mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2024-09-18 20:43:38 +00:00
lavu/riscv: add forward-edge CFI landing pads
This commit is contained in:
parent
6319601343
commit
a14d21a446
@ -21,6 +21,7 @@
|
|||||||
#include "asm.S"
|
#include "asm.S"
|
||||||
|
|
||||||
func ff_vector_fmul_window_scaled_rvv, zve64x, zba
|
func ff_vector_fmul_window_scaled_rvv, zve64x, zba
|
||||||
|
lpad 0
|
||||||
csrwi vxrm, 0
|
csrwi vxrm, 0
|
||||||
vsetvli t0, zero, e16, m1, ta, ma
|
vsetvli t0, zero, e16, m1, ta, ma
|
||||||
sh2add a2, a4, a2
|
sh2add a2, a4, a2
|
||||||
@ -69,6 +70,7 @@ func ff_vector_fmul_window_scaled_rvv, zve64x, zba
|
|||||||
endfunc
|
endfunc
|
||||||
|
|
||||||
func ff_vector_fmul_window_fixed_rvv, zve64x, zba
|
func ff_vector_fmul_window_fixed_rvv, zve64x, zba
|
||||||
|
lpad 0
|
||||||
csrwi vxrm, 0
|
csrwi vxrm, 0
|
||||||
vsetvli t0, zero, e16, m1, ta, ma
|
vsetvli t0, zero, e16, m1, ta, ma
|
||||||
sh2add a2, a4, a2
|
sh2add a2, a4, a2
|
||||||
@ -113,6 +115,7 @@ func ff_vector_fmul_window_fixed_rvv, zve64x, zba
|
|||||||
endfunc
|
endfunc
|
||||||
|
|
||||||
func ff_vector_fmul_fixed_rvv, zve32x, zba
|
func ff_vector_fmul_fixed_rvv, zve32x, zba
|
||||||
|
lpad 0
|
||||||
csrwi vxrm, 0
|
csrwi vxrm, 0
|
||||||
1:
|
1:
|
||||||
vsetvli t0, a3, e32, m4, ta, ma
|
vsetvli t0, a3, e32, m4, ta, ma
|
||||||
@ -156,6 +159,7 @@ func ff_vector_fmul_reverse_fixed_rvv, zve32x, zba
|
|||||||
endfunc
|
endfunc
|
||||||
|
|
||||||
func ff_vector_fmul_add_fixed_rvv, zve32x, zba
|
func ff_vector_fmul_add_fixed_rvv, zve32x, zba
|
||||||
|
lpad 0
|
||||||
csrwi vxrm, 0
|
csrwi vxrm, 0
|
||||||
1:
|
1:
|
||||||
vsetvli t0, a4, e32, m8, ta, ma
|
vsetvli t0, a4, e32, m8, ta, ma
|
||||||
@ -176,6 +180,7 @@ func ff_vector_fmul_add_fixed_rvv, zve32x, zba
|
|||||||
endfunc
|
endfunc
|
||||||
|
|
||||||
func ff_scalarproduct_fixed_rvv, zve64x, zba
|
func ff_scalarproduct_fixed_rvv, zve64x, zba
|
||||||
|
lpad 0
|
||||||
li t1, 1 << 30
|
li t1, 1 << 30
|
||||||
vsetvli t0, zero, e64, m8, ta, ma
|
vsetvli t0, zero, e64, m8, ta, ma
|
||||||
vmv.v.x v8, zero
|
vmv.v.x v8, zero
|
||||||
@ -199,6 +204,7 @@ endfunc
|
|||||||
|
|
||||||
// (a0) = (a0) + (a1), (a1) = (a0) - (a1) [0..a2-1]
|
// (a0) = (a0) + (a1), (a1) = (a0) - (a1) [0..a2-1]
|
||||||
func ff_butterflies_fixed_rvv, zve32x, zba
|
func ff_butterflies_fixed_rvv, zve32x, zba
|
||||||
|
lpad 0
|
||||||
1:
|
1:
|
||||||
vsetvli t0, a2, e32, m4, ta, ma
|
vsetvli t0, a2, e32, m4, ta, ma
|
||||||
vle32.v v16, (a0)
|
vle32.v v16, (a0)
|
||||||
|
@ -22,6 +22,7 @@
|
|||||||
|
|
||||||
// (a0) = (a1) * (a2) [0..a3-1]
|
// (a0) = (a1) * (a2) [0..a3-1]
|
||||||
func ff_vector_fmul_rvv, zve32f, zba
|
func ff_vector_fmul_rvv, zve32f, zba
|
||||||
|
lpad 0
|
||||||
1:
|
1:
|
||||||
vsetvli t0, a3, e32, m8, ta, ma
|
vsetvli t0, a3, e32, m8, ta, ma
|
||||||
vle32.v v16, (a1)
|
vle32.v v16, (a1)
|
||||||
@ -39,6 +40,7 @@ endfunc
|
|||||||
|
|
||||||
// (a0) += (a1) * fa0 [0..a2-1]
|
// (a0) += (a1) * fa0 [0..a2-1]
|
||||||
func ff_vector_fmac_scalar_rvv, zve32f, zba
|
func ff_vector_fmac_scalar_rvv, zve32f, zba
|
||||||
|
lpad 0
|
||||||
NOHWF fmv.w.x fa0, a2
|
NOHWF fmv.w.x fa0, a2
|
||||||
NOHWF mv a2, a3
|
NOHWF mv a2, a3
|
||||||
1:
|
1:
|
||||||
@ -58,6 +60,7 @@ endfunc
|
|||||||
|
|
||||||
// (a0) = (a1) * fa0 [0..a2-1]
|
// (a0) = (a1) * fa0 [0..a2-1]
|
||||||
func ff_vector_fmul_scalar_rvv, zve32f, zba
|
func ff_vector_fmul_scalar_rvv, zve32f, zba
|
||||||
|
lpad 0
|
||||||
NOHWF fmv.w.x fa0, a2
|
NOHWF fmv.w.x fa0, a2
|
||||||
NOHWF mv a2, a3
|
NOHWF mv a2, a3
|
||||||
1:
|
1:
|
||||||
@ -74,6 +77,7 @@ NOHWF mv a2, a3
|
|||||||
endfunc
|
endfunc
|
||||||
|
|
||||||
func ff_vector_fmul_window_rvv, zve32f, zba
|
func ff_vector_fmul_window_rvv, zve32f, zba
|
||||||
|
lpad 0
|
||||||
// a0: dst, a1: src0, a2: src1, a3: window, a4: length
|
// a0: dst, a1: src0, a2: src1, a3: window, a4: length
|
||||||
// e16/m2 and e32/m4 are possible but slower due to gather.
|
// e16/m2 and e32/m4 are possible but slower due to gather.
|
||||||
vsetvli t0, zero, e16, m1, ta, ma
|
vsetvli t0, zero, e16, m1, ta, ma
|
||||||
@ -114,6 +118,7 @@ endfunc
|
|||||||
|
|
||||||
// (a0) = (a1) * (a2) + (a3) [0..a4-1]
|
// (a0) = (a1) * (a2) + (a3) [0..a4-1]
|
||||||
func ff_vector_fmul_add_rvv, zve32f, zba
|
func ff_vector_fmul_add_rvv, zve32f, zba
|
||||||
|
lpad 0
|
||||||
1:
|
1:
|
||||||
vsetvli t0, a4, e32, m8, ta, ma
|
vsetvli t0, a4, e32, m8, ta, ma
|
||||||
vle32.v v8, (a1)
|
vle32.v v8, (a1)
|
||||||
@ -134,6 +139,7 @@ endfunc
|
|||||||
// TODO factor vrsub, separate last iteration?
|
// TODO factor vrsub, separate last iteration?
|
||||||
// (a0) = (a1) * reverse(a2) [0..a3-1]
|
// (a0) = (a1) * reverse(a2) [0..a3-1]
|
||||||
func ff_vector_fmul_reverse_rvv, zve32f, zba
|
func ff_vector_fmul_reverse_rvv, zve32f, zba
|
||||||
|
lpad 0
|
||||||
// e16/m4 and e32/m8 are possible but slower due to gather.
|
// e16/m4 and e32/m8 are possible but slower due to gather.
|
||||||
vsetvli t0, zero, e16, m1, ta, ma
|
vsetvli t0, zero, e16, m1, ta, ma
|
||||||
sh2add a2, a3, a2
|
sh2add a2, a3, a2
|
||||||
@ -160,6 +166,7 @@ endfunc
|
|||||||
|
|
||||||
// (a0) = (a0) + (a1), (a1) = (a0) - (a1) [0..a2-1]
|
// (a0) = (a0) + (a1), (a1) = (a0) - (a1) [0..a2-1]
|
||||||
func ff_butterflies_float_rvv, zve32f, zba
|
func ff_butterflies_float_rvv, zve32f, zba
|
||||||
|
lpad 0
|
||||||
1:
|
1:
|
||||||
vsetvli t0, a2, e32, m8, ta, ma
|
vsetvli t0, a2, e32, m8, ta, ma
|
||||||
vle32.v v16, (a0)
|
vle32.v v16, (a0)
|
||||||
@ -178,6 +185,7 @@ endfunc
|
|||||||
|
|
||||||
// a0 = (a0).(a1) [0..a2-1]
|
// a0 = (a0).(a1) [0..a2-1]
|
||||||
func ff_scalarproduct_float_rvv, zve32f, zba
|
func ff_scalarproduct_float_rvv, zve32f, zba
|
||||||
|
lpad 0
|
||||||
vsetvli t0, zero, e32, m8, ta, ma
|
vsetvli t0, zero, e32, m8, ta, ma
|
||||||
vmv.v.x v8, zero
|
vmv.v.x v8, zero
|
||||||
vmv.s.x v0, zero
|
vmv.s.x v0, zero
|
||||||
@ -200,6 +208,7 @@ endfunc
|
|||||||
|
|
||||||
// (a0) = (a1) * (a2) [0..a3-1]
|
// (a0) = (a1) * (a2) [0..a3-1]
|
||||||
func ff_vector_dmul_rvv, zve64d, zba
|
func ff_vector_dmul_rvv, zve64d, zba
|
||||||
|
lpad 0
|
||||||
1:
|
1:
|
||||||
vsetvli t0, a3, e64, m8, ta, ma
|
vsetvli t0, a3, e64, m8, ta, ma
|
||||||
vle64.v v16, (a1)
|
vle64.v v16, (a1)
|
||||||
@ -217,6 +226,7 @@ endfunc
|
|||||||
|
|
||||||
// (a0) += (a1) * fa0 [0..a2-1]
|
// (a0) += (a1) * fa0 [0..a2-1]
|
||||||
func ff_vector_dmac_scalar_rvv, zve64d, zba
|
func ff_vector_dmac_scalar_rvv, zve64d, zba
|
||||||
|
lpad 0
|
||||||
NOHWD fmv.d.x fa0, a2
|
NOHWD fmv.d.x fa0, a2
|
||||||
NOHWD mv a2, a3
|
NOHWD mv a2, a3
|
||||||
1:
|
1:
|
||||||
@ -235,6 +245,7 @@ endfunc
|
|||||||
|
|
||||||
// (a0) = (a1) * fa0 [0..a2-1]
|
// (a0) = (a1) * fa0 [0..a2-1]
|
||||||
func ff_vector_dmul_scalar_rvv, zve64d, zba
|
func ff_vector_dmul_scalar_rvv, zve64d, zba
|
||||||
|
lpad 0
|
||||||
NOHWD fmv.d.x fa0, a2
|
NOHWD fmv.d.x fa0, a2
|
||||||
NOHWD mv a2, a3
|
NOHWD mv a2, a3
|
||||||
1:
|
1:
|
||||||
@ -251,6 +262,7 @@ NOHWD mv a2, a3
|
|||||||
endfunc
|
endfunc
|
||||||
|
|
||||||
func ff_scalarproduct_double_rvv, zve64f, zba
|
func ff_scalarproduct_double_rvv, zve64f, zba
|
||||||
|
lpad 0
|
||||||
vsetvli t0, zero, e64, m8, ta, ma
|
vsetvli t0, zero, e64, m8, ta, ma
|
||||||
vmv.v.x v8, zero
|
vmv.v.x v8, zero
|
||||||
vmv.s.x v0, zero
|
vmv.s.x v0, zero
|
||||||
|
@ -21,6 +21,7 @@
|
|||||||
#include "asm.S"
|
#include "asm.S"
|
||||||
|
|
||||||
func ff_lls_update_covariance_rvv, zve64d, zbb
|
func ff_lls_update_covariance_rvv, zve64d, zbb
|
||||||
|
lpad 0
|
||||||
vtype_vli t0, a2, t1, e64, ta, ma
|
vtype_vli t0, a2, t1, e64, ta, ma
|
||||||
vsetvl zero, a2, t0
|
vsetvl zero, a2, t0
|
||||||
vle64.v v8, (a1)
|
vle64.v v8, (a1)
|
||||||
|
Loading…
Reference in New Issue
Block a user