vadd.xlane.0.8x128.f32
|
trf0, v[0..31]
|
vadd.xlane.0.seg.perm.8x128.f32
|
trf0, v[0..31]
|
vadd.xlane.1.8x128.f32
|
trf1, v[0..31]
|
vadd.xlane.1.seg.perm.8x128.f32
|
trf1, v[0..31]
|
vadd.xlane.2.8x128.f32
|
trf0, v[0..31]
|
vadd.xlane.2.seg.perm.8x128.f32
|
trf0, v[0..31]
|
vadd.xlane.3.8x128.f32
|
trf1, v[0..31]
|
vadd.xlane.3.seg.perm.8x128.f32
|
trf1, v[0..31]
|
vdwg.128x128.f16
|
gmr[0..3], gsfn[0..3]
gmr[0..3], gsft[0..3]
|
vmatmul.8x128.f32
|
mrf0, v[0..31]
mrf1, v[0..31]
mrf2, v[0..31]
mrf3, v[0..31]
|
vmatmul.dwg.8x128.f32
|
(gmr0, gsfn0, mrf0), v[0..31]
(gmr1, gsfn1, mrf1), v[0..31]
(gmr2, gsfn2, mrf2), v[0..31]
(gmr3, gsfn3, mrf3), v[0..31]
(gmr0, gsft0, mrf0), v[0..31]
(gmr1, gsft1, mrf1), v[0..31]
(gmr2, gsft2, mrf2), v[0..31]
(gmr3, gsft3, mrf3), v[0..31]
|
vmatmul.hi.8x128.f32
|
mrf0, v[0..31]
mrf1, v[0..31]
mrf2, v[0..31]
mrf3, v[0..31]
|
vmatmul.hi.dwg.8x128.f32
|
(gmr0, gsfn0, mrf0), v[0..31]
(gmr1, gsfn1, mrf1), v[0..31]
(gmr2, gsfn2, mrf2), v[0..31]
(gmr3, gsfn3, mrf3), v[0..31]
(gmr0, gsft0, mrf0), v[0..31]
(gmr1, gsft1, mrf1), v[0..31]
(gmr2, gsft2, mrf2), v[0..31]
(gmr3, gsft3, mrf3), v[0..31]
|
vmatmul.hi.msk.8x128.f32
|
mrf0, vm[0..7], v[0..31]
mrf1, vm[0..7], v[0..31]
mrf2, vm[0..7], v[0..31]
mrf3, vm[0..7], v[0..31]
|
vmatmul.hi.msk.dwg.8x128.f32
|
(gmr0, gsfn0, mrf0), vm[0..7], v[0..31]
(gmr1, gsfn1, mrf1), vm[0..7], v[0..31]
(gmr2, gsfn2, mrf2), vm[0..7], v[0..31]
(gmr3, gsfn3, mrf3), vm[0..7], v[0..31]
(gmr0, gsft0, mrf0), vm[0..7], v[0..31]
(gmr1, gsft1, mrf1), vm[0..7], v[0..31]
(gmr2, gsft2, mrf2), vm[0..7], v[0..31]
(gmr3, gsft3, mrf3), vm[0..7], v[0..31]
|
vmatmul.low.8x128.f32
|
mrf0, v[0..31]
mrf1, v[0..31]
mrf2, v[0..31]
mrf3, v[0..31]
|
vmatmul.low.dwg.8x128.f32
|
(gmr0, gsfn0, mrf0), v[0..31]
(gmr1, gsfn1, mrf1), v[0..31]
(gmr2, gsfn2, mrf2), v[0..31]
(gmr3, gsfn3, mrf3), v[0..31]
(gmr0, gsft0, mrf0), v[0..31]
(gmr1, gsft1, mrf1), v[0..31]
(gmr2, gsft2, mrf2), v[0..31]
(gmr3, gsft3, mrf3), v[0..31]
|
vmatmul.low.msk.8x128.f32
|
mrf0, vm[0..7], v[0..31]
mrf1, vm[0..7], v[0..31]
mrf2, vm[0..7], v[0..31]
mrf3, vm[0..7], v[0..31]
|
vmatmul.low.msk.dwg.8x128.f32
|
(gmr0, gsfn0, mrf0), vm[0..7], v[0..31]
(gmr1, gsfn1, mrf1), vm[0..7], v[0..31]
(gmr2, gsfn2, mrf2), vm[0..7], v[0..31]
(gmr3, gsfn3, mrf3), vm[0..7], v[0..31]
(gmr0, gsft0, mrf0), vm[0..7], v[0..31]
(gmr1, gsft1, mrf1), vm[0..7], v[0..31]
(gmr2, gsft2, mrf2), vm[0..7], v[0..31]
(gmr3, gsft3, mrf3), vm[0..7], v[0..31]
|
vmatmul.msk.8x128.f32
|
mrf0, vm[0..7], v[0..31]
mrf1, vm[0..7], v[0..31]
mrf2, vm[0..7], v[0..31]
mrf3, vm[0..7], v[0..31]
|
vmatmul.msk.dwg.8x128.f32
|
(gmr0, gsfn0, mrf0), vm[0..7], v[0..31]
(gmr1, gsfn1, mrf1), vm[0..7], v[0..31]
(gmr2, gsfn2, mrf2), vm[0..7], v[0..31]
(gmr3, gsfn3, mrf3), vm[0..7], v[0..31]
(gmr0, gsft0, mrf0), vm[0..7], v[0..31]
(gmr1, gsft1, mrf1), vm[0..7], v[0..31]
(gmr2, gsft2, mrf2), vm[0..7], v[0..31]
(gmr3, gsft3, mrf3), vm[0..7], v[0..31]
|
vmatmul.packed.8x128.f16
|
mrf0, v[0..31]
mrf1, v[0..31]
mrf2, v[0..31]
mrf3, v[0..31]
|
vmatmul.packed.dwg.8x128.f16
|
(gmr0, gsfn0, mrf0), v[0..31]
(gmr1, gsfn1, mrf1), v[0..31]
(gmr2, gsfn2, mrf2), v[0..31]
(gmr3, gsfn3, mrf3), v[0..31]
(gmr0, gsft0, mrf0), v[0..31]
(gmr1, gsft1, mrf1), v[0..31]
(gmr2, gsft2, mrf2), v[0..31]
(gmr3, gsft3, mrf3), v[0..31]
|
vmatmul.packed.msk.8x128.f16
|
mrf0, vm[0..7], v[0..31]
mrf1, vm[0..7], v[0..31]
mrf2, vm[0..7], v[0..31]
mrf3, vm[0..7], v[0..31]
|
vmatmul.packed.msk.dwg.8x128.f16
|
(gmr0, gsfn0, mrf0), vm[0..7], v[0..31]
(gmr1, gsfn1, mrf1), vm[0..7], v[0..31]
(gmr2, gsfn2, mrf2), vm[0..7], v[0..31]
(gmr3, gsfn3, mrf3), vm[0..7], v[0..31]
(gmr0, gsft0, mrf0), vm[0..7], v[0..31]
(gmr1, gsft1, mrf1), vm[0..7], v[0..31]
(gmr2, gsft2, mrf2), vm[0..7], v[0..31]
(gmr3, gsft3, mrf3), vm[0..7], v[0..31]
|
vmatpush.8x128.f32
|
gsfn[0..3], v[0..31]
|
vmatpush.byte.8x128.s8
|
gsfn[0..3], v[0..31]
|
vmatpush.byte.msk.8x128.s8
|
gsfn[0..3], vm[0..7], v[0..31]
|
vmatpush.byte.xpose.8x128.s8
|
gsft[0..3], v[0..31]
|
vmatpush.byte.xpose.msk.8x128.s8
|
gsft[0..3], vm[0..7], v[0..31]
|
vmatpush.hi.8x128.f32
|
gsfn[0..3], v[0..31]
|
vmatpush.hi.msk.8x128.f32
|
gsfn[0..3], vm[0..7], v[0..31]
|
vmatpush.hi.xpose.8x128.f32
|
gsft[0..3], v[0..31]
|
vmatpush.hi.xpose.msk.8x128.f32
|
gsft[0..3], vm[0..7], v[0..31]
|
vmatpush.low.8x128.f32
|
gsfn[0..3], v[0..31]
|
vmatpush.low.msk.8x128.f32
|
gsfn[0..3], vm[0..7], v[0..31]
|
vmatpush.low.xpose.8x128.f32
|
gsft[0..3], v[0..31]
|
vmatpush.low.xpose.msk.8x128.f32
|
gsft[0..3], vm[0..7], v[0..31]
|
vmatpush.msk.8x128.f32
|
gsfn[0..3], vm[0..7], v[0..31]
|
vmatpush.packed.8x128.f16
|
gsfn[0..3], v[0..31]
|
vmatpush.packed.msk.8x128.f16
|
gsfn[0..3], vm[0..7], v[0..31]
|
vmatpush.packed.xpose.8x128.f16
|
gsft[0..3], v[0..31]
|
vmatpush.packed.xpose.msk.8x128.f16
|
gsft[0..3], vm[0..7], v[0..31]
|
vmatpush.xpose.8x128.f32
|
gsft[0..3], v[0..31]
|
vmatpush.xpose.msk.8x128.f32
|
gsft[0..3], vm[0..7], v[0..31]
|
vmax.index.xlane.0.8x128.f32
|
trf0, v[0..31]
|
vmax.index.xlane.0.seg.perm.8x128.f32
|
trf0, v[0..31]
|
vmax.index.xlane.1.8x128.f32
|
trf1, v[0..31]
|
vmax.index.xlane.1.seg.perm.8x128.f32
|
trf1, v[0..31]
|
vmax.index.xlane.2.8x128.f32
|
trf0, v[0..31]
|
vmax.index.xlane.2.seg.perm.8x128.f32
|
trf0, v[0..31]
|
vmax.index.xlane.3.8x128.f32
|
trf1, v[0..31]
|
vmax.index.xlane.3.seg.perm.8x128.f32
|
trf1, v[0..31]
|
vmax.xlane.0.8x128.f32
|
trf0, v[0..31]
|
vmax.xlane.0.seg.perm.8x128.f32
|
trf0, v[0..31]
|
vmax.xlane.1.8x128.f32
|
trf1, v[0..31]
|
vmax.xlane.1.seg.perm.8x128.f32
|
trf1, v[0..31]
|
vmax.xlane.2.8x128.f32
|
trf0, v[0..31]
|
vmax.xlane.2.seg.perm.8x128.f32
|
trf0, v[0..31]
|
vmax.xlane.3.8x128.f32
|
trf1, v[0..31]
|
vmax.xlane.3.seg.perm.8x128.f32
|
trf1, v[0..31]
|
vmin.index.xlane.0.8x128.f32
|
trf0, v[0..31]
|
vmin.index.xlane.0.seg.perm.8x128.f32
|
trf0, v[0..31]
|
vmin.index.xlane.1.8x128.f32
|
trf1, v[0..31]
|
vmin.index.xlane.1.seg.perm.8x128.f32
|
trf1, v[0..31]
|
vmin.index.xlane.2.8x128.f32
|
trf0, v[0..31]
|
vmin.index.xlane.2.seg.perm.8x128.f32
|
trf0, v[0..31]
|
vmin.index.xlane.3.8x128.f32
|
trf1, v[0..31]
|
vmin.index.xlane.3.seg.perm.8x128.f32
|
trf1, v[0..31]
|
vmin.xlane.0.8x128.f32
|
trf0, v[0..31]
|
vmin.xlane.0.seg.perm.8x128.f32
|
trf0, v[0..31]
|
vmin.xlane.1.8x128.f32
|
trf1, v[0..31]
|
vmin.xlane.1.seg.perm.8x128.f32
|
trf1, v[0..31]
|
vmin.xlane.2.8x128.f32
|
trf0, v[0..31]
|
vmin.xlane.2.seg.perm.8x128.f32
|
trf0, v[0..31]
|
vmin.xlane.3.8x128.f32
|
trf1, v[0..31]
|
vmin.xlane.3.seg.perm.8x128.f32
|
trf1, v[0..31]
|
vperm.0.8x128
|
trf0, v[0..31]
|
vperm.0.packed.8x128
|
trf0, v[0..31]
|
vperm.1.8x128
|
trf1, v[0..31]
|
vperm.1.packed.8x128
|
trf1, v[0..31]
|
vperm.2.8x128
|
trf0, v[0..31]
|
vperm.2.packed.8x128
|
trf0, v[0..31]
|
vperm.3.8x128
|
trf1, v[0..31]
|
vperm.3.packed.8x128
|
trf1, v[0..31]
|
vrot.0.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vrot.0.packed.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vrot.1.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vrot.1.packed.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vrot.2.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vrot.2.packed.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vrot.3.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vrot.3.packed.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsetperm.0.all.bytes.u32
|
pcr0, v[0..31]
|
vsetperm.0.all.u8
|
pcr0, v[0..31]
|
vsetperm.0.u8
|
pcr0, v[0..31]
|
vsetperm.1.all.bytes.u32
|
pcr1, v[0..31]
|
vsetperm.1.all.u8
|
pcr1, v[0..31]
|
vsetperm.1.u8
|
pcr1, v[0..31]
|
vsetperm.2.all.bytes.u32
|
pcr0, v[0..31]
|
vsetperm.2.all.u8
|
pcr0, v[0..31]
|
vsetperm.2.u8
|
pcr0, v[0..31]
|
vsetperm.3.all.bytes.u32
|
pcr1, v[0..31]
|
vsetperm.3.all.u8
|
pcr1, v[0..31]
|
vsetperm.3.u8
|
pcr1, v[0..31]
|
vsetspr.0.u1
|
spr0, v[0..31]
|
vsetspr.1.u1
|
spr1, v[0..31]
|
vsetspr.2.u1
|
spr0, v[0..31]
|
vsetspr.3.u1
|
spr1, v[0..31]
|
vsupp.0.8x128
|
trf0, v[0..31]
|
vsupp.1.8x128
|
trf1, v[0..31]
|
vsupp.2.8x128
|
trf0, v[0..31]
|
vsupp.3.8x128
|
trf1, v[0..31]
|
vsxpose.0.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.0.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.0.packed.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.0.packed.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.0.packed.start.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.0.packed.start.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.0.start.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.0.start.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.1.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.1.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.1.packed.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.1.packed.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.1.packed.start.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.1.packed.start.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.1.start.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.1.start.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.2.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.2.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.2.packed.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.2.packed.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.2.packed.start.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.2.packed.start.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.2.start.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.2.start.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vsxpose.3.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.3.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.3.packed.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.3.packed.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.3.packed.start.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.3.packed.start.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.3.start.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vsxpose.3.start.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.0.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.0.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.0.packed.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.0.packed.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.0.packed.start.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.0.packed.start.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.0.start.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.0.start.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.1.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.1.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.1.packed.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.1.packed.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.1.packed.start.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.1.packed.start.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.1.start.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.1.start.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.2.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.2.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.2.packed.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.2.packed.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.2.packed.start.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.2.packed.start.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.2.start.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.2.start.end.8x128
|
trf0, v[0..31], s[0..31] / u16
|
vxpose.3.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.3.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.3.packed.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.3.packed.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.3.packed.start.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.3.packed.start.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.3.start.8x128
|
trf1, v[0..31], s[0..31] / u16
|
vxpose.3.start.end.8x128
|
trf1, v[0..31], s[0..31] / u16
|