Leverage previous approach.
Before this patch:
.L5:
add a3,s0,s2
add a4,s6,s2
add a5,s7,s2
vsetvli zero,s0,e64,m8,ta,ma
vle8.v v4,0(s2)
vle8.v v3,0(a3)
mv s2,s1
vle8.v v2,0(a4)
vle8.v v1,0(a5)
nop
vluxei8.v v8,(s1),v4
vs8r.v v8,0(sp) ---> spill
vluxei8.v v8,(s1),v3
vluxei8.v v16,(s1),v2
vluxei8.v v24,(s1),v1
nop
vmv.x.s a1,v8
vl8re64.v v8,0(sp) ---> reload
vmv.x.s a3,v24
vmv.x.s a2,v16
vmv.x.s a0,v8
add s1,s1,s5
call sumation
add s3,s3,a0
bgeu s4,s1,.L5
After this patch:
.L5:
add a3,s0,s2
add a4,s6,s2
add a5,s7,s2
vsetvli zero,s0,e64,m8,ta,ma
vle8.v v15,0(s2)
vle8.v v23,0(a3)
mv s2,s1
vle8.v v31,0(a4)
vle8.v v7,0(a5)
vluxei8.v v8,(s1),v15
vluxei8.v v16,(s1),v23
vluxei8.v v24,(s1),v31
vluxei8.v v0,(s1),v7
vmv.x.s a3,v0
vmv.x.s a2,v24
vmv.x.s a1,v16
vmv.x.s a0,v8
add s1,s1,s5
call sumation
add s3,s3,a0
bgeu s4,s1,.L5
PR target/112431
gcc/ChangeLog:
* config/riscv/vector.md: Support highpart overlap for indexed load.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/base/pr112431-28.c: New test.
* gcc.target/riscv/rvv/base/pr112431-29.c: New test.
* gcc.target/riscv/rvv/base/pr112431-30.c: New test.
* gcc.target/riscv/rvv/base/pr112431-31.c: New test.
* gcc.target/riscv/rvv/base/pr112431-32.c: New test.
* gcc.target/riscv/rvv/base/pr112431-33.c: New test.
;; DEST eew is greater than SOURCE eew.
(define_insn "@pred_indexed_<order>load<mode>_x2_greater_eew"
- [(set (match_operand:VEEWEXT2 0 "register_operand" "=&vr, &vr")
+ [(set (match_operand:VEEWEXT2 0 "register_operand" "=vr, vr, vr, vr, vr, vr, ?&vr, ?&vr")
(if_then_else:VEEWEXT2
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 5 "vector_length_operand" " rK, rK")
- (match_operand 6 "const_int_operand" " i, i")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1,vmWc1,vmWc1,vmWc1,vmWc1,vmWc1")
+ (match_operand 5 "vector_length_operand" " rK, rK, rK, rK, rK, rK, rK, rK")
+ (match_operand 6 "const_int_operand" " i, i, i, i, i, i, i, i")
+ (match_operand 7 "const_int_operand" " i, i, i, i, i, i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i, i, i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(unspec:VEEWEXT2
- [(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ")
+ [(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ, rJ, rJ, rJ, rJ, 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")))]
+ (match_operand:<VINDEX_DOUBLE_TRUNC> 4 "register_operand" " W21, W21, W42, W42, W84, W84, vr, vr")] ORDER)
+ (match_operand:VEEWEXT2 2 "vector_merge_operand" " vu, 0, vu, 0, vu, 0, vu, 0")))]
"TARGET_VECTOR"
"vl<order>xei<double_trunc_sew>.v\t%0,(%z3),%4%p1"
[(set_attr "type" "vld<order>x")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "W21,W21,W42,W42,W84,W84,none,none")])
(define_insn "@pred_indexed_<order>load<mode>_x4_greater_eew"
- [(set (match_operand:VEEWEXT4 0 "register_operand" "=&vr, &vr")
+ [(set (match_operand:VEEWEXT4 0 "register_operand" "=vr, vr, vr, vr, ?&vr, ?&vr")
(if_then_else:VEEWEXT4
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 5 "vector_length_operand" " rK, rK")
- (match_operand 6 "const_int_operand" " i, i")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1,vmWc1,vmWc1,vmWc1")
+ (match_operand 5 "vector_length_operand" " rK, rK, rK, rK, rK, rK")
+ (match_operand 6 "const_int_operand" " i, i, i, i, i, i")
+ (match_operand 7 "const_int_operand" " i, i, i, i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(unspec:VEEWEXT4
- [(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ")
+ [(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ, rJ, rJ, 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")))]
+ (match_operand:<VINDEX_QUAD_TRUNC> 4 "register_operand" " W43, W43, W86, W86, vr, vr")] ORDER)
+ (match_operand:VEEWEXT4 2 "vector_merge_operand" " vu, 0, vu, 0, vu, 0")))]
"TARGET_VECTOR"
"vl<order>xei<quad_trunc_sew>.v\t%0,(%z3),%4%p1"
[(set_attr "type" "vld<order>x")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "W43,W43,W86,W86,none,none")])
(define_insn "@pred_indexed_<order>load<mode>_x8_greater_eew"
- [(set (match_operand:VEEWEXT8 0 "register_operand" "=&vr, &vr")
+ [(set (match_operand:VEEWEXT8 0 "register_operand" "=vr, vr, ?&vr, ?&vr")
(if_then_else:VEEWEXT8
(unspec:<VM>
- [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1")
- (match_operand 5 "vector_length_operand" " rK, rK")
- (match_operand 6 "const_int_operand" " i, i")
- (match_operand 7 "const_int_operand" " i, i")
- (match_operand 8 "const_int_operand" " i, i")
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1,vmWc1,vmWc1,vmWc1")
+ (match_operand 5 "vector_length_operand" " rK, rK, rK, rK")
+ (match_operand 6 "const_int_operand" " i, i, i, i")
+ (match_operand 7 "const_int_operand" " i, i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i, i")
(reg:SI VL_REGNUM)
(reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
(unspec:VEEWEXT8
- [(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ")
+ [(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ, 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")))]
+ (match_operand:<VINDEX_OCT_TRUNC> 4 "register_operand" " W87, W87, vr, vr")] ORDER)
+ (match_operand:VEEWEXT8 2 "vector_merge_operand" " vu, 0, vu, 0")))]
"TARGET_VECTOR"
"vl<order>xei<oct_trunc_sew>.v\t%0,(%z3),%4%p1"
[(set_attr "type" "vld<order>x")
- (set_attr "mode" "<MODE>")])
+ (set_attr "mode" "<MODE>")
+ (set_attr "group_overlap" "W87,W87,none,none")])
;; DEST eew is smaller than SOURCE eew.
(define_insn "@pred_indexed_<order>load<mode>_x2_smaller_eew"
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3, size_t sum4,
+ size_t sum5, size_t sum6, size_t sum7, size_t sum8, size_t sum9,
+ size_t sum10, size_t sum11, size_t sum12, size_t sum13, size_t sum14,
+ size_t sum15)
+{
+ return sum0 + sum1 + sum2 + sum3 + sum4 + sum5 + sum6 + sum7 + sum8 + sum9
+ + sum10 + sum11 + sum12 + sum13 + sum14 + sum15;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+ size_t sum = 0;
+ size_t vl = __riscv_vsetvlmax_e8m8 ();
+ size_t step = vl * 4;
+ const char *it = buf, *end = buf + len;
+ for (; it + step <= end;)
+ {
+ vuint8m1_t v0 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v1 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v2 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v3 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v4 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v5 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v6 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v7 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v8 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v9 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v10 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v11 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v12 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v13 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v14 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v15 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+
+ asm volatile("nop" ::: "memory");
+ vint16m2_t vw0 = __riscv_vluxei8_v_i16m2 ((void *) it, v0, vl);
+ vint16m2_t vw1 = __riscv_vluxei8_v_i16m2 ((void *) it, v1, vl);
+ vint16m2_t vw2 = __riscv_vluxei8_v_i16m2 ((void *) it, v2, vl);
+ vint16m2_t vw3 = __riscv_vluxei8_v_i16m2 ((void *) it, v3, vl);
+ vint16m2_t vw4 = __riscv_vluxei8_v_i16m2 ((void *) it, v4, vl);
+ vint16m2_t vw5 = __riscv_vluxei8_v_i16m2 ((void *) it, v5, vl);
+ vint16m2_t vw6 = __riscv_vluxei8_v_i16m2 ((void *) it, v6, vl);
+ vint16m2_t vw7 = __riscv_vluxei8_v_i16m2 ((void *) it, v7, vl);
+ vint16m2_t vw8 = __riscv_vluxei8_v_i16m2 ((void *) it, v8, vl);
+ vint16m2_t vw9 = __riscv_vluxei8_v_i16m2 ((void *) it, v9, vl);
+ vint16m2_t vw10 = __riscv_vluxei8_v_i16m2 ((void *) it, v10, vl);
+ vint16m2_t vw11 = __riscv_vluxei8_v_i16m2 ((void *) it, v11, vl);
+ vint16m2_t vw12 = __riscv_vluxei8_v_i16m2 ((void *) it, v12, vl);
+ vint16m2_t vw13 = __riscv_vluxei8_v_i16m2 ((void *) it, v13, vl);
+ vint16m2_t vw14 = __riscv_vluxei8_v_i16m2 ((void *) it, v14, vl);
+ vint16m2_t vw15 = __riscv_vluxei8_v_i16m2 ((void *) it, v15, vl);
+
+ asm volatile("nop" ::: "memory");
+ size_t sum0 = __riscv_vmv_x_s_i16m2_i16 (vw0);
+ size_t sum1 = __riscv_vmv_x_s_i16m2_i16 (vw1);
+ size_t sum2 = __riscv_vmv_x_s_i16m2_i16 (vw2);
+ size_t sum3 = __riscv_vmv_x_s_i16m2_i16 (vw3);
+ size_t sum4 = __riscv_vmv_x_s_i16m2_i16 (vw4);
+ size_t sum5 = __riscv_vmv_x_s_i16m2_i16 (vw5);
+ size_t sum6 = __riscv_vmv_x_s_i16m2_i16 (vw6);
+ size_t sum7 = __riscv_vmv_x_s_i16m2_i16 (vw7);
+ size_t sum8 = __riscv_vmv_x_s_i16m2_i16 (vw8);
+ size_t sum9 = __riscv_vmv_x_s_i16m2_i16 (vw9);
+ size_t sum10 = __riscv_vmv_x_s_i16m2_i16 (vw10);
+ size_t sum11 = __riscv_vmv_x_s_i16m2_i16 (vw11);
+ size_t sum12 = __riscv_vmv_x_s_i16m2_i16 (vw12);
+ size_t sum13 = __riscv_vmv_x_s_i16m2_i16 (vw13);
+ size_t sum14 = __riscv_vmv_x_s_i16m2_i16 (vw14);
+ size_t sum15 = __riscv_vmv_x_s_i16m2_i16 (vw15);
+
+ sum += sumation (sum0, sum1, sum2, sum3, sum4, sum5, sum6, sum7, sum8,
+ sum9, sum10, sum11, sum12, sum13, sum14, sum15);
+ }
+ return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3, size_t sum4,
+ size_t sum5, size_t sum6, size_t sum7)
+{
+ return sum0 + sum1 + sum2 + sum3 + sum4 + sum5 + sum6 + sum7;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+ size_t sum = 0;
+ size_t vl = __riscv_vsetvlmax_e8m8 ();
+ size_t step = vl * 4;
+ const char *it = buf, *end = buf + len;
+ for (; it + step <= end;)
+ {
+ vuint8m2_t v0 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+ vuint8m2_t v1 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+ vuint8m2_t v2 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+ vuint8m2_t v3 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+ vuint8m2_t v4 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+ vuint8m2_t v5 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+ vuint8m2_t v6 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+ vuint8m2_t v7 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+
+ asm volatile("nop" ::: "memory");
+ vint16m4_t vw0 = __riscv_vluxei8_v_i16m4 ((void *) it, v0, vl);
+ vint16m4_t vw1 = __riscv_vluxei8_v_i16m4 ((void *) it, v1, vl);
+ vint16m4_t vw2 = __riscv_vluxei8_v_i16m4 ((void *) it, v2, vl);
+ vint16m4_t vw3 = __riscv_vluxei8_v_i16m4 ((void *) it, v3, vl);
+ vint16m4_t vw4 = __riscv_vluxei8_v_i16m4 ((void *) it, v4, vl);
+ vint16m4_t vw5 = __riscv_vluxei8_v_i16m4 ((void *) it, v5, vl);
+ vint16m4_t vw6 = __riscv_vluxei8_v_i16m4 ((void *) it, v6, vl);
+ vint16m4_t vw7 = __riscv_vluxei8_v_i16m4 ((void *) it, v7, vl);
+
+ asm volatile("nop" ::: "memory");
+ size_t sum0 = __riscv_vmv_x_s_i16m4_i16 (vw0);
+ size_t sum1 = __riscv_vmv_x_s_i16m4_i16 (vw1);
+ size_t sum2 = __riscv_vmv_x_s_i16m4_i16 (vw2);
+ size_t sum3 = __riscv_vmv_x_s_i16m4_i16 (vw3);
+ size_t sum4 = __riscv_vmv_x_s_i16m4_i16 (vw4);
+ size_t sum5 = __riscv_vmv_x_s_i16m4_i16 (vw5);
+ size_t sum6 = __riscv_vmv_x_s_i16m4_i16 (vw6);
+ size_t sum7 = __riscv_vmv_x_s_i16m4_i16 (vw7);
+
+ sum += sumation (sum0, sum1, sum2, sum3, sum4, sum5, sum6, sum7);
+ }
+ return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3)
+{
+ return sum0 + sum1 + sum2 + sum3;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+ size_t sum = 0;
+ size_t vl = __riscv_vsetvlmax_e8m8 ();
+ size_t step = vl * 4;
+ const char *it = buf, *end = buf + len;
+ for (; it + step <= end;)
+ {
+ vuint8m4_t v0 = __riscv_vle8_v_u8m4 ((void *) it, vl);
+ it += vl;
+ vuint8m4_t v1 = __riscv_vle8_v_u8m4 ((void *) it, vl);
+ it += vl;
+ vuint8m4_t v2 = __riscv_vle8_v_u8m4 ((void *) it, vl);
+ it += vl;
+ vuint8m4_t v3 = __riscv_vle8_v_u8m4 ((void *) it, vl);
+ it += vl;
+
+ asm volatile("nop" ::: "memory");
+ vint16m8_t vw0 = __riscv_vluxei8_v_i16m8 ((void *) it, v0, vl);
+ vint16m8_t vw1 = __riscv_vluxei8_v_i16m8 ((void *) it, v1, vl);
+ vint16m8_t vw2 = __riscv_vluxei8_v_i16m8 ((void *) it, v2, vl);
+ vint16m8_t vw3 = __riscv_vluxei8_v_i16m8 ((void *) it, v3, vl);
+
+ asm volatile("nop" ::: "memory");
+ size_t sum0 = __riscv_vmv_x_s_i16m8_i16 (vw0);
+ size_t sum1 = __riscv_vmv_x_s_i16m8_i16 (vw1);
+ size_t sum2 = __riscv_vmv_x_s_i16m8_i16 (vw2);
+ size_t sum3 = __riscv_vmv_x_s_i16m8_i16 (vw3);
+
+ sum += sumation (sum0, sum1, sum2, sum3);
+ }
+ return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3, size_t sum4,
+ size_t sum5, size_t sum6, size_t sum7)
+{
+ return sum0 + sum1 + sum2 + sum3 + sum4 + sum5 + sum6 + sum7;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+ size_t sum = 0;
+ size_t vl = __riscv_vsetvlmax_e8m8 ();
+ size_t step = vl * 4;
+ const char *it = buf, *end = buf + len;
+ for (; it + step <= end;)
+ {
+ vuint8m1_t v0 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v1 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v2 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v3 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v4 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v5 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v6 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v7 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+
+ asm volatile("nop" ::: "memory");
+ vint32m4_t vw0 = __riscv_vluxei8_v_i32m4 ((void *) it, v0, vl);
+ vint32m4_t vw1 = __riscv_vluxei8_v_i32m4 ((void *) it, v1, vl);
+ vint32m4_t vw2 = __riscv_vluxei8_v_i32m4 ((void *) it, v2, vl);
+ vint32m4_t vw3 = __riscv_vluxei8_v_i32m4 ((void *) it, v3, vl);
+ vint32m4_t vw4 = __riscv_vluxei8_v_i32m4 ((void *) it, v4, vl);
+ vint32m4_t vw5 = __riscv_vluxei8_v_i32m4 ((void *) it, v5, vl);
+ vint32m4_t vw6 = __riscv_vluxei8_v_i32m4 ((void *) it, v6, vl);
+ vint32m4_t vw7 = __riscv_vluxei8_v_i32m4 ((void *) it, v7, vl);
+
+ asm volatile("nop" ::: "memory");
+ size_t sum0 = __riscv_vmv_x_s_i32m4_i32 (vw0);
+ size_t sum1 = __riscv_vmv_x_s_i32m4_i32 (vw1);
+ size_t sum2 = __riscv_vmv_x_s_i32m4_i32 (vw2);
+ size_t sum3 = __riscv_vmv_x_s_i32m4_i32 (vw3);
+ size_t sum4 = __riscv_vmv_x_s_i32m4_i32 (vw4);
+ size_t sum5 = __riscv_vmv_x_s_i32m4_i32 (vw5);
+ size_t sum6 = __riscv_vmv_x_s_i32m4_i32 (vw6);
+ size_t sum7 = __riscv_vmv_x_s_i32m4_i32 (vw7);
+
+ sum += sumation (sum0, sum1, sum2, sum3, sum4, sum5, sum6, sum7);
+ }
+ return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3)
+{
+ return sum0 + sum1 + sum2 + sum3;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+ size_t sum = 0;
+ size_t vl = __riscv_vsetvlmax_e8m8 ();
+ size_t step = vl * 4;
+ const char *it = buf, *end = buf + len;
+ for (; it + step <= end;)
+ {
+ vuint8m2_t v0 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+ vuint8m2_t v1 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+ vuint8m2_t v2 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+ vuint8m2_t v3 = __riscv_vle8_v_u8m2 ((void *) it, vl);
+ it += vl;
+
+ asm volatile("nop" ::: "memory");
+ vint32m8_t vw0 = __riscv_vluxei8_v_i32m8 ((void *) it, v0, vl);
+ vint32m8_t vw1 = __riscv_vluxei8_v_i32m8 ((void *) it, v1, vl);
+ vint32m8_t vw2 = __riscv_vluxei8_v_i32m8 ((void *) it, v2, vl);
+ vint32m8_t vw3 = __riscv_vluxei8_v_i32m8 ((void *) it, v3, vl);
+
+ asm volatile("nop" ::: "memory");
+ size_t sum0 = __riscv_vmv_x_s_i32m8_i32 (vw0);
+ size_t sum1 = __riscv_vmv_x_s_i32m8_i32 (vw1);
+ size_t sum2 = __riscv_vmv_x_s_i32m8_i32 (vw2);
+ size_t sum3 = __riscv_vmv_x_s_i32m8_i32 (vw3);
+
+ sum += sumation (sum0, sum1, sum2, sum3);
+ }
+ return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3)
+{
+ return sum0 + sum1 + sum2 + sum3;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+ size_t sum = 0;
+ size_t vl = __riscv_vsetvlmax_e8m8 ();
+ size_t step = vl * 4;
+ const char *it = buf, *end = buf + len;
+ for (; it + step <= end;)
+ {
+ vuint8m1_t v0 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v1 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v2 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+ vuint8m1_t v3 = __riscv_vle8_v_u8m1 ((void *) it, vl);
+ it += vl;
+
+ asm volatile("nop" ::: "memory");
+ vint64m8_t vw0 = __riscv_vluxei8_v_i64m8 ((void *) it, v0, vl);
+ vint64m8_t vw1 = __riscv_vluxei8_v_i64m8 ((void *) it, v1, vl);
+ vint64m8_t vw2 = __riscv_vluxei8_v_i64m8 ((void *) it, v2, vl);
+ vint64m8_t vw3 = __riscv_vluxei8_v_i64m8 ((void *) it, v3, vl);
+
+ asm volatile("nop" ::: "memory");
+ size_t sum0 = __riscv_vmv_x_s_i64m8_i64 (vw0);
+ size_t sum1 = __riscv_vmv_x_s_i64m8_i64 (vw1);
+ size_t sum2 = __riscv_vmv_x_s_i64m8_i64 (vw2);
+ size_t sum3 = __riscv_vmv_x_s_i64m8_i64 (vw3);
+
+ sum += sumation (sum0, sum1, sum2, sum3);
+ }
+ return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} } } */
projects / thirdparty / gcc.git / commitdiff
