According to the issue as below.
https://hub.fgit.cf/riscv-non-isa/riscv-elf-psabi-doc/pull/416
When the mode size of vls integer mode is less than 2 * XLEN, we will
take the gpr for both the args and the return values. Instead of the
reference. For example the below code:
typedef short v8hi __attribute__ ((vector_size (16)));
v8hi __attribute__((noinline))
add (v8hi a, v8hi b)
{
v8hi r = a + b;
return r;
}
Before this patch:
add:
vsetivli zero,8,e16,m1,ta,ma
vle16.v v1,0(a1) <== arg by reference
vle16.v v2,0(a2) <== arg by reference
vadd.vv v1,v1,v2
vse16.v v1,0(a0) <== return by reference
ret
After this patch:
add:
addi sp,sp,-32
sd a0,0(sp) <== arg by register a0 - a3
sd a1,8(sp)
sd a2,16(sp)
sd a3,24(sp)
addi a5,sp,16
vsetivli zero,8,e16,m1,ta,ma
vle16.v v2,0(sp)
vle16.v v1,0(a5)
vadd.vv v1,v1,v2
vse16.v v1,0(sp)
ld a0,0(sp) <== return by a0 - a1.
ld a1,8(sp)
addi sp,sp,32
jr ra
For vls floating point, we take the same rules as integer and passed by
the gpr or reference.
The riscv regression passed for this patch.
gcc/ChangeLog:
* config/riscv/riscv.cc (riscv_v_vls_mode_aggregate_gpr_count): New function to
calculate the gpr count required by vls mode.
(riscv_v_vls_to_gpr_mode): New function convert vls mode to gpr mode.
(riscv_pass_vls_aggregate_in_gpr): New function to return the rtx of gpr
for vls mode.
(riscv_get_arg_info): Add vls mode handling.
(riscv_pass_by_reference): Return false if arg info has no zero gpr count.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/vls/def.h: Add new helper macro.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-1.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-10.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-2.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-3.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-4.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-5.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-6.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-7.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-8.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-9.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-run-1.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-run-2.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-run-3.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-run-4.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-run-5.c: New test.
* gcc.target/riscv/rvv/autovec/vls/calling-convention-run-6.c: New test.
Signed-off-by: Pan Li <pan2.li@intel.com>
|| riscv_v_ext_vls_mode_p (mode);
}
+static unsigned
+riscv_v_vls_mode_aggregate_gpr_count (unsigned vls_unit_size,
+ unsigned scalar_unit_size)
+{
+ gcc_assert (vls_unit_size != 0 && scalar_unit_size != 0);
+
+ if (vls_unit_size < scalar_unit_size)
+ return 1;
+
+ /* Ensure the vls mode is exact_div by scalar_unit_size. */
+ gcc_assert ((vls_unit_size % scalar_unit_size) == 0);
+
+ return vls_unit_size / scalar_unit_size;
+}
+
+static machine_mode
+riscv_v_vls_to_gpr_mode (unsigned vls_mode_size)
+{
+ switch (vls_mode_size)
+ {
+ case 16:
+ return TImode;
+ case 8:
+ return DImode;
+ case 4:
+ return SImode;
+ case 2:
+ return HImode;
+ case 1:
+ return QImode;
+ default:
+ gcc_unreachable ();
+ }
+}
+
/* Call from ADJUST_NUNITS in riscv-modes.def. Return the correct
NUNITS size for corresponding machine_mode. */
GEN_INT (offset2))));
}
+static rtx
+riscv_pass_vls_aggregate_in_gpr (struct riscv_arg_info *info, machine_mode mode,
+ unsigned gpr_base)
+{
+ gcc_assert (riscv_v_ext_vls_mode_p (mode));
+
+ unsigned count = 0;
+ unsigned regnum = 0;
+ machine_mode gpr_mode = VOIDmode;
+ unsigned vls_size = GET_MODE_SIZE (mode).to_constant ();
+ unsigned gpr_size = GET_MODE_SIZE (Xmode);
+
+ if (IN_RANGE (vls_size, 0, gpr_size * 2))
+ {
+ count = riscv_v_vls_mode_aggregate_gpr_count (vls_size, gpr_size);
+
+ if (count + info->gpr_offset <= MAX_ARGS_IN_REGISTERS)
+ {
+ regnum = gpr_base + info->gpr_offset;
+ info->num_gprs = count;
+ gpr_mode = riscv_v_vls_to_gpr_mode (vls_size);
+ }
+ }
+
+ if (!regnum)
+ return NULL_RTX; /* Return NULL_RTX if we cannot find a suitable reg. */
+
+ gcc_assert (gpr_mode != VOIDmode);
+
+ rtx reg = gen_rtx_REG (gpr_mode, regnum);
+ rtx x = gen_rtx_EXPR_LIST (VOIDmode, reg, CONST0_RTX (gpr_mode));
+
+ return gen_rtx_PARALLEL (mode, gen_rtvec (1, x));
+}
+
/* Initialize a variable CUM of type CUMULATIVE_ARGS
for a call to a function whose data type is FNTYPE.
For a library call, FNTYPE is 0. */
/* For scalable vector argument. */
if (riscv_vector_type_p (type) && riscv_v_ext_mode_p (mode))
return riscv_get_vector_arg (info, cum, mode, return_p);
+
+ /* For vls mode aggregated in gpr. */
+ if (riscv_v_ext_vls_mode_p (mode))
+ return riscv_pass_vls_aggregate_in_gpr (info, mode, gpr_base);
}
/* Work out the size of the argument. */
if (info.num_fprs)
return false;
+ /* Don't pass by reference if we can use general register(s) for vls. */
+ if (info.num_gprs && riscv_v_ext_vls_mode_p (arg.mode))
+ return false;
+
/* Don't pass by reference if we can use vector register groups. */
if (info.num_vrs > 0 || info.num_mrs > 0)
return false;
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl4096b --param riscv-autovec-preference=scalable -mabi=lp64d -O3" } */
+
+#include "def.h"
+
+DEF_RET1_ARG0 (v1qi)
+DEF_RET1_ARG0 (v2qi)
+DEF_RET1_ARG0 (v4qi)
+DEF_RET1_ARG0 (v8qi)
+DEF_RET1_ARG0 (v16qi)
+DEF_RET1_ARG0 (v32qi)
+DEF_RET1_ARG0 (v64qi)
+DEF_RET1_ARG0 (v128qi)
+DEF_RET1_ARG0 (v256qi)
+DEF_RET1_ARG0 (v512qi)
+DEF_RET1_ARG0 (v1024qi)
+DEF_RET1_ARG0 (v2048qi)
+DEF_RET1_ARG0 (v4096qi)
+
+DEF_RET1_ARG1 (v1qi)
+DEF_RET1_ARG1 (v2qi)
+DEF_RET1_ARG1 (v4qi)
+DEF_RET1_ARG1 (v8qi)
+DEF_RET1_ARG1 (v16qi)
+DEF_RET1_ARG1 (v32qi)
+DEF_RET1_ARG1 (v64qi)
+DEF_RET1_ARG1 (v128qi)
+DEF_RET1_ARG1 (v256qi)
+DEF_RET1_ARG1 (v512qi)
+DEF_RET1_ARG1 (v1024qi)
+DEF_RET1_ARG1 (v2048qi)
+DEF_RET1_ARG1 (v4096qi)
+
+DEF_RET1_ARG2 (v1qi)
+DEF_RET1_ARG2 (v2qi)
+DEF_RET1_ARG2 (v4qi)
+DEF_RET1_ARG2 (v8qi)
+DEF_RET1_ARG2 (v16qi)
+DEF_RET1_ARG2 (v32qi)
+DEF_RET1_ARG2 (v64qi)
+DEF_RET1_ARG2 (v128qi)
+DEF_RET1_ARG2 (v256qi)
+DEF_RET1_ARG2 (v512qi)
+DEF_RET1_ARG2 (v1024qi)
+DEF_RET1_ARG2 (v2048qi)
+DEF_RET1_ARG2 (v4096qi)
+
+DEF_RET1_ARG3 (v1qi)
+DEF_RET1_ARG3 (v2qi)
+DEF_RET1_ARG3 (v4qi)
+DEF_RET1_ARG3 (v8qi)
+DEF_RET1_ARG3 (v16qi)
+DEF_RET1_ARG3 (v32qi)
+DEF_RET1_ARG3 (v64qi)
+DEF_RET1_ARG3 (v128qi)
+DEF_RET1_ARG3 (v256qi)
+DEF_RET1_ARG3 (v512qi)
+DEF_RET1_ARG3 (v1024qi)
+DEF_RET1_ARG3 (v2048qi)
+DEF_RET1_ARG3 (v4096qi)
+
+DEF_RET1_ARG4 (v1qi)
+DEF_RET1_ARG4 (v2qi)
+DEF_RET1_ARG4 (v4qi)
+DEF_RET1_ARG4 (v8qi)
+DEF_RET1_ARG4 (v16qi)
+DEF_RET1_ARG4 (v32qi)
+DEF_RET1_ARG4 (v64qi)
+DEF_RET1_ARG4 (v128qi)
+DEF_RET1_ARG4 (v256qi)
+DEF_RET1_ARG4 (v512qi)
+DEF_RET1_ARG4 (v1024qi)
+DEF_RET1_ARG4 (v2048qi)
+DEF_RET1_ARG4 (v4096qi)
+
+DEF_RET1_ARG5 (v1qi)
+DEF_RET1_ARG5 (v2qi)
+DEF_RET1_ARG5 (v4qi)
+DEF_RET1_ARG5 (v8qi)
+DEF_RET1_ARG5 (v16qi)
+DEF_RET1_ARG5 (v32qi)
+DEF_RET1_ARG5 (v64qi)
+DEF_RET1_ARG5 (v128qi)
+DEF_RET1_ARG5 (v256qi)
+DEF_RET1_ARG5 (v512qi)
+DEF_RET1_ARG5 (v1024qi)
+DEF_RET1_ARG5 (v2048qi)
+DEF_RET1_ARG5 (v4096qi)
+
+DEF_RET1_ARG6 (v1qi)
+DEF_RET1_ARG6 (v2qi)
+DEF_RET1_ARG6 (v4qi)
+DEF_RET1_ARG6 (v8qi)
+DEF_RET1_ARG6 (v16qi)
+DEF_RET1_ARG6 (v32qi)
+DEF_RET1_ARG6 (v64qi)
+DEF_RET1_ARG6 (v128qi)
+DEF_RET1_ARG6 (v256qi)
+DEF_RET1_ARG6 (v512qi)
+DEF_RET1_ARG6 (v1024qi)
+DEF_RET1_ARG6 (v2048qi)
+DEF_RET1_ARG6 (v4096qi)
+
+DEF_RET1_ARG7 (v1qi)
+DEF_RET1_ARG7 (v2qi)
+DEF_RET1_ARG7 (v4qi)
+DEF_RET1_ARG7 (v8qi)
+DEF_RET1_ARG7 (v16qi)
+DEF_RET1_ARG7 (v32qi)
+DEF_RET1_ARG7 (v64qi)
+DEF_RET1_ARG7 (v128qi)
+DEF_RET1_ARG7 (v256qi)
+DEF_RET1_ARG7 (v512qi)
+DEF_RET1_ARG7 (v1024qi)
+DEF_RET1_ARG7 (v2048qi)
+DEF_RET1_ARG7 (v4096qi)
+
+DEF_RET1_ARG8 (v1qi)
+DEF_RET1_ARG8 (v2qi)
+DEF_RET1_ARG8 (v4qi)
+DEF_RET1_ARG8 (v8qi)
+DEF_RET1_ARG8 (v16qi)
+DEF_RET1_ARG8 (v32qi)
+DEF_RET1_ARG8 (v64qi)
+DEF_RET1_ARG8 (v128qi)
+DEF_RET1_ARG8 (v256qi)
+DEF_RET1_ARG8 (v512qi)
+DEF_RET1_ARG8 (v1024qi)
+DEF_RET1_ARG8 (v2048qi)
+DEF_RET1_ARG8 (v4096qi)
+
+DEF_RET1_ARG9 (v1qi)
+DEF_RET1_ARG9 (v2qi)
+DEF_RET1_ARG9 (v4qi)
+DEF_RET1_ARG9 (v8qi)
+DEF_RET1_ARG9 (v16qi)
+DEF_RET1_ARG9 (v32qi)
+DEF_RET1_ARG9 (v64qi)
+DEF_RET1_ARG9 (v128qi)
+DEF_RET1_ARG9 (v256qi)
+DEF_RET1_ARG9 (v512qi)
+DEF_RET1_ARG9 (v1024qi)
+DEF_RET1_ARG9 (v2048qi)
+DEF_RET1_ARG9 (v4096qi)
+
+/* { dg-final { scan-assembler-times {li\s+a[0-1],\s*0} 9 } } */
+/* { dg-final { scan-assembler-times {lbu\s+a0,\s*[0-9]+\(sp\)} 8 } } */
+/* { dg-final { scan-assembler-times {lhu\s+a0,\s*[0-9]+\(sp\)} 8 } } */
+/* { dg-final { scan-assembler-times {lw\s+a0,\s*[0-9]+\(sp\)} 8 } } */
+/* { dg-final { scan-assembler-times {ld\s+a[0-1],\s*[0-9]+\(sp\)} 35 } } */
+/* { dg-final { scan-assembler-times {sb\s+a[0-7],\s*[0-9]+\(sp\)} 43 } } */
+/* { dg-final { scan-assembler-times {sh\s+a[0-7],\s*[0-9]+\(sp\)} 43 } } */
+/* { dg-final { scan-assembler-times {sw\s+a[0-7],\s*[0-9]+\(sp\)} 43 } } */
+/* { dg-final { scan-assembler-times {sd\s+a[0-7],\s*[0-9]+\(sp\)} 103 } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvfh_zvl4096b -mabi=lp64 --param riscv-autovec-preference=scalable -O3 -fno-schedule-insns -fno-schedule-insns2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "def.h"
+
+/*
+** v4hf_RET1_ARG1:
+** ret
+*/
+DEF_RET1_ARG1 (v4hf)
+
+/*
+** v2sf_RET1_ARG2:
+** addi\s+sp,\s*sp,\s*-16
+** sd\s+a0,\s*0\(sp\)
+** sd\s+a1,\s*8\(sp\)
+** ...
+** ld\s+a0,\s*0\(sp\)
+** addi\s+sp,\s*sp,\s*16
+** jr\s+ra
+*/
+DEF_RET1_ARG2 (v2sf)
+
+/*
+** v4sf_RET1_ARG2:
+** addi\s+sp,\s*sp,\s*-32
+** sd\s+a0,\s*0\(sp\)
+** sd\s+a1,\s*8\(sp\)
+** sd\s+a2,\s*16\(sp\)
+** sd\s+a3,\s*24\(sp\)
+** ...
+** ld\s+a0,\s*0\(sp\)
+** ld\s+a1,\s*8\(sp\)
+** addi\s+sp,\s*sp,\s*32
+** jr\s+ra
+*/
+DEF_RET1_ARG2 (v4sf)
+
+/*
+** v1df_RET1_ARG3:
+** addi\s+sp,\s*sp,\s*-32
+** sd\s+a0,\s*8\(sp\)
+** sd\s+a1,\s*16\(sp\)
+** sd\s+a2,\s*24\(sp\)
+** ...
+** ld\s+a0,\s*8\(sp\)
+** addi\s+sp,\s*sp,\s*32
+** jr\s+ra
+*/
+DEF_RET1_ARG3 (v1df)
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl4096b --param riscv-autovec-preference=scalable -mabi=lp64d -O3" } */
+
+#include "def.h"
+
+DEF_RET1_ARG0 (v1hi)
+DEF_RET1_ARG0 (v2hi)
+DEF_RET1_ARG0 (v4hi)
+DEF_RET1_ARG0 (v8hi)
+DEF_RET1_ARG0 (v16hi)
+DEF_RET1_ARG0 (v32hi)
+DEF_RET1_ARG0 (v64hi)
+DEF_RET1_ARG0 (v128hi)
+DEF_RET1_ARG0 (v256hi)
+DEF_RET1_ARG0 (v512hi)
+DEF_RET1_ARG0 (v1024hi)
+DEF_RET1_ARG0 (v2048hi)
+
+DEF_RET1_ARG1 (v1hi)
+DEF_RET1_ARG1 (v2hi)
+DEF_RET1_ARG1 (v4hi)
+DEF_RET1_ARG1 (v8hi)
+DEF_RET1_ARG1 (v16hi)
+DEF_RET1_ARG1 (v32hi)
+DEF_RET1_ARG1 (v64hi)
+DEF_RET1_ARG1 (v128hi)
+DEF_RET1_ARG1 (v256hi)
+DEF_RET1_ARG1 (v512hi)
+DEF_RET1_ARG1 (v1024hi)
+DEF_RET1_ARG1 (v2048hi)
+
+DEF_RET1_ARG2 (v1hi)
+DEF_RET1_ARG2 (v2hi)
+DEF_RET1_ARG2 (v4hi)
+DEF_RET1_ARG2 (v8hi)
+DEF_RET1_ARG2 (v16hi)
+DEF_RET1_ARG2 (v32hi)
+DEF_RET1_ARG2 (v64hi)
+DEF_RET1_ARG2 (v128hi)
+DEF_RET1_ARG2 (v256hi)
+DEF_RET1_ARG2 (v512hi)
+DEF_RET1_ARG2 (v1024hi)
+DEF_RET1_ARG2 (v2048hi)
+
+DEF_RET1_ARG3 (v1hi)
+DEF_RET1_ARG3 (v2hi)
+DEF_RET1_ARG3 (v4hi)
+DEF_RET1_ARG3 (v8hi)
+DEF_RET1_ARG3 (v16hi)
+DEF_RET1_ARG3 (v32hi)
+DEF_RET1_ARG3 (v64hi)
+DEF_RET1_ARG3 (v128hi)
+DEF_RET1_ARG3 (v256hi)
+DEF_RET1_ARG3 (v512hi)
+DEF_RET1_ARG3 (v1024hi)
+DEF_RET1_ARG3 (v2048hi)
+
+DEF_RET1_ARG4 (v1hi)
+DEF_RET1_ARG4 (v2hi)
+DEF_RET1_ARG4 (v4hi)
+DEF_RET1_ARG4 (v8hi)
+DEF_RET1_ARG4 (v16hi)
+DEF_RET1_ARG4 (v32hi)
+DEF_RET1_ARG4 (v64hi)
+DEF_RET1_ARG4 (v128hi)
+DEF_RET1_ARG4 (v256hi)
+DEF_RET1_ARG4 (v512hi)
+DEF_RET1_ARG4 (v1024hi)
+DEF_RET1_ARG4 (v2048hi)
+
+DEF_RET1_ARG5 (v1hi)
+DEF_RET1_ARG5 (v2hi)
+DEF_RET1_ARG5 (v4hi)
+DEF_RET1_ARG5 (v8hi)
+DEF_RET1_ARG5 (v16hi)
+DEF_RET1_ARG5 (v32hi)
+DEF_RET1_ARG5 (v64hi)
+DEF_RET1_ARG5 (v128hi)
+DEF_RET1_ARG5 (v256hi)
+DEF_RET1_ARG5 (v512hi)
+DEF_RET1_ARG5 (v1024hi)
+DEF_RET1_ARG5 (v2048hi)
+
+DEF_RET1_ARG6 (v1hi)
+DEF_RET1_ARG6 (v2hi)
+DEF_RET1_ARG6 (v4hi)
+DEF_RET1_ARG6 (v8hi)
+DEF_RET1_ARG6 (v16hi)
+DEF_RET1_ARG6 (v32hi)
+DEF_RET1_ARG6 (v64hi)
+DEF_RET1_ARG6 (v128hi)
+DEF_RET1_ARG6 (v256hi)
+DEF_RET1_ARG6 (v512hi)
+DEF_RET1_ARG6 (v1024hi)
+DEF_RET1_ARG6 (v2048hi)
+
+DEF_RET1_ARG7 (v1hi)
+DEF_RET1_ARG7 (v2hi)
+DEF_RET1_ARG7 (v4hi)
+DEF_RET1_ARG7 (v8hi)
+DEF_RET1_ARG7 (v16hi)
+DEF_RET1_ARG7 (v32hi)
+DEF_RET1_ARG7 (v64hi)
+DEF_RET1_ARG7 (v128hi)
+DEF_RET1_ARG7 (v256hi)
+DEF_RET1_ARG7 (v512hi)
+DEF_RET1_ARG7 (v1024hi)
+DEF_RET1_ARG7 (v2048hi)
+
+DEF_RET1_ARG8 (v1hi)
+DEF_RET1_ARG8 (v2hi)
+DEF_RET1_ARG8 (v4hi)
+DEF_RET1_ARG8 (v8hi)
+DEF_RET1_ARG8 (v16hi)
+DEF_RET1_ARG8 (v32hi)
+DEF_RET1_ARG8 (v64hi)
+DEF_RET1_ARG8 (v128hi)
+DEF_RET1_ARG8 (v256hi)
+DEF_RET1_ARG8 (v512hi)
+DEF_RET1_ARG8 (v1024hi)
+DEF_RET1_ARG8 (v2048hi)
+
+DEF_RET1_ARG9 (v1hi)
+DEF_RET1_ARG9 (v2hi)
+DEF_RET1_ARG9 (v4hi)
+DEF_RET1_ARG9 (v8hi)
+DEF_RET1_ARG9 (v16hi)
+DEF_RET1_ARG9 (v32hi)
+DEF_RET1_ARG9 (v64hi)
+DEF_RET1_ARG9 (v128hi)
+DEF_RET1_ARG9 (v256hi)
+DEF_RET1_ARG9 (v512hi)
+DEF_RET1_ARG9 (v1024hi)
+DEF_RET1_ARG9 (v2048hi)
+
+/* { dg-final { scan-assembler-times {li\s+a[0-1],\s*0} 8 } } */
+/* { dg-final { scan-assembler-times {lhu\s+a0,\s*[0-9]+\(sp\)} 8 } } */
+/* { dg-final { scan-assembler-times {lw\s+a0,\s*[0-9]+\(sp\)} 8 } } */
+/* { dg-final { scan-assembler-times {ld\s+a[0-1],\s*[0-9]+\(sp\)} 33 } } */
+/* { dg-final { scan-assembler-times {sh\s+a[0-7],\s*[0-9]+\(sp\)} 43 } } */
+/* { dg-final { scan-assembler-times {sw\s+a[0-7],\s*[0-9]+\(sp\)} 43 } } */
+/* { dg-final { scan-assembler-times {sd\s+a[0-7],\s*[0-9]+\(sp\)} 103 } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl4096b --param riscv-autovec-preference=scalable -mabi=lp64d -O3" } */
+
+#include "def.h"
+
+DEF_RET1_ARG0 (v1si)
+DEF_RET1_ARG0 (v2si)
+DEF_RET1_ARG0 (v4si)
+DEF_RET1_ARG0 (v8si)
+DEF_RET1_ARG0 (v16si)
+DEF_RET1_ARG0 (v32si)
+DEF_RET1_ARG0 (v64si)
+DEF_RET1_ARG0 (v128si)
+DEF_RET1_ARG0 (v256si)
+DEF_RET1_ARG0 (v512si)
+DEF_RET1_ARG0 (v1024si)
+
+DEF_RET1_ARG1 (v1si)
+DEF_RET1_ARG1 (v2si)
+DEF_RET1_ARG1 (v4si)
+DEF_RET1_ARG1 (v8si)
+DEF_RET1_ARG1 (v16si)
+DEF_RET1_ARG1 (v32si)
+DEF_RET1_ARG1 (v64si)
+DEF_RET1_ARG1 (v128si)
+DEF_RET1_ARG1 (v256si)
+DEF_RET1_ARG1 (v512si)
+DEF_RET1_ARG1 (v1024si)
+
+DEF_RET1_ARG2 (v1si)
+DEF_RET1_ARG2 (v2si)
+DEF_RET1_ARG2 (v4si)
+DEF_RET1_ARG2 (v8si)
+DEF_RET1_ARG2 (v16si)
+DEF_RET1_ARG2 (v32si)
+DEF_RET1_ARG2 (v64si)
+DEF_RET1_ARG2 (v128si)
+DEF_RET1_ARG2 (v256si)
+DEF_RET1_ARG2 (v512si)
+DEF_RET1_ARG2 (v1024si)
+
+DEF_RET1_ARG3 (v1si)
+DEF_RET1_ARG3 (v2si)
+DEF_RET1_ARG3 (v4si)
+DEF_RET1_ARG3 (v8si)
+DEF_RET1_ARG3 (v16si)
+DEF_RET1_ARG3 (v32si)
+DEF_RET1_ARG3 (v64si)
+DEF_RET1_ARG3 (v128si)
+DEF_RET1_ARG3 (v256si)
+DEF_RET1_ARG3 (v512si)
+DEF_RET1_ARG3 (v1024si)
+
+DEF_RET1_ARG4 (v1si)
+DEF_RET1_ARG4 (v2si)
+DEF_RET1_ARG4 (v4si)
+DEF_RET1_ARG4 (v8si)
+DEF_RET1_ARG4 (v16si)
+DEF_RET1_ARG4 (v32si)
+DEF_RET1_ARG4 (v64si)
+DEF_RET1_ARG4 (v128si)
+DEF_RET1_ARG4 (v256si)
+DEF_RET1_ARG4 (v512si)
+DEF_RET1_ARG4 (v1024si)
+
+DEF_RET1_ARG5 (v1si)
+DEF_RET1_ARG5 (v2si)
+DEF_RET1_ARG5 (v4si)
+DEF_RET1_ARG5 (v8si)
+DEF_RET1_ARG5 (v16si)
+DEF_RET1_ARG5 (v32si)
+DEF_RET1_ARG5 (v64si)
+DEF_RET1_ARG5 (v128si)
+DEF_RET1_ARG5 (v256si)
+DEF_RET1_ARG5 (v512si)
+DEF_RET1_ARG5 (v1024si)
+
+DEF_RET1_ARG6 (v1si)
+DEF_RET1_ARG6 (v2si)
+DEF_RET1_ARG6 (v4si)
+DEF_RET1_ARG6 (v8si)
+DEF_RET1_ARG6 (v16si)
+DEF_RET1_ARG6 (v32si)
+DEF_RET1_ARG6 (v64si)
+DEF_RET1_ARG6 (v128si)
+DEF_RET1_ARG6 (v256si)
+DEF_RET1_ARG6 (v512si)
+DEF_RET1_ARG6 (v1024si)
+
+DEF_RET1_ARG7 (v1si)
+DEF_RET1_ARG7 (v2si)
+DEF_RET1_ARG7 (v4si)
+DEF_RET1_ARG7 (v8si)
+DEF_RET1_ARG7 (v16si)
+DEF_RET1_ARG7 (v32si)
+DEF_RET1_ARG7 (v64si)
+DEF_RET1_ARG7 (v128si)
+DEF_RET1_ARG7 (v256si)
+DEF_RET1_ARG7 (v512si)
+DEF_RET1_ARG7 (v1024si)
+
+DEF_RET1_ARG8 (v1si)
+DEF_RET1_ARG8 (v2si)
+DEF_RET1_ARG8 (v4si)
+DEF_RET1_ARG8 (v8si)
+DEF_RET1_ARG8 (v16si)
+DEF_RET1_ARG8 (v32si)
+DEF_RET1_ARG8 (v64si)
+DEF_RET1_ARG8 (v128si)
+DEF_RET1_ARG8 (v256si)
+DEF_RET1_ARG8 (v512si)
+DEF_RET1_ARG8 (v1024si)
+
+DEF_RET1_ARG9 (v1si)
+DEF_RET1_ARG9 (v2si)
+DEF_RET1_ARG9 (v4si)
+DEF_RET1_ARG9 (v8si)
+DEF_RET1_ARG9 (v16si)
+DEF_RET1_ARG9 (v32si)
+DEF_RET1_ARG9 (v64si)
+DEF_RET1_ARG9 (v128si)
+DEF_RET1_ARG9 (v256si)
+DEF_RET1_ARG9 (v512si)
+DEF_RET1_ARG9 (v1024si)
+
+/* { dg-final { scan-assembler-times {li\s+a[0-1],\s*0} 7 } } */
+/* { dg-final { scan-assembler-times {lw\s+a0,\s*[0-9]+\(sp\)} 8 } } */
+/* { dg-final { scan-assembler-times {ld\s+a[0-1],\s*[0-9]+\(sp\)} 31 } } */
+/* { dg-final { scan-assembler-times {sw\s+a[0-7],\s*[0-9]+\(sp\)} 43 } } */
+/* { dg-final { scan-assembler-times {sd\s+a[0-7],\s*[0-9]+\(sp\)} 103 } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl4096b --param riscv-autovec-preference=scalable -mabi=lp64d -O3" } */
+
+#include "def.h"
+
+DEF_RET1_ARG0 (v1di)
+DEF_RET1_ARG0 (v2di)
+DEF_RET1_ARG0 (v4di)
+DEF_RET1_ARG0 (v8di)
+DEF_RET1_ARG0 (v16di)
+DEF_RET1_ARG0 (v32di)
+DEF_RET1_ARG0 (v64di)
+DEF_RET1_ARG0 (v128di)
+DEF_RET1_ARG0 (v256di)
+DEF_RET1_ARG0 (v512di)
+
+DEF_RET1_ARG1 (v1di)
+DEF_RET1_ARG1 (v2di)
+DEF_RET1_ARG1 (v4di)
+DEF_RET1_ARG1 (v8di)
+DEF_RET1_ARG1 (v16di)
+DEF_RET1_ARG1 (v32di)
+DEF_RET1_ARG1 (v64di)
+DEF_RET1_ARG1 (v128di)
+DEF_RET1_ARG1 (v256di)
+DEF_RET1_ARG1 (v512di)
+
+DEF_RET1_ARG2 (v1di)
+DEF_RET1_ARG2 (v2di)
+DEF_RET1_ARG2 (v4di)
+DEF_RET1_ARG2 (v8di)
+DEF_RET1_ARG2 (v16di)
+DEF_RET1_ARG2 (v32di)
+DEF_RET1_ARG2 (v64di)
+DEF_RET1_ARG2 (v128di)
+DEF_RET1_ARG2 (v256di)
+DEF_RET1_ARG2 (v512di)
+
+DEF_RET1_ARG3 (v1di)
+DEF_RET1_ARG3 (v2di)
+DEF_RET1_ARG3 (v4di)
+DEF_RET1_ARG3 (v8di)
+DEF_RET1_ARG3 (v16di)
+DEF_RET1_ARG3 (v32di)
+DEF_RET1_ARG3 (v64di)
+DEF_RET1_ARG3 (v128di)
+DEF_RET1_ARG3 (v256di)
+DEF_RET1_ARG3 (v512di)
+
+DEF_RET1_ARG4 (v1di)
+DEF_RET1_ARG4 (v2di)
+DEF_RET1_ARG4 (v4di)
+DEF_RET1_ARG4 (v8di)
+DEF_RET1_ARG4 (v16di)
+DEF_RET1_ARG4 (v32di)
+DEF_RET1_ARG4 (v64di)
+DEF_RET1_ARG4 (v128di)
+DEF_RET1_ARG4 (v256di)
+DEF_RET1_ARG4 (v512di)
+
+DEF_RET1_ARG5 (v1di)
+DEF_RET1_ARG5 (v2di)
+DEF_RET1_ARG5 (v4di)
+DEF_RET1_ARG5 (v8di)
+DEF_RET1_ARG5 (v16di)
+DEF_RET1_ARG5 (v32di)
+DEF_RET1_ARG5 (v64di)
+DEF_RET1_ARG5 (v128di)
+DEF_RET1_ARG5 (v256di)
+DEF_RET1_ARG5 (v512di)
+
+DEF_RET1_ARG6 (v1di)
+DEF_RET1_ARG6 (v2di)
+DEF_RET1_ARG6 (v4di)
+DEF_RET1_ARG6 (v8di)
+DEF_RET1_ARG6 (v16di)
+DEF_RET1_ARG6 (v32di)
+DEF_RET1_ARG6 (v64di)
+DEF_RET1_ARG6 (v128di)
+DEF_RET1_ARG6 (v256di)
+DEF_RET1_ARG6 (v512di)
+
+DEF_RET1_ARG7 (v1di)
+DEF_RET1_ARG7 (v2di)
+DEF_RET1_ARG7 (v4di)
+DEF_RET1_ARG7 (v8di)
+DEF_RET1_ARG7 (v16di)
+DEF_RET1_ARG7 (v32di)
+DEF_RET1_ARG7 (v64di)
+DEF_RET1_ARG7 (v128di)
+DEF_RET1_ARG7 (v256di)
+DEF_RET1_ARG7 (v512di)
+
+DEF_RET1_ARG8 (v1di)
+DEF_RET1_ARG8 (v2di)
+DEF_RET1_ARG8 (v4di)
+DEF_RET1_ARG8 (v8di)
+DEF_RET1_ARG8 (v16di)
+DEF_RET1_ARG8 (v32di)
+DEF_RET1_ARG8 (v64di)
+DEF_RET1_ARG8 (v128di)
+DEF_RET1_ARG8 (v256di)
+DEF_RET1_ARG8 (v512di)
+
+DEF_RET1_ARG9 (v1di)
+DEF_RET1_ARG9 (v2di)
+DEF_RET1_ARG9 (v4di)
+DEF_RET1_ARG9 (v8di)
+DEF_RET1_ARG9 (v16di)
+DEF_RET1_ARG9 (v32di)
+DEF_RET1_ARG9 (v64di)
+DEF_RET1_ARG9 (v128di)
+DEF_RET1_ARG9 (v256di)
+DEF_RET1_ARG9 (v512di)
+
+/* { dg-final { scan-assembler-times {li\s+a[0-1],\s*0} 6 } } */
+/* { dg-final { scan-assembler-times {ld\s+a[0-1],\s*[0-9]+\(sp\)} 29 } } */
+/* { dg-final { scan-assembler-times {sd\s+a[0-7],\s*[0-9]+\(sp\)} 103 } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvfh_zvl4096b --param riscv-autovec-preference=scalable -mabi=lp64d -O3" } */
+
+#include "def.h"
+
+DEF_RET1_ARG0 (v1hf)
+DEF_RET1_ARG0 (v2hf)
+DEF_RET1_ARG0 (v4hf)
+DEF_RET1_ARG0 (v8hf)
+DEF_RET1_ARG0 (v16hf)
+DEF_RET1_ARG0 (v32hf)
+DEF_RET1_ARG0 (v64hf)
+DEF_RET1_ARG0 (v128hf)
+DEF_RET1_ARG0 (v256hf)
+DEF_RET1_ARG0 (v512hf)
+DEF_RET1_ARG0 (v1024hf)
+DEF_RET1_ARG0 (v2048hf)
+
+DEF_RET1_ARG1 (v1hf)
+DEF_RET1_ARG1 (v2hf)
+DEF_RET1_ARG1 (v4hf)
+DEF_RET1_ARG1 (v8hf)
+DEF_RET1_ARG1 (v16hf)
+DEF_RET1_ARG1 (v32hf)
+DEF_RET1_ARG1 (v64hf)
+DEF_RET1_ARG1 (v128hf)
+DEF_RET1_ARG1 (v256hf)
+DEF_RET1_ARG1 (v512hf)
+DEF_RET1_ARG1 (v1024hf)
+DEF_RET1_ARG1 (v2048hf)
+
+DEF_RET1_ARG2 (v1hf)
+DEF_RET1_ARG2 (v2hf)
+DEF_RET1_ARG2 (v4hf)
+DEF_RET1_ARG2 (v8hf)
+DEF_RET1_ARG2 (v16hf)
+DEF_RET1_ARG2 (v32hf)
+DEF_RET1_ARG2 (v64hf)
+DEF_RET1_ARG2 (v128hf)
+DEF_RET1_ARG2 (v256hf)
+DEF_RET1_ARG2 (v512hf)
+DEF_RET1_ARG2 (v1024hf)
+DEF_RET1_ARG2 (v2048hf)
+
+DEF_RET1_ARG3 (v1hf)
+DEF_RET1_ARG3 (v2hf)
+DEF_RET1_ARG3 (v4hf)
+DEF_RET1_ARG3 (v8hf)
+DEF_RET1_ARG3 (v16hf)
+DEF_RET1_ARG3 (v32hf)
+DEF_RET1_ARG3 (v64hf)
+DEF_RET1_ARG3 (v128hf)
+DEF_RET1_ARG3 (v256hf)
+DEF_RET1_ARG3 (v512hf)
+DEF_RET1_ARG3 (v1024hf)
+DEF_RET1_ARG3 (v2048hf)
+
+DEF_RET1_ARG4 (v1hf)
+DEF_RET1_ARG4 (v2hf)
+DEF_RET1_ARG4 (v4hf)
+DEF_RET1_ARG4 (v8hf)
+DEF_RET1_ARG4 (v16hf)
+DEF_RET1_ARG4 (v32hf)
+DEF_RET1_ARG4 (v64hf)
+DEF_RET1_ARG4 (v128hf)
+DEF_RET1_ARG4 (v256hf)
+DEF_RET1_ARG4 (v512hf)
+DEF_RET1_ARG4 (v1024hf)
+DEF_RET1_ARG4 (v2048hf)
+
+DEF_RET1_ARG5 (v1hf)
+DEF_RET1_ARG5 (v2hf)
+DEF_RET1_ARG5 (v4hf)
+DEF_RET1_ARG5 (v8hf)
+DEF_RET1_ARG5 (v16hf)
+DEF_RET1_ARG5 (v32hf)
+DEF_RET1_ARG5 (v64hf)
+DEF_RET1_ARG5 (v128hf)
+DEF_RET1_ARG5 (v256hf)
+DEF_RET1_ARG5 (v512hf)
+DEF_RET1_ARG5 (v1024hf)
+DEF_RET1_ARG5 (v2048hf)
+
+DEF_RET1_ARG6 (v1hf)
+DEF_RET1_ARG6 (v2hf)
+DEF_RET1_ARG6 (v4hf)
+DEF_RET1_ARG6 (v8hf)
+DEF_RET1_ARG6 (v16hf)
+DEF_RET1_ARG6 (v32hf)
+DEF_RET1_ARG6 (v64hf)
+DEF_RET1_ARG6 (v128hf)
+DEF_RET1_ARG6 (v256hf)
+DEF_RET1_ARG6 (v512hf)
+DEF_RET1_ARG6 (v1024hf)
+DEF_RET1_ARG6 (v2048hf)
+
+DEF_RET1_ARG7 (v1hf)
+DEF_RET1_ARG7 (v2hf)
+DEF_RET1_ARG7 (v4hf)
+DEF_RET1_ARG7 (v8hf)
+DEF_RET1_ARG7 (v16hf)
+DEF_RET1_ARG7 (v32hf)
+DEF_RET1_ARG7 (v64hf)
+DEF_RET1_ARG7 (v128hf)
+DEF_RET1_ARG7 (v256hf)
+DEF_RET1_ARG7 (v512hf)
+DEF_RET1_ARG7 (v1024hf)
+DEF_RET1_ARG7 (v2048hf)
+
+DEF_RET1_ARG8 (v1hf)
+DEF_RET1_ARG8 (v2hf)
+DEF_RET1_ARG8 (v4hf)
+DEF_RET1_ARG8 (v8hf)
+DEF_RET1_ARG8 (v16hf)
+DEF_RET1_ARG8 (v32hf)
+DEF_RET1_ARG8 (v64hf)
+DEF_RET1_ARG8 (v128hf)
+DEF_RET1_ARG8 (v256hf)
+DEF_RET1_ARG8 (v512hf)
+DEF_RET1_ARG8 (v1024hf)
+DEF_RET1_ARG8 (v2048hf)
+
+DEF_RET1_ARG9 (v1hf)
+DEF_RET1_ARG9 (v2hf)
+DEF_RET1_ARG9 (v4hf)
+DEF_RET1_ARG9 (v8hf)
+DEF_RET1_ARG9 (v16hf)
+DEF_RET1_ARG9 (v32hf)
+DEF_RET1_ARG9 (v64hf)
+DEF_RET1_ARG9 (v128hf)
+DEF_RET1_ARG9 (v256hf)
+DEF_RET1_ARG9 (v512hf)
+DEF_RET1_ARG9 (v1024hf)
+DEF_RET1_ARG9 (v2048hf)
+
+/* { dg-final { scan-assembler-times {li\s+a[0-1],\s*0} 8 } } */
+/* { dg-final { scan-assembler-times {lhu\s+a[0-1],\s*[0-9]+\(sp\)} 8 } } */
+/* { dg-final { scan-assembler-times {lw\s+a[0-1],\s*[0-9]+\(sp\)} 8 } } */
+/* { dg-final { scan-assembler-times {sh\s+a[0-7],\s*[0-9]+\(sp\)} 43 } } */
+/* { dg-final { scan-assembler-times {sw\s+a[0-7],\s*[0-9]+\(sp\)} 43 } } */
+/* { dg-final { scan-assembler-times {sd\s+a[0-7],\s*[0-9]+\(sp\)} 103 } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl4096b --param riscv-autovec-preference=scalable -mabi=lp64d -O3" } */
+
+#include "def.h"
+
+DEF_RET1_ARG0 (v1sf)
+DEF_RET1_ARG0 (v2sf)
+DEF_RET1_ARG0 (v4sf)
+DEF_RET1_ARG0 (v8sf)
+DEF_RET1_ARG0 (v16sf)
+DEF_RET1_ARG0 (v32sf)
+DEF_RET1_ARG0 (v64sf)
+DEF_RET1_ARG0 (v128sf)
+DEF_RET1_ARG0 (v256sf)
+DEF_RET1_ARG0 (v512sf)
+DEF_RET1_ARG0 (v1024sf)
+
+DEF_RET1_ARG1 (v1sf)
+DEF_RET1_ARG1 (v2sf)
+DEF_RET1_ARG1 (v4sf)
+DEF_RET1_ARG1 (v8sf)
+DEF_RET1_ARG1 (v16sf)
+DEF_RET1_ARG1 (v32sf)
+DEF_RET1_ARG1 (v64sf)
+DEF_RET1_ARG1 (v128sf)
+DEF_RET1_ARG1 (v256sf)
+DEF_RET1_ARG1 (v512sf)
+DEF_RET1_ARG1 (v1024sf)
+
+DEF_RET1_ARG2 (v1sf)
+DEF_RET1_ARG2 (v2sf)
+DEF_RET1_ARG2 (v4sf)
+DEF_RET1_ARG2 (v8sf)
+DEF_RET1_ARG2 (v16sf)
+DEF_RET1_ARG2 (v32sf)
+DEF_RET1_ARG2 (v64sf)
+DEF_RET1_ARG2 (v128sf)
+DEF_RET1_ARG2 (v256sf)
+DEF_RET1_ARG2 (v512sf)
+DEF_RET1_ARG2 (v1024sf)
+
+DEF_RET1_ARG3 (v1sf)
+DEF_RET1_ARG3 (v2sf)
+DEF_RET1_ARG3 (v4sf)
+DEF_RET1_ARG3 (v8sf)
+DEF_RET1_ARG3 (v16sf)
+DEF_RET1_ARG3 (v32sf)
+DEF_RET1_ARG3 (v64sf)
+DEF_RET1_ARG3 (v128sf)
+DEF_RET1_ARG3 (v256sf)
+DEF_RET1_ARG3 (v512sf)
+DEF_RET1_ARG3 (v1024sf)
+
+DEF_RET1_ARG4 (v1sf)
+DEF_RET1_ARG4 (v2sf)
+DEF_RET1_ARG4 (v4sf)
+DEF_RET1_ARG4 (v8sf)
+DEF_RET1_ARG4 (v16sf)
+DEF_RET1_ARG4 (v32sf)
+DEF_RET1_ARG4 (v64sf)
+DEF_RET1_ARG4 (v128sf)
+DEF_RET1_ARG4 (v256sf)
+DEF_RET1_ARG4 (v512sf)
+DEF_RET1_ARG4 (v1024sf)
+
+DEF_RET1_ARG5 (v1sf)
+DEF_RET1_ARG5 (v2sf)
+DEF_RET1_ARG5 (v4sf)
+DEF_RET1_ARG5 (v8sf)
+DEF_RET1_ARG5 (v16sf)
+DEF_RET1_ARG5 (v32sf)
+DEF_RET1_ARG5 (v64sf)
+DEF_RET1_ARG5 (v128sf)
+DEF_RET1_ARG5 (v256sf)
+DEF_RET1_ARG5 (v512sf)
+DEF_RET1_ARG5 (v1024sf)
+
+DEF_RET1_ARG6 (v1sf)
+DEF_RET1_ARG6 (v2sf)
+DEF_RET1_ARG6 (v4sf)
+DEF_RET1_ARG6 (v8sf)
+DEF_RET1_ARG6 (v16sf)
+DEF_RET1_ARG6 (v32sf)
+DEF_RET1_ARG6 (v64sf)
+DEF_RET1_ARG6 (v128sf)
+DEF_RET1_ARG6 (v256sf)
+DEF_RET1_ARG6 (v512sf)
+DEF_RET1_ARG6 (v1024sf)
+
+DEF_RET1_ARG7 (v1sf)
+DEF_RET1_ARG7 (v2sf)
+DEF_RET1_ARG7 (v4sf)
+DEF_RET1_ARG7 (v8sf)
+DEF_RET1_ARG7 (v16sf)
+DEF_RET1_ARG7 (v32sf)
+DEF_RET1_ARG7 (v64sf)
+DEF_RET1_ARG7 (v128sf)
+DEF_RET1_ARG7 (v256sf)
+DEF_RET1_ARG7 (v512sf)
+DEF_RET1_ARG7 (v1024sf)
+
+DEF_RET1_ARG8 (v1sf)
+DEF_RET1_ARG8 (v2sf)
+DEF_RET1_ARG8 (v4sf)
+DEF_RET1_ARG8 (v8sf)
+DEF_RET1_ARG8 (v16sf)
+DEF_RET1_ARG8 (v32sf)
+DEF_RET1_ARG8 (v64sf)
+DEF_RET1_ARG8 (v128sf)
+DEF_RET1_ARG8 (v256sf)
+DEF_RET1_ARG8 (v512sf)
+DEF_RET1_ARG8 (v1024sf)
+
+DEF_RET1_ARG9 (v1sf)
+DEF_RET1_ARG9 (v2sf)
+DEF_RET1_ARG9 (v4sf)
+DEF_RET1_ARG9 (v8sf)
+DEF_RET1_ARG9 (v16sf)
+DEF_RET1_ARG9 (v32sf)
+DEF_RET1_ARG9 (v64sf)
+DEF_RET1_ARG9 (v128sf)
+DEF_RET1_ARG9 (v256sf)
+DEF_RET1_ARG9 (v512sf)
+DEF_RET1_ARG9 (v1024sf)
+
+/* { dg-final { scan-assembler-times {li\s+a[0-1],\s*0} 7 } } */
+/* { dg-final { scan-assembler-times {lw\s+a[0-1],\s*[0-9]+\(sp\)} 8 } } */
+/* { dg-final { scan-assembler-times {sw\s+a[0-7],\s*[0-9]+\(sp\)} 43 } } */
+/* { dg-final { scan-assembler-times {sd\s+a[0-7],\s*[0-9]+\(sp\)} 103 } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl4096b --param riscv-autovec-preference=scalable -mabi=lp64d -O3" } */
+
+#include "def.h"
+
+DEF_RET1_ARG0 (v1df)
+DEF_RET1_ARG0 (v2df)
+DEF_RET1_ARG0 (v4df)
+DEF_RET1_ARG0 (v8df)
+DEF_RET1_ARG0 (v16df)
+DEF_RET1_ARG0 (v32df)
+DEF_RET1_ARG0 (v64df)
+DEF_RET1_ARG0 (v128df)
+DEF_RET1_ARG0 (v256df)
+DEF_RET1_ARG0 (v512df)
+
+DEF_RET1_ARG1 (v1df)
+DEF_RET1_ARG1 (v2df)
+DEF_RET1_ARG1 (v4df)
+DEF_RET1_ARG1 (v8df)
+DEF_RET1_ARG1 (v16df)
+DEF_RET1_ARG1 (v32df)
+DEF_RET1_ARG1 (v64df)
+DEF_RET1_ARG1 (v128df)
+DEF_RET1_ARG1 (v256df)
+DEF_RET1_ARG1 (v512df)
+
+DEF_RET1_ARG2 (v1df)
+DEF_RET1_ARG2 (v2df)
+DEF_RET1_ARG2 (v4df)
+DEF_RET1_ARG2 (v8df)
+DEF_RET1_ARG2 (v16df)
+DEF_RET1_ARG2 (v32df)
+DEF_RET1_ARG2 (v64df)
+DEF_RET1_ARG2 (v128df)
+DEF_RET1_ARG2 (v256df)
+DEF_RET1_ARG2 (v512df)
+
+DEF_RET1_ARG3 (v1df)
+DEF_RET1_ARG3 (v2df)
+DEF_RET1_ARG3 (v4df)
+DEF_RET1_ARG3 (v8df)
+DEF_RET1_ARG3 (v16df)
+DEF_RET1_ARG3 (v32df)
+DEF_RET1_ARG3 (v64df)
+DEF_RET1_ARG3 (v128df)
+DEF_RET1_ARG3 (v256df)
+DEF_RET1_ARG3 (v512df)
+
+DEF_RET1_ARG4 (v1df)
+DEF_RET1_ARG4 (v2df)
+DEF_RET1_ARG4 (v4df)
+DEF_RET1_ARG4 (v8df)
+DEF_RET1_ARG4 (v16df)
+DEF_RET1_ARG4 (v32df)
+DEF_RET1_ARG4 (v64df)
+DEF_RET1_ARG4 (v128df)
+DEF_RET1_ARG4 (v256df)
+DEF_RET1_ARG4 (v512df)
+
+DEF_RET1_ARG5 (v1df)
+DEF_RET1_ARG5 (v2df)
+DEF_RET1_ARG5 (v4df)
+DEF_RET1_ARG5 (v8df)
+DEF_RET1_ARG5 (v16df)
+DEF_RET1_ARG5 (v32df)
+DEF_RET1_ARG5 (v64df)
+DEF_RET1_ARG5 (v128df)
+DEF_RET1_ARG5 (v256df)
+DEF_RET1_ARG5 (v512df)
+
+DEF_RET1_ARG6 (v1df)
+DEF_RET1_ARG6 (v2df)
+DEF_RET1_ARG6 (v4df)
+DEF_RET1_ARG6 (v8df)
+DEF_RET1_ARG6 (v16df)
+DEF_RET1_ARG6 (v32df)
+DEF_RET1_ARG6 (v64df)
+DEF_RET1_ARG6 (v128df)
+DEF_RET1_ARG6 (v256df)
+DEF_RET1_ARG6 (v512df)
+
+DEF_RET1_ARG7 (v1df)
+DEF_RET1_ARG7 (v2df)
+DEF_RET1_ARG7 (v4df)
+DEF_RET1_ARG7 (v8df)
+DEF_RET1_ARG7 (v16df)
+DEF_RET1_ARG7 (v32df)
+DEF_RET1_ARG7 (v64df)
+DEF_RET1_ARG7 (v128df)
+DEF_RET1_ARG7 (v256df)
+DEF_RET1_ARG7 (v512df)
+
+DEF_RET1_ARG8 (v1df)
+DEF_RET1_ARG8 (v2df)
+DEF_RET1_ARG8 (v4df)
+DEF_RET1_ARG8 (v8df)
+DEF_RET1_ARG8 (v16df)
+DEF_RET1_ARG8 (v32df)
+DEF_RET1_ARG8 (v64df)
+DEF_RET1_ARG8 (v128df)
+DEF_RET1_ARG8 (v256df)
+DEF_RET1_ARG8 (v512df)
+
+DEF_RET1_ARG9 (v1df)
+DEF_RET1_ARG9 (v2df)
+DEF_RET1_ARG9 (v4df)
+DEF_RET1_ARG9 (v8df)
+DEF_RET1_ARG9 (v16df)
+DEF_RET1_ARG9 (v32df)
+DEF_RET1_ARG9 (v64df)
+DEF_RET1_ARG9 (v128df)
+DEF_RET1_ARG9 (v256df)
+DEF_RET1_ARG9 (v512df)
+
+/* { dg-final { scan-assembler-times {li\s+a[0-1],\s*0} 6 } } */
+/* { dg-final { scan-assembler-times {ld\s+a[0-1],\s*[0-9]+\(sp\)} 29 } } */
+/* { dg-final { scan-assembler-times {sd\s+a[0-7],\s*[0-9]+\(sp\)} 103 } } */
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl4096b -mabi=lp64d --param riscv-autovec-preference=scalable -O3 -fno-schedule-insns -fno-schedule-insns2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "def.h"
+
+/*
+** v8qi_RET1_ARG0:
+** li\s+a0,\s*0
+** ret
+*/
+DEF_RET1_ARG0 (v8qi)
+
+/*
+** v4hi_RET1_ARG1:
+** ret
+*/
+DEF_RET1_ARG1 (v4hi)
+
+/*
+** v2si_RET1_ARG2:
+** addi\s+sp,\s*sp,\s*-16
+** sd\s+a0,\s*0\(sp\)
+** sd\s+a1,\s*8\(sp\)
+** ...
+** ld\s+a0,\s*0\(sp\)
+** addi\s+sp,\s*sp,\s*16
+** jr\s+ra
+*/
+DEF_RET1_ARG2 (v2si)
+
+/*
+** v1di_RET1_ARG3:
+** addi\s+sp,\s*sp,\s*-32
+** sd\s+a0,\s*8\(sp\)
+** sd\s+a1,\s*16\(sp\)
+** sd\s+a2,\s*24\(sp\)
+** ...
+** ld\s+a0,\s*8\(sp\)
+** addi\s+sp,\s*sp,\s*32
+** jr\s+ra
+*/
+DEF_RET1_ARG3 (v1di)
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvfh_zvl4096b -mabi=lp64d --param riscv-autovec-preference=scalable -O3 -fno-schedule-insns -fno-schedule-insns2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "def.h"
+
+/*
+** v4hf_RET1_ARG1:
+** ret
+*/
+DEF_RET1_ARG1 (v4hf)
+
+/*
+** v2sf_RET1_ARG2:
+** addi\s+sp,\s*sp,\s*-16
+** sd\s+a0,\s*0\(sp\)
+** sd\s+a1,\s*8\(sp\)
+** ...
+** ld\s+a0,\s*0\(sp\)
+** addi\s+sp,\s*sp,\s*16
+** jr\s+ra
+*/
+DEF_RET1_ARG2 (v2sf)
+
+/*
+** v4sf_RET1_ARG2:
+** addi\s+sp,\s*sp,\s*-32
+** sd\s+a0,\s*0\(sp\)
+** sd\s+a1,\s*8\(sp\)
+** sd\s+a2,\s*16\(sp\)
+** sd\s+a3,\s*24\(sp\)
+** ...
+** ld\s+a0,\s*0\(sp\)
+** ld\s+a1,\s*8\(sp\)
+** addi\s+sp,\s*sp,\s*32
+** jr\s+ra
+*/
+DEF_RET1_ARG2 (v4sf)
+
+/*
+** v1df_RET1_ARG3:
+** addi\s+sp,\s*sp,\s*-32
+** sd\s+a0,\s*8\(sp\)
+** sd\s+a1,\s*16\(sp\)
+** sd\s+a2,\s*24\(sp\)
+** ...
+** ld\s+a0,\s*8\(sp\)
+** addi\s+sp,\s*sp,\s*32
+** jr\s+ra
+*/
+DEF_RET1_ARG3 (v1df)
--- /dev/null
+/* { dg-do run { target { riscv_v } } } */
+/* { dg-additional-options "-std=c99 -fno-vect-cost-model --param=riscv-autovec-preference=scalable" } */
+
+typedef char v16qi __attribute__ ((vector_size (16)));
+
+v16qi
+add (v16qi a1, v16qi a2, v16qi a3, v16qi a4, v16qi a5, v16qi a6, v16qi a7,
+ v16qi a8, v16qi a9)
+{
+ return a1 + a2 + a3 + a4 + a5 + a6 + a7 + a8 + a9;
+}
+
+int
+main ()
+{
+ v16qi a1 = {
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v16qi a2 = {
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v16qi a3 = {
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v16qi a4 = {
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v16qi a5 = {
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v16qi a6 = {
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v16qi a7 = {
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v16qi a8 = {
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v16qi a9 = {
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v16qi expected = {
+ 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9,
+ };
+ v16qi result = add (a1, a2, a3, a4, a5, a6, a7, a8, a9);
+
+ unsigned i;
+
+ for (i = 0; i < 16; i++)
+ if (result[i] != expected[i])
+ __builtin_abort ();
+
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_v } } } */
+/* { dg-additional-options "-std=c99 -fno-vect-cost-model --param=riscv-autovec-preference=scalable" } */
+
+typedef short v8hi __attribute__ ((vector_size (16)));
+
+v8hi
+add (v8hi a1, v8hi a2, v8hi a3, v8hi a4, v8hi a5, v8hi a6, v8hi a7,
+ v8hi a8, v8hi a9)
+{
+ return a1 + a2 + a3 + a4 + a5 + a6 + a7 + a8 + a9;
+}
+
+int
+main ()
+{
+ v8hi a1 = {
+ 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v8hi a2 = {
+ 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v8hi a3 = {
+ 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v8hi a4 = {
+ 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v8hi a5 = {
+ 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v8hi a6 = {
+ 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v8hi a7 = {
+ 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v8hi a8 = {
+ 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v8hi a9 = {
+ 1, 1, 1, 1, 1, 1, 1, 1,
+ };
+ v8hi expected = {
+ 9, 9, 9, 9, 9, 9, 9, 9,
+ };
+ v8hi result = add (a1, a2, a3, a4, a5, a6, a7, a8, a9);
+
+ unsigned i;
+
+ for (i = 0; i < 8; i++)
+ if (result[i] != expected[i])
+ __builtin_abort ();
+
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_v } } } */
+/* { dg-additional-options "-std=c99 -fno-vect-cost-model --param=riscv-autovec-preference=scalable" } */
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+v4si
+add (v4si a1, v4si a2, v4si a3, v4si a4, v4si a5, v4si a6, v4si a7,
+ v4si a8, v4si a9)
+{
+ return a1 + a2 + a3 + a4 + a5 + a6 + a7 + a8 + a9;
+}
+
+int
+main ()
+{
+ v4si a1 = {
+ 1, 1, 1, 1,
+ };
+ v4si a2 = {
+ 1, 1, 1, 1,
+ };
+ v4si a3 = {
+ 1, 1, 1, 1,
+ };
+ v4si a4 = {
+ 1, 1, 1, 1,
+ };
+ v4si a5 = {
+ 1, 1, 1, 1,
+ };
+ v4si a6 = {
+ 1, 1, 1, 1,
+ };
+ v4si a7 = {
+ 1, 1, 1, 1,
+ };
+ v4si a8 = {
+ 1, 1, 1, 1,
+ };
+ v4si a9 = {
+ 1, 1, 1, 1,
+ };
+ v4si expected = {
+ 9, 9, 9, 9,
+ };
+ v4si result = add (a1, a2, a3, a4, a5, a6, a7, a8, a9);
+
+ unsigned i;
+
+ for (i = 0; i < 4; i++)
+ if (result[i] != expected[i])
+ __builtin_abort ();
+
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_v } } } */
+/* { dg-additional-options "-std=c99 -fno-vect-cost-model --param=riscv-autovec-preference=scalable" } */
+
+typedef long long v2di __attribute__ ((vector_size (16)));
+
+v2di
+add (v2di a1, v2di a2, v2di a3, v2di a4, v2di a5, v2di a6, v2di a7,
+ v2di a8, v2di a9)
+{
+ return a1 + a2 + a3 + a4 + a5 + a6 + a7 + a8 + a9;
+}
+
+int
+main ()
+{
+ v2di a1 = {
+ 1, 1,
+ };
+ v2di a2 = {
+ 1, 1,
+ };
+ v2di a3 = {
+ 1, 1,
+ };
+ v2di a4 = {
+ 1, 1,
+ };
+ v2di a5 = {
+ 1, 1,
+ };
+ v2di a6 = {
+ 1, 1,
+ };
+ v2di a7 = {
+ 1, 1,
+ };
+ v2di a8 = {
+ 1, 1,
+ };
+ v2di a9 = {
+ 1, 1,
+ };
+ v2di expected = {
+ 9, 9,
+ };
+ v2di result = add (a1, a2, a3, a4, a5, a6, a7, a8, a9);
+
+ unsigned i;
+
+ for (i = 0; i < 2; i++)
+ if (result[i] != expected[i])
+ __builtin_abort ();
+
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_v } } } */
+/* { dg-additional-options "-std=c99 -fno-vect-cost-model --param=riscv-autovec-preference=scalable" } */
+
+typedef float v4sf __attribute__ ((vector_size (16)));
+
+v4sf
+add (v4sf a1, v4sf a2, v4sf a3, v4sf a4, v4sf a5, v4sf a6, v4sf a7,
+ v4sf a8, v4sf a9)
+{
+ return a1 + a2 + a3 + a4 + a5 + a6 + a7 + a8 + a9;
+}
+
+int
+main ()
+{
+ v4sf a1 = {
+ 1.0, 1.0, 1.0, 1.0,
+ };
+ v4sf a2 = {
+ 1.0, 1.0, 1.0, 1.0,
+ };
+ v4sf a3 = {
+ 1.0, 1.0, 1.0, 1.0,
+ };
+ v4sf a4 = {
+ 1.0, 1.0, 1.0, 1.0,
+ };
+ v4sf a5 = {
+ 1.0, 1.0, 1.0, 1.0,
+ };
+ v4sf a6 = {
+ 1.0, 1.0, 1.0, 1.0,
+ };
+ v4sf a7 = {
+ 1.0, 1.0, 1.0, 1.0,
+ };
+ v4sf a8 = {
+ 1.0, 1.0, 1.0, 1.0,
+ };
+ v4sf a9 = {
+ 1.0, 1.0, 1.0, 1.0,
+ };
+ v4sf expected = {
+ 9.0, 9.0, 9.0, 9.0,
+ };
+ v4sf result = add (a1, a2, a3, a4, a5, a6, a7, a8, a9);
+
+ unsigned i;
+
+ for (i = 0; i < 4; i++)
+ if (result[i] != expected[i])
+ __builtin_abort ();
+
+ return 0;
+}
--- /dev/null
+/* { dg-do run { target { riscv_v } } } */
+/* { dg-additional-options "-std=c99 -fno-vect-cost-model --param=riscv-autovec-preference=scalable" } */
+
+typedef long long v2df __attribute__ ((vector_size (16)));
+
+v2df
+add (v2df a1, v2df a2, v2df a3, v2df a4, v2df a5, v2df a6, v2df a7,
+ v2df a8, v2df a9)
+{
+ return a1 + a2 + a3 + a4 + a5 + a6 + a7 + a8 + a9;
+}
+
+int
+main ()
+{
+ v2df a1 = {
+ 1.0, 1.0,
+ };
+ v2df a2 = {
+ 1.0, 1.0,
+ };
+ v2df a3 = {
+ 1.0, 1.0,
+ };
+ v2df a4 = {
+ 1.0, 1.0,
+ };
+ v2df a5 = {
+ 1.0, 1.0,
+ };
+ v2df a6 = {
+ 1.0, 1.0,
+ };
+ v2df a7 = {
+ 1.0, 1.0,
+ };
+ v2df a8 = {
+ 1.0, 1.0,
+ };
+ v2df a9 = {
+ 1.0, 1.0,
+ };
+ v2df expected = {
+ 9.0, 9.0,
+ };
+ v2df result = add (a1, a2, a3, a4, a5, a6, a7, a8, a9);
+
+ unsigned i;
+
+ for (i = 0; i < 2; i++)
+ if (result[i] != expected[i])
+ __builtin_abort ();
+
+ return 0;
+}
TYPE1 v = {__VA_ARGS__}; \
*(TYPE1 *) out = v; \
}
+
+#define DEF_RET1_ARG0(TYPE) \
+ TYPE __attribute__((noinline)) \
+ TYPE##_RET1_ARG0 () \
+ { \
+ TYPE r = {}; \
+ return r; \
+ }
+
+#define DEF_RET1_ARG1(TYPE) \
+ TYPE __attribute__((noinline)) \
+ TYPE##_RET1_ARG1 (TYPE a1) \
+ { \
+ return a1; \
+ }
+
+#define DEF_RET1_ARG2(TYPE) \
+ TYPE __attribute__((noinline)) \
+ TYPE##_RET1_ARG2 (TYPE a1, TYPE a2) \
+ { \
+ return a1 + a2; \
+ }
+
+#define DEF_RET1_ARG3(TYPE) \
+ TYPE __attribute__((noinline)) \
+ TYPE##_RET1_ARG3 (TYPE a1, TYPE a2, TYPE a3) \
+ { \
+ return a1 + a2 + a3; \
+ }
+
+#define DEF_RET1_ARG4(TYPE) \
+ TYPE __attribute__((noinline)) \
+ TYPE##_RET1_ARG4 (TYPE a1, TYPE a2, TYPE a3, TYPE a4) \
+ { \
+ return a1 + a2 + a3 + a4; \
+ }
+
+#define DEF_RET1_ARG5(TYPE) \
+ TYPE __attribute__((noinline)) \
+ TYPE##_RET1_ARG5 (TYPE a1, TYPE a2, TYPE a3, TYPE a4, TYPE a5) \
+ { \
+ return a1 + a2 + a3 + a4 + a5; \
+ }
+
+#define DEF_RET1_ARG6(TYPE) \
+ TYPE __attribute__((noinline)) \
+ TYPE##_RET1_ARG6 (TYPE a1, TYPE a2, TYPE a3, TYPE a4, TYPE a5, TYPE a6) \
+ { \
+ return a1 + a2 + a3 + a4 + a5 + a6; \
+ }
+
+#define DEF_RET1_ARG7(TYPE) \
+ TYPE __attribute__((noinline)) \
+ TYPE##_RET1_ARG7 (TYPE a1, TYPE a2, TYPE a3, TYPE a4, TYPE a5, TYPE a6, \
+ TYPE a7) \
+ { \
+ return a1 + a2 + a3 + a4 + a5 + a6 + a7; \
+ }
+
+#define DEF_RET1_ARG8(TYPE) \
+ TYPE __attribute__((noinline)) \
+ TYPE##_RET1_ARG8 (TYPE a1, TYPE a2, TYPE a3, TYPE a4, TYPE a5, TYPE a6, \
+ TYPE a7, TYPE a8) \
+ { \
+ return a1 + a2 + a3 + a4 + a5 + a6 + a7 + a8; \
+ }
+
+#define DEF_RET1_ARG9(TYPE) \
+ TYPE __attribute__((noinline)) \
+ TYPE##_RET1_ARG9 (TYPE a1, TYPE a2, TYPE a3, TYPE a4, TYPE a5, TYPE a6, \
+ TYPE a7, TYPE a8, TYPE a9) \
+ { \
+ return a1 + a2 + a3 + a4 + a5 + a6 + a7 + a8 + a9; \
+ }
projects / thirdparty / gcc.git / commitdiff
