TeamHeptaMirrors/gcc
1
0
Fork 1
mirror of https://github.com/gcc-mirror/gcc.git synced 2026-05-06 14:59:39 +02:00
Code Issues Packages Projects Releases Wiki Activity

RISC-V: Legitimise the const0_rtx for RVV indexed load/store

Browse Source 
This patch try to legitimise the const0_rtx (aka zero register)
as the base register for the RVV indexed load/store instructions
by allowing the const as the operand of the indexed RTL pattern.
Then the underlying combine pass will try to perform the const
propagation.

For example:
vint32m1_t
test_vluxei32_v_i32m1_shortcut (vuint32m1_t bindex, size_t vl)
{
  return __riscv_vluxei32_v_i32m1 ((int32_t *)0, bindex, vl);
}

Before this patch:
li         a5,0                 <- can be eliminated.
vl1re32.v  v1,0(a1)
vsetvli    zero,a2,e32,m1,ta,ma
vluxei32.v v1,(a5),v1           <- can propagate the const 0 to a5 here.
vs1r.v     v1,0(a0)
ret

After this patch:
test_vluxei32_v_i32m1_shortcut:
vl1re32.v       v1,0(a1)
vsetvli zero,a2,e32,m1,ta,ma
vluxei32.v      v1,(0),v1
vs1r.v  v1,0(a0)
ret

As above, this patch allow you to propagaate the const 0 (aka zero
register) to the base register of the RVV indexed load in the combine
pass. This may benefit the underlying RVV auto-vectorization.

gcc/ChangeLog:

	* config/riscv/vector.md: Allow const as the operand of RVV
	indexed load/store.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/base/zero_base_load_store_optimization.c:
	Adjust indexed load/store check condition.

Signed-off-by: Pan Li <pan2.li@intel.com>
Co-authored-by: Ju-Zhe Zhong <juzhe.zhong@rivai.ai>
This commit is contained in:
Pan Li
2023-05-04 17:11:18 +08:00
committed by Kito Cheng
parent 3365956d55
commit 0c1eaac3fd
2 changed files with 33 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
gcc/config/riscv/vector.md
View File

@@ -1511,12 +1511,12 @@
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(unspec:V
[(match_operand 3 "pmode_register_operand" " r, r, r, r")
[(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ,rJ, rJ")
(mem:BLK (scratch))
(match_operand:<VINDEX> 4 "register_operand" " vr, vr,vr, vr")] ORDER)
(match_operand:V 2 "vector_merge_operand" " vu, vu, 0, 0")))]
"TARGET_VECTOR"
"vl<order>xei<sew>.v\t%0,(%3),%4%p1"
"vl<order>xei<sew>.v\t%0,(%z3),%4%p1"
[(set_attr "type" "vld<order>x")
(set_attr "mode" "<MODE>")])
@@ -1533,12 +1533,12 @@
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(unspec:VEEWEXT2
[(match_operand 3 "pmode_register_operand" " r, r")
[(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ")
(mem:BLK (scratch))
(match_operand:<VINDEX_DOUBLE_TRUNC> 4 "register_operand" " vr, vr")] ORDER)
(match_operand:VEEWEXT2 2 "vector_merge_operand" " vu, 0")))]
"TARGET_VECTOR"
"vl<order>xei<double_trunc_sew>.v\t%0,(%3),%4%p1"
"vl<order>xei<double_trunc_sew>.v\t%0,(%z3),%4%p1"
[(set_attr "type" "vld<order>x")
(set_attr "mode" "<MODE>")])
@@ -1554,12 +1554,12 @@
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(unspec:VEEWEXT4
[(match_operand 3 "pmode_register_operand" " r, r")
[(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ")
(mem:BLK (scratch))
(match_operand:<VINDEX_QUAD_TRUNC> 4 "register_operand" " vr, vr")] ORDER)
(match_operand:VEEWEXT4 2 "vector_merge_operand" " vu, 0")))]
"TARGET_VECTOR"
"vl<order>xei<quad_trunc_sew>.v\t%0,(%3),%4%p1"
"vl<order>xei<quad_trunc_sew>.v\t%0,(%z3),%4%p1"
[(set_attr "type" "vld<order>x")
(set_attr "mode" "<MODE>")])
@@ -1575,12 +1575,12 @@
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(unspec:VEEWEXT8
[(match_operand 3 "pmode_register_operand" " r, r")
[(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ")
(mem:BLK (scratch))
(match_operand:<VINDEX_OCT_TRUNC> 4 "register_operand" " vr, vr")] ORDER)
(match_operand:VEEWEXT8 2 "vector_merge_operand" " vu, 0")))]
"TARGET_VECTOR"
"vl<order>xei<oct_trunc_sew>.v\t%0,(%3),%4%p1"
"vl<order>xei<oct_trunc_sew>.v\t%0,(%z3),%4%p1"
[(set_attr "type" "vld<order>x")
(set_attr "mode" "<MODE>")])
@@ -1597,12 +1597,12 @@
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(unspec:VEEWTRUNC2
[(match_operand 3 "pmode_register_operand" " r, r, r, r, r, r")
[(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ, rJ, rJ, rJ, rJ")
(mem:BLK (scratch))
(match_operand:<VINDEX_DOUBLE_EXT> 4 "register_operand" " 0, 0, 0, 0, vr, vr")] ORDER)
(match_operand:VEEWTRUNC2 2 "vector_merge_operand" " vu, 0, vu, 0, vu, 0")))]
"TARGET_VECTOR"
"vl<order>xei<double_ext_sew>.v\t%0,(%3),%4%p1"
"vl<order>xei<double_ext_sew>.v\t%0,(%z3),%4%p1"
[(set_attr "type" "vld<order>x")
(set_attr "mode" "<MODE>")])
@@ -1618,12 +1618,12 @@
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(unspec:VEEWTRUNC4
[(match_operand 3 "pmode_register_operand" " r, r, r, r, r, r")
[(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ, rJ, rJ, rJ, rJ")
(mem:BLK (scratch))
(match_operand:<VINDEX_QUAD_EXT> 4 "register_operand" " 0, 0, 0, 0, vr, vr")] ORDER)
(match_operand:VEEWTRUNC4 2 "vector_merge_operand" " vu, 0, vu, 0, vu, 0")))]
"TARGET_VECTOR"
"vl<order>xei<quad_ext_sew>.v\t%0,(%3),%4%p1"
"vl<order>xei<quad_ext_sew>.v\t%0,(%z3),%4%p1"
[(set_attr "type" "vld<order>x")
(set_attr "mode" "<MODE>")])
@@ -1639,12 +1639,12 @@
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(unspec:VEEWTRUNC8
[(match_operand 3 "pmode_register_operand" " r, r, r, r, r, r")
[(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ, rJ, rJ, rJ, rJ")
(mem:BLK (scratch))
(match_operand:<VINDEX_OCT_EXT> 4 "register_operand" " 0, 0, 0, 0, vr, vr")] ORDER)
(match_operand:VEEWTRUNC8 2 "vector_merge_operand" " vu, 0, vu, 0, vu, 0")))]
"TARGET_VECTOR"
"vl<order>xei<oct_ext_sew>.v\t%0,(%3),%4%p1"
"vl<order>xei<oct_ext_sew>.v\t%0,(%z3),%4%p1"
[(set_attr "type" "vld<order>x")
(set_attr "mode" "<MODE>")])
@@ -1657,11 +1657,11 @@
(match_operand 5 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operand 1 "pmode_register_operand" " r")
(match_operand 1 "pmode_reg_or_0_operand" " rJ")
(match_operand:VNX1_QHSDI 2 "register_operand" " vr")
(match_operand:VNX1_QHSD 3 "register_operand" " vr")] ORDER))]
"TARGET_VECTOR"
"vs<order>xei<VNX1_QHSDI:sew>.v\t%3,(%1),%2%p0"
"vs<order>xei<VNX1_QHSDI:sew>.v\t%3,(%z1),%2%p0"
[(set_attr "type" "vst<order>x")
(set_attr "mode" "<VNX1_QHSD:MODE>")])
@@ -1674,11 +1674,11 @@
(match_operand 5 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operand 1 "pmode_register_operand" " r")
(match_operand 1 "pmode_reg_or_0_operand" " rJ")
(match_operand:VNX2_QHSDI 2 "register_operand" " vr")
(match_operand:VNX2_QHSD 3 "register_operand" " vr")] ORDER))]
"TARGET_VECTOR"
"vs<order>xei<VNX2_QHSDI:sew>.v\t%3,(%1),%2%p0"
"vs<order>xei<VNX2_QHSDI:sew>.v\t%3,(%z1),%2%p0"
[(set_attr "type" "vst<order>x")
(set_attr "mode" "<VNX2_QHSD:MODE>")])
@@ -1691,11 +1691,11 @@
(match_operand 5 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operand 1 "pmode_register_operand" " r")
(match_operand 1 "pmode_reg_or_0_operand" " rJ")
(match_operand:VNX4_QHSDI 2 "register_operand" " vr")
(match_operand:VNX4_QHSD 3 "register_operand" " vr")] ORDER))]
"TARGET_VECTOR"
"vs<order>xei<VNX4_QHSDI:sew>.v\t%3,(%1),%2%p0"
"vs<order>xei<VNX4_QHSDI:sew>.v\t%3,(%z1),%2%p0"
[(set_attr "type" "vst<order>x")
(set_attr "mode" "<VNX4_QHSD:MODE>")])
@@ -1708,11 +1708,11 @@
(match_operand 5 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operand 1 "pmode_register_operand" " r")
(match_operand 1 "pmode_reg_or_0_operand" " rJ")
(match_operand:VNX8_QHSDI 2 "register_operand" " vr")
(match_operand:VNX8_QHSD 3 "register_operand" " vr")] ORDER))]
"TARGET_VECTOR"
"vs<order>xei<VNX8_QHSDI:sew>.v\t%3,(%1),%2%p0"
"vs<order>xei<VNX8_QHSDI:sew>.v\t%3,(%z1),%2%p0"
[(set_attr "type" "vst<order>x")
(set_attr "mode" "<VNX8_QHSD:MODE>")])
@@ -1725,11 +1725,11 @@
(match_operand 5 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operand 1 "pmode_register_operand" " r")
(match_operand 1 "pmode_reg_or_0_operand" " rJ")
(match_operand:VNX16_QHSI 2 "register_operand" " vr")
(match_operand:VNX16_QHS 3 "register_operand" " vr")] ORDER))]
"TARGET_VECTOR"
"vs<order>xei<VNX16_QHSI:sew>.v\t%3,(%1),%2%p0"
"vs<order>xei<VNX16_QHSI:sew>.v\t%3,(%z1),%2%p0"
[(set_attr "type" "vst<order>x")
(set_attr "mode" "<VNX16_QHS:MODE>")])
@@ -1742,11 +1742,11 @@
(match_operand 5 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operand 1 "pmode_register_operand" " r")
(match_operand 1 "pmode_reg_or_0_operand" " rJ")
(match_operand:VNX32_QHSI 2 "register_operand" " vr")
(match_operand:VNX32_QHS 3 "register_operand" " vr")] ORDER))]
"TARGET_VECTOR"
"vs<order>xei<VNX32_QHSI:sew>.v\t%3,(%1),%2%p0"
"vs<order>xei<VNX32_QHSI:sew>.v\t%3,(%z1),%2%p0"
[(set_attr "type" "vst<order>x")
(set_attr "mode" "<VNX32_QHS:MODE>")])
@@ -1759,11 +1759,11 @@
(match_operand 5 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operand 1 "pmode_register_operand" " r")
(match_operand:VNX64_QHI 2 "register_operand" " vr")
(match_operand 1 "pmode_reg_or_0_operand" " rJ")
(match_operand:VNX64_QHI 2 "register_operand" " vr")
(match_operand:VNX64_QH 3 "register_operand" " vr")] ORDER))]
"TARGET_VECTOR"
"vs<order>xei<VNX64_QHI:sew>.v\t%3,(%1),%2%p0"
"vs<order>xei<VNX64_QHI:sew>.v\t%3,(%z1),%2%p0"
[(set_attr "type" "vst<order>x")
(set_attr "mode" "<VNX64_QH:MODE>")])
@@ -1776,11 +1776,11 @@
(match_operand 5 "const_int_operand" " i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(match_operand 1 "pmode_register_operand" " r")
(match_operand 1 "pmode_reg_or_0_operand" " rJ")
(match_operand:VNX128_Q 2 "register_operand" " vr")
(match_operand:VNX128_Q 3 "register_operand" " vr")] ORDER))]
"TARGET_VECTOR"
"vs<order>xei<VNX128_Q:sew>.v\t%3,(%1),%2%p0"
"vs<order>xei<VNX128_Q:sew>.v\t%3,(%z1),%2%p0"
[(set_attr "type" "vst<order>x")
(set_attr "mode" "<VNX128_Q:MODE>")])

3
gcc/testsuite/gcc.target/riscv/rvv/base/zero_base_load_store_optimization.c
View File

@@ -131,4 +131,5 @@ void test_vsoxei32_v_f32m1_shortcut (vuint32m1_t bindex, vfloat32m1_t val, size_
/* { dg-final { scan-assembler-times {v[ls]e[0-9]+\.v\s+v[0-9]+,\s*0\(zero\)} 6 } } */
/* { dg-final { scan-assembler-times {v[ls]se[0-9]+\.v\s+v[0-9]+,\s*0\(zero\),\s*[ax][0-9]+} 6 } } */
/* { dg-final { scan-assembler-times {li\s+[a-x][0-9]+,\s*0} 12 } } */
/* { dg-final { scan-assembler-times {v[ls][uo]xei[0-9]+\.v\s+v[0-9]+,\s*\(zero\),\s*v[0-9]+} 12 } } */
/* { dg-final { scan-assembler-not {li\s+[a-x][0-9]+,\s*0} } } */