 q0, q7
|
||||
; CHECK-NEXT: vmov.16 q7[0], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q2[3]
|
||||
; CHECK-NEXT: vstrw.32 q0, [sp, #32] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.16 q7[1], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q3[4]
|
||||
; CHECK-NEXT: vldrw.u32 q0, [sp, #16] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.16 q7[6], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q2[5]
|
||||
; CHECK-NEXT: vldrw.u32 q2, [sp, #112] @ 16-byte Reload
|
||||
; CHECK-NEXT: vldrw.u32 q3, [sp, #144] @ 16-byte Reload
|
||||
; CHECK-NEXT: vrev32.16 q0, q0
|
||||
; CHECK-NEXT: vmov.16 q7[7], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q2[2]
|
||||
; CHECK-NEXT: vstrw.32 q0, [sp, #16] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.16 q2[5], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q6[5]
|
||||
; CHECK-NEXT: vmov.16 q0[0], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q3[3]
|
||||
; CHECK-NEXT: vmov.f32 s5, s21
|
||||
; CHECK-NEXT: vmov.16 q0[1], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q2[4]
|
||||
; CHECK-NEXT: vldrw.u32 q2, [sp, #64] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.16 q0[6], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q3[5]
|
||||
; CHECK-NEXT: vldrw.u32 q3, [sp, #80] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.f32 s25, s9
|
||||
; CHECK-NEXT: vmov.16 q0[7], r0
|
||||
; CHECK-NEXT: vmov.f32 s26, s10
|
||||
; CHECK-NEXT: vldrw.u32 q2, [sp, #96] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.f32 s6, s22
|
||||
; CHECK-NEXT: vstrw.32 q6, [r1]
|
||||
; CHECK-NEXT: vmov.f32 s13, s9
|
||||
; CHECK-NEXT: vstrw.32 q1, [r1, #80]
|
||||
; CHECK-NEXT: vmov.f32 s14, s10
|
||||
; CHECK-NEXT: vldrw.u32 q2, [sp, #48] @ 16-byte Reload
|
||||
; CHECK-NEXT: vldrw.u32 q1, [sp, #16] @ 16-byte Reload
|
||||
; CHECK-NEXT: vstrw.32 q3, [r1, #48]
|
||||
; CHECK-NEXT: vmov.f32 s17, s9
|
||||
; CHECK-NEXT: vmov.f32 s18, s10
|
||||
; CHECK-NEXT: vldrw.u32 q2, [sp, #112] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.u16 r2, q1[2]
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[5]
|
||||
; CHECK-NEXT: vmov.f32 s1, s9
|
||||
; CHECK-NEXT: vldrw.u32 q2, [sp, #144] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.16 q1[2], r2
|
||||
; CHECK-NEXT: vstrw.32 q4, [r1, #32]
|
||||
; CHECK-NEXT: vmov.f32 s2, s10
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[3]
|
||||
; CHECK-NEXT: vmov.16 q1[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[4]
|
||||
; CHECK-NEXT: vmov.16 q1[4], r2
|
||||
; CHECK-NEXT: vmov.16 q1[5], r0
|
||||
; CHECK-NEXT: vmov.f32 s1, s5
|
||||
; CHECK-NEXT: vmov.f32 s2, s6
|
||||
; CHECK-NEXT: vldrw.u32 q1, [sp] @ 16-byte Reload
|
||||
; CHECK-NEXT: vstrw.32 q0, [r1, #16]
|
||||
; CHECK-NEXT: vldrw.u32 q0, [sp, #32] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.f32 s29, s5
|
||||
; CHECK-NEXT: vmov.16 q0[1], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q6[7]
|
||||
; CHECK-NEXT: vins.f16 s1, s27
|
||||
; CHECK-NEXT: vstrw.32 q2, [sp, #64] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.16 q0[6], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[7]
|
||||
; CHECK-NEXT: vldrw.u32 q1, [sp, #128] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.16 q0[7], r0
|
||||
; CHECK-NEXT: vmov.f32 s2, s19
|
||||
; CHECK-NEXT: vmov r2, s7
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[3]
|
||||
; CHECK-NEXT: vdup.32 q6, r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q6[2]
|
||||
; CHECK-NEXT: vmov.16 q2[2], r2
|
||||
; CHECK-NEXT: vmov.16 q2[3], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[4]
|
||||
; CHECK-NEXT: vmov.16 q2[4], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q6[5]
|
||||
; CHECK-NEXT: vmov.16 q2[5], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q4[2]
|
||||
; CHECK-NEXT: vmov.16 q3[0], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[3]
|
||||
; CHECK-NEXT: vmov.16 q3[1], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q4[4]
|
||||
; CHECK-NEXT: vldrw.u32 q6, [sp, #32] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.16 q3[6], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[5]
|
||||
; CHECK-NEXT: vldrw.u32 q1, [sp, #144] @ 16-byte Reload
|
||||
; CHECK-NEXT: vldrw.u32 q4, [sp, #48] @ 16-byte Reload
|
||||
; CHECK-NEXT: vrev32.16 q6, q6
|
||||
; CHECK-NEXT: vmov.16 q3[7], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[2]
|
||||
; CHECK-NEXT: vstrw.32 q6, [sp, #32] @ 16-byte Spill
|
||||
; CHECK-NEXT: vmov.16 q6[0], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q4[3]
|
||||
; CHECK-NEXT: vmov.f32 s1, s9
|
||||
; CHECK-NEXT: vmov.16 q6[1], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q1[4]
|
||||
; CHECK-NEXT: vldrw.u32 q1, [sp, #64] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.f32 s2, s10
|
||||
; CHECK-NEXT: vldrw.u32 q2, [sp, #96] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.16 q6[6], r0
|
||||
; CHECK-NEXT: vmov.f32 s29, s5
|
||||
; CHECK-NEXT: vmov.u16 r0, q4[5]
|
||||
; CHECK-NEXT: vmov.f32 s30, s6
|
||||
; CHECK-NEXT: vldrw.u32 q1, [sp, #80] @ 16-byte Reload
|
||||
; CHECK-NEXT: vstrw.32 q0, [r1, #80]
|
||||
; CHECK-NEXT: vldrw.u32 q0, [sp] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.f32 s21, s5
|
||||
; CHECK-NEXT: vmov.16 q6[7], r0
|
||||
; CHECK-NEXT: vmov.f32 s22, s6
|
||||
; CHECK-NEXT: vldrw.u32 q1, [sp, #112] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[2]
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[5]
|
||||
; CHECK-NEXT: vmov.f32 s30, s6
|
||||
; CHECK-NEXT: vmov.f32 s9, s5
|
||||
; CHECK-NEXT: vmov.16 q0[2], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q7[3]
|
||||
; CHECK-NEXT: vmov.f32 s10, s6
|
||||
; CHECK-NEXT: vldrw.u32 q1, [sp, #144] @ 16-byte Reload
|
||||
; CHECK-NEXT: vstrw.32 q5, [r1, #32]
|
||||
; CHECK-NEXT: vstrw.32 q2, [r1, #48]
|
||||
; CHECK-NEXT: vmov.f32 s25, s5
|
||||
; CHECK-NEXT: vldrw.u32 q1, [sp, #16] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.f32 s26, s18
|
||||
; CHECK-NEXT: vstrw.32 q7, [r1]
|
||||
; CHECK-NEXT: vmov.u16 r2, q6[3]
|
||||
; CHECK-NEXT: vmov.f32 s13, s5
|
||||
; CHECK-NEXT: vmov.16 q0[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q7[4]
|
||||
; CHECK-NEXT: vmov.u16 r2, q6[4]
|
||||
; CHECK-NEXT: vmov.16 q0[4], r2
|
||||
; CHECK-NEXT: vldrw.u32 q1, [sp, #128] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.16 q0[5], r0
|
||||
; CHECK-NEXT: vmov.f32 s25, s1
|
||||
; CHECK-NEXT: vmov.f32 s26, s2
|
||||
; CHECK-NEXT: vldrw.u32 q0, [sp, #32] @ 16-byte Reload
|
||||
; CHECK-NEXT: vmov.f32 s14, s6
|
||||
; CHECK-NEXT: vstrw.32 q6, [r1, #16]
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[2]
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[5]
|
||||
; CHECK-NEXT: vmov.16 q0[2], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[3]
|
||||
; CHECK-NEXT: vmov.16 q0[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q3[4]
|
||||
; CHECK-NEXT: vmov.16 q0[4], r2
|
||||
; CHECK-NEXT: vmov.16 q0[5], r0
|
||||
; CHECK-NEXT: vmov.f32 s29, s1
|
||||
; CHECK-NEXT: vmov.f32 s30, s2
|
||||
; CHECK-NEXT: vstrw.32 q7, [r1, #64]
|
||||
; CHECK-NEXT: vmov.f32 s13, s1
|
||||
; CHECK-NEXT: vmov.f32 s14, s2
|
||||
; CHECK-NEXT: vstrw.32 q3, [r1, #64]
|
||||
; CHECK-NEXT: add sp, #160
|
||||
; CHECK-NEXT: vpop {d8, d9, d10, d11, d12, d13, d14, d15}
|
||||
; CHECK-NEXT: bx lr
|
||||
|
@ -775,20 +772,19 @@ define void @vst3_v8i8(<8 x i8> *%src, <24 x i8> *%dst) {
|
|||
; CHECK-NEXT: vmov.16 q0[0], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[5]
|
||||
; CHECK-NEXT: vmov.16 q0[1], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q1[6]
|
||||
; CHECK-NEXT: vmov.16 q0[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q1[7]
|
||||
; CHECK-NEXT: vins.f16 s1, s7
|
||||
; CHECK-NEXT: vmov r0, s15
|
||||
; CHECK-NEXT: vmov.16 q0[6], r2
|
||||
; CHECK-NEXT: vmov.u16 r2, q2[7]
|
||||
; CHECK-NEXT: vmov r0, s15
|
||||
; CHECK-NEXT: vmov.16 q0[7], r2
|
||||
; CHECK-NEXT: vdup.32 q4, r0
|
||||
; CHECK-NEXT: vmov.f32 s2, s11
|
||||
; CHECK-NEXT: vmov.u16 r0, q4[2]
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[3]
|
||||
; CHECK-NEXT: vmov.16 q5[2], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[4]
|
||||
; CHECK-NEXT: vmov.u16 r2, q0[3]
|
||||
; CHECK-NEXT: vmov.16 q5[3], r2
|
||||
; CHECK-NEXT: vmov.u16 r0, q0[4]
|
||||
; CHECK-NEXT: vmov.16 q5[4], r0
|
||||
; CHECK-NEXT: vmov.u16 r0, q4[5]
|
||||
; CHECK-NEXT: vmov.16 q5[5], r0
|
||||
|
|
Loading…
Reference in New Issue