vadd.xlane.8x128.bf16
|
trf0 / trf1, v[0..63]
|
vadd.xlane.8x128.f32
|
trf0 / trf1, v[0..63]
|
vbcast.lane.8x128
|
trf0 / trf1, v[0..63], s[0..31] / u20
|
vbcast.lane.packed.8x128
|
trf0 / trf1, v[0..63], s[0..31] / u20
|
vbcast.lane.packed.b8.8x128
|
v[0..63], s[0..31] / u20
|
vlgmr
|
gmr0 / gmr1, msra0 / msra1
gmr0 / gmr1, msrb0 / msrb1
|
vllmr
|
lmr0 / lmr1, msra0 / msra1
lmr0 / lmr1, msrb0 / msrb1
|
vmatmul.8x128.bf16
|
mrf0 / mrf1, v[0..63]
|
vmatmul.8x128.bf16.lgmr
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), v[0..63]
|
vmatmul.8x128.bf16.lgmr.msk
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), vm[0..15], v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), vm[0..15], v[0..63]
|
vmatmul.8x128.bf16.msk
|
mrf0 / mrf1, vm[0..15], v[0..63]
|
vmatmul.8x128.bf8.bf16
|
mrf0 / mrf1, v[0..63]
|
vmatmul.8x128.bf8.bf16.lgmr
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), v[0..63]
|
vmatmul.8x128.bf8.bf16.lgmr.msk
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), vm[0..15], v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), vm[0..15], v[0..63]
|
vmatmul.8x128.bf8.bf16.msk
|
mrf0 / mrf1, vm[0..15], v[0..63]
|
vmatmul.8x128.f32
|
mrf0 / mrf1, v[0..63]
|
vmatmul.8x128.f32.lgmr
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), v[0..63]
|
vmatmul.8x128.f32.lgmr.msk
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), vm[0..15], v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), vm[0..15], v[0..63]
|
vmatmul.8x128.f32.msk
|
mrf0 / mrf1, vm[0..15], v[0..63]
|
vmatmul.8x128.if8.bf16
|
mrf0 / mrf1, v[0..63]
|
vmatmul.8x128.if8.bf16.lgmr
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), v[0..63]
|
vmatmul.8x128.if8.bf16.lgmr.msk
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), vm[0..15], v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), vm[0..15], v[0..63]
|
vmatmul.8x128.if8.bf16.msk
|
mrf0 / mrf1, vm[0..15], v[0..63]
|
vmatmul.8x128.s4
|
mrf0 / mrf1, v[0..63]
|
vmatmul.8x128.s4.lgmr
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), v[0..63]
|
vmatmul.8x128.s4.lgmr.msk
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), vm[0..15], v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), vm[0..15], v[0..63]
|
vmatmul.8x128.s4.msk
|
mrf0 / mrf1, vm[0..15], v[0..63]
|
vmatmul.8x128.s8
|
mrf0 / mrf1, v[0..63]
|
vmatmul.8x128.s8.lgmr
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), v[0..63]
|
vmatmul.8x128.s8.lgmr.msk
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), vm[0..15], v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), vm[0..15], v[0..63]
|
vmatmul.8x128.s8.msk
|
mrf0 / mrf1, vm[0..15], v[0..63]
|
vmatmul.8x128.u4
|
mrf0 / mrf1, v[0..63]
|
vmatmul.8x128.u4.lgmr
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), v[0..63]
|
vmatmul.8x128.u4.lgmr.msk
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), vm[0..15], v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), vm[0..15], v[0..63]
|
vmatmul.8x128.u4.msk
|
mrf0 / mrf1, vm[0..15], v[0..63]
|
vmatmul.8x128.u8
|
mrf0 / mrf1, v[0..63]
|
vmatmul.8x128.u8.lgmr
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), v[0..63]
|
vmatmul.8x128.u8.lgmr.msk
|
(mrf0, gmr0, msra0) / (mrf1, gmr1, msra1), vm[0..15], v[0..63]
(mrf0, gmr0, msrb0) / (mrf1, gmr1, msrb1), vm[0..15], v[0..63]
|
vmatmul.8x128.u8.msk
|
mrf0 / mrf1, vm[0..15], v[0..63]
|
vmatmul.lmr.104
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.104.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.112
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.112.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.120
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.120.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.128
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.128.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.16
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.16.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.24
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.24.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.32
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.32.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.40
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.40.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.48
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.48.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.56
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.56.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.64
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.64.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.72
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.72.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.8
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.8.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.80
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.80.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.88
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.88.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmul.lmr.96
|
(mrf0, lmr0) / (mrf1, lmr1)
|
vmatmul.lmr.96.lgmr
|
(mrf0, lmr0, gmr0, msra0) / (mrf1, lmr1, gmr1, msra1)
(mrf0, lmr0, gmr0, msrb0) / (mrf1, lmr1, gmr1, msrb1)
|
vmatmulprep
|
mubr0 / mubr1, v[0..63]
|
vmatmulprep.b16.msk
|
mubr0 / mubr1, vm[0..15], v[0..63]
|
vmatmulprep.b32.msk
|
mubr0 / mubr1, vm[0..15], v[0..63]
|
vmatmulprep.b8.msk
|
mubr0 / mubr1, vm[0..15], v[0..63]
|
vmatpush1.8x128.bf16
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.bf16.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.bf16.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.bf16.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.bf8.bf16
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.bf8.bf16.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.bf8.bf16.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.bf8.bf16.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.f32
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.f32.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.f32.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.f32.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.if8.bf16
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.if8.bf16.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.if8.bf16.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.if8.bf16.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.s4
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.s4.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.s4.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.s4.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.s8
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.s8.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.s8.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.s8.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.u4
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.u4.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.u4.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.u4.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.u8
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.u8.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush1.8x128.u8.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush1.8x128.u8.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.bf16
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.bf16.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.bf16.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.bf16.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.bf8.bf16
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.bf8.bf16.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.bf8.bf16.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.bf8.bf16.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.f32
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.f32.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.f32.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.f32.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.if8.bf16
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.if8.bf16.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.if8.bf16.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.if8.bf16.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.s4
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.s4.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.s4.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.s4.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.s8
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.s8.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.s8.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.s8.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.u4
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.u4.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.u4.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.u4.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.u8
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.u8.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush2.8x128.u8.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush2.8x128.u8.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.bf16
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.bf16.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.bf16.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.bf16.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.bf8.bf16
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.bf8.bf16.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.bf8.bf16.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.bf8.bf16.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.f32
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.f32.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.f32.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.f32.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.if8.bf16
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.if8.bf16.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.if8.bf16.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.if8.bf16.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.s4
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.s4.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.s4.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.s4.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.s8
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.s8.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.s8.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.s8.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.u4
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.u4.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.u4.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.u4.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.u8
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.u8.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpush3.8x128.u8.xpose
|
msra0 / msrb0 / msra1 / msrb1, v[0..63]
|
vmatpush3.8x128.u8.xpose.msk
|
msra0 / msrb0 / msra1 / msrb1, vm[0..15], v[0..63]
|
vmatpushprep
|
subr0 / subr1, v[0..63]
|
vmatpushprep.b16.msk
|
subr0 / subr1, vm[0..15], v[0..63]
|
vmatpushprep.b32.msk
|
subr0 / subr1, vm[0..15], v[0..63]
|
vmatpushprep.b8.msk
|
subr0 / subr1, vm[0..15], v[0..63]
|
vmax.index.xlane.8x128.bf16
|
trf0 / trf1, v[0..63]
|
vmax.index.xlane.8x128.f32
|
trf0 / trf1, v[0..63]
|
vmax.xlane.8x128.bf16
|
trf0 / trf1, v[0..63]
|
vmax.xlane.8x128.f32
|
trf0 / trf1, v[0..63]
|
vmin.index.xlane.8x128.bf16
|
trf0 / trf1, v[0..63]
|
vmin.index.xlane.8x128.f32
|
trf0 / trf1, v[0..63]
|
vmin.xlane.8x128.bf16
|
trf0 / trf1, v[0..63]
|
vmin.xlane.8x128.f32
|
trf0 / trf1, v[0..63]
|
vperm.lane.8x128
|
trf0 / trf1, v[0..63]
|
vrot.lane.8x128
|
trf0 / trf1, v[0..63], s[0..31] / u20
|
vrot.lane.packed.8x128
|
trf0 / trf1, v[0..63], s[0..31] / u20
|
vrot.lane.packed.b8.8x128
|
v[0..63], s[0..31] / u20
|
vsetperm.all.bytes.u32
|
pcr0 / pcr1, v[0..63]
|
vsetperm.all.u8
|
pcr0 / pcr1, v[0..63]
|
vsetperm.half.u8
|
v[0..63]
|
vsetperm.u8
|
pcr0 / pcr1, v[0..63]
|
vxpose.c.b8.start
|
trf0 / trf1, v[0..63], s[0..31] / u20
|
vxpose.c.b8.start.end
|
trf0 / trf1, v[0..63], s[0..31] / u20
|
vxpose.cont
|
trf0 / trf1, v[0..63]
|
vxpose.end
|
trf0 / trf1, v[0..63]
|
vxpose.packed.start
|
trf0 / trf1, v[0..63], s[0..31] / u20
|
vxpose.packed.start.end
|
trf0 / trf1, v[0..63], s[0..31] / u20
|
vxpose.start
|
trf0 / trf1, v[0..63], s[0..31] / u20
|
vxpose.start.end
|
trf0 / trf1, v[0..63], s[0..31] / u20
|