OpenE2K/gcc
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

AArch64: Adjust costing of by element MUL to be the same as SAME3 MUL.

Browse Source 
The cost model is currently treating multiplication by element as being more
expensive than 3 same multiplication.  This means that if the value is on the
SIMD side we add an unneeded DUP.  If the value is on the genreg side we use the
more expensive DUP instead of fmov.

This patch corrects the costs such that the two multiplies are costed the same
which allows us to generate

        fmul    v3.4s, v3.4s, v0.s[0]

instead of

        dup     v0.4s, v0.s[0]
        fmul    v3.4s, v3.4s, v0.4s

gcc/ChangeLog:

	* config/aarch64/aarch64.c (aarch64_rtx_mult_cost): Adjust costs for mul.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/asimd-mull-elem.c: New test.
This commit is contained in:
Tamar Christina 2020-06-10 11:55:46 +01:00
parent b05d5563f4
commit df81764ba1
2 changed files with 38 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
gcc/config/aarch64/aarch64.c
View File

@ -11279,7 +11279,23 @@ aarch64_rtx_mult_cost (rtx x, enum rtx_code code, int outer, bool speed)
op1 = XEXP (x, 1);
if (VECTOR_MODE_P (mode))
mode = GET_MODE_INNER (mode);
{
unsigned int vec_flags = aarch64_classify_vector_mode (mode);
mode = GET_MODE_INNER (mode);
if (vec_flags & VEC_ADVSIMD)
{
/* The by-element versions of the instruction have the same costs as
the normal 3-vector version. So don't add the costs of the
duplicate into the costs of the multiply. We make an assumption
that the input to the VEC_DUPLICATE is already on the FP & SIMD
side. This means costing of a MUL by element pre RA is a bit
optimistic. */
if (GET_CODE (op0) == VEC_DUPLICATE)
op0 = XEXP (op0, 0);
else if (GET_CODE (op1) == VEC_DUPLICATE)
op1 = XEXP (op1, 0);
}
}
/* Integer multiply/fma. */
if (GET_MODE_CLASS (mode) == MODE_INT)

21
gcc/testsuite/gcc.target/aarch64/asimd-mull-elem.c Normal file
View File

@ -0,0 +1,21 @@
/* { dg-do compile } */
/* { dg-require-effective-target vect_int } */
/* { dg-require-effective-target vect_float } */
/* { dg-options "-Ofast" } */
#include <arm_neon.h>
void s_mult_i (int32_t* restrict res, int32_t* restrict a, int32_t b)
{
for (int x = 0; x < 16; x++)
res[x] = a[x] * b;
}
void s_mult_f (float32_t* restrict res, float32_t* restrict a, float32_t b)
{
for (int x = 0; x < 16; x++)
res[x] = a[x] * b;
}
/* { dg-final { scan-assembler-times {\s+mul\tv[0-9]+\.4s, v[0-9]+\.4s, v[0-9]+\.s\[0\]} 4 } } */
/* { dg-final { scan-assembler-times {\s+fmul\tv[0-9]+\.4s, v[0-9]+\.4s, v[0-9]+\.s\[0\]} 4 } } */