Consider this following case:
typedef int32_t vnx32si __attribute__ ((vector_size (128)));
__attribute__ ((noipa)) void permute_##TYPE (TYPE values1, TYPE values2, \
TYPE *out) \
{ \
TYPE v \
= __builtin_shufflevector (values1, values2, MASK_##NUNITS (0, NUNITS)); \
*(TYPE *) out = v; \
}
T (vnx32si, 32) \
TEST_ALL (PERMUTE)
Before this patch:
li a4,31
vsetvli a5,zero,e32,m8,ta,ma
vl8re32.v v24,0(a0)
vid.v v8
vrsub.vx v8,v8,a4
vrgather.vv v16,v24,v8
vs8r.v v16,0(a2)
ret
The index vector register "v8" occupies 8 registers.
We should optimize it into vrgatherei16.vv which is
using int16 as the index elements.
After this patch:
vsetvli a5,zero,e16,m4,ta,ma
li a4,31
vid.v v4
vl8re32.v v16,0(a0)
vrsub.vx v4,v4,a4
vsetvli zero,zero,e32,m8,ta,ma
vrgatherei16.vv v8,v16,v4
vs8r.v v8,0(a2)
ret
With vrgatherei16.vv, the v8 will occupy 4 registers instead
of 8. Lower the register consuming and register pressure.
PR target/111451
gcc/ChangeLog:
* config/riscv/riscv-v.cc (emit_vlmax_gather_insn): Optimization of vrgather.vv
into vrgatherei16.vv.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/vls-vlmax/perm-4.c: Adjust case.
* gcc.target/riscv/rvv/autovec/vls/perm-4.c: Ditto.
icode = code_for_pred_gather_scalar (data_mode);
sel = elt;
}
+ else if (CONST_VECTOR_P (sel)
+ && GET_MODE_BITSIZE (GET_MODE_INNER (sel_mode)) > 16
+ && riscv_get_v_regno_alignment (data_mode) > 1)
+ {
+ /* If the inner mode of data is not QI or HI and data_lmul > 1,
+ emitting vrgatherei16.vv instruction will lower register
+ pressure.
+ data_mode sel_mode ei16
+ RVVM1QI RVVM1QI RVVM2HI not needed
+ RVVM2QI RVVM2QI RVVM4HI not needed
+ RVVM2HI RVVM2HI RVVM2HI not needed
+ RVVM2SI RVVM2SI RVVM1HI need
+ RVVM4SI RVVM4SI RVVM2HI need
+ RVVM8DI RVVM8DI RVVM2HI need */
+ PUT_MODE (sel, get_vector_mode (HImode,
+ GET_MODE_NUNITS (data_mode)).require ());
+ icode = code_for_pred_gatherei16 (data_mode);
+ }
else
icode = code_for_pred_gather (data_mode);
rtx ops[] = {target, op, sel};
TEST_ALL (PERMUTE)
-/* { dg-final { scan-assembler-times {vrgather\.vv\tv[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 31 } } */
+/* { dg-final { scan-assembler-times {vrgather\.vv\tv[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 19 } } */
+/* { dg-final { scan-assembler-times {vrgatherei16\.vv\tv[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 12 } } */
/* { dg-final { scan-assembler-times {vrsub\.vi} 24 } } */
/* { dg-final { scan-assembler-times {vrsub\.vx} 7 } } */
#include "../vls-vlmax/perm-4.c"
-/* { dg-final { scan-assembler-times {vrgather\.vv\tv[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 31 } } */
+/* { dg-final { scan-assembler-times {vrgather\.vv\tv[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 19 } } */
+/* { dg-final { scan-assembler-times {vrgatherei16\.vv\tv[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 12 } } */
/* { dg-final { scan-assembler-times {vrsub\.vi} 24 } } */
/* { dg-final { scan-assembler-times {vrsub\.vx} 7 } } */