Hi Saurabh,
> On 13 Sep 2024, at 11:06, [email protected] wrote:
>
> External email: Use caution opening links or attachments
>
>
> The AArch64 FEAT_FAMINMAX extension is optional from Armv9.2-a and
> mandatory from Armv9.5-a. It introduces instructions for computing the
> floating point absolute maximum and minimum of the two vectors
> element-wise.
>
> This patch adds code generation for famax and famin in terms of existing
> unspecs. With this patch:
> 1. famax can be expressed as taking fmax/fmaxnm of the two operands and
> then taking absolute value of their result.
> 2. famin can be expressed as taking fmin/fminnm of the two operands and
> then taking absolute value of their result.
>
> This fusion of operators is only possible when
> -march=armv9-a+faminmax+sve flags are passed.
>
> This code generation is only available on -O2 or -O3 as that is when
> auto-vectorization is enabled.
>
> gcc/ChangeLog:
>
> * config/aarch64/aarch64-sve.md
> (*aarch64_pred_faminmax_fused): Instruction pattern for faminmax
> codegen.
> * config/aarch64/iterators.md: Attribute for faminmax codegen.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/aarch64/sve/faminmax.c: New test.
> ---
> gcc/config/aarch64/aarch64-sve.md | 29 +++++++
> gcc/config/aarch64/iterators.md | 6 ++
> .../gcc.target/aarch64/sve/faminmax.c | 85 +++++++++++++++++++
> 3 files changed, 120 insertions(+)
> create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/faminmax.c
>
diff --git a/gcc/config/aarch64/aarch64-sve.md
b/gcc/config/aarch64/aarch64-sve.md
index a5cd42be9d5..feb6438efde 100644
--- a/gcc/config/aarch64/aarch64-sve.md
+++ b/gcc/config/aarch64/aarch64-sve.md
@@ -11111,3 +11111,32 @@
return "sel\t%0.<Vetype>, %3, %2.<Vetype>, %1.<Vetype>";
}
)
A slight tangent, maybe more of a question for Richard, but should we be
putting these extensions into aarch64-sve2.md or aarch64-sve.md?
It looks like the architecture has had a major extension with SVE2 or SVE so it
made sense to create aarch64-sve2.md but now the incremental improvements can
be considered as an extension to either?
+
+;; -------------------------------------------------------------------------
+;; -- [FP] Absolute maximum and minimum
+;; -------------------------------------------------------------------------
+;; Includes:
+;; - FAMAX
+;; - FAMIN
+;; -------------------------------------------------------------------------
+
+;; Predicated floating-point absolute maximum and minimum.
+(define_insn "*aarch64_pred_faminmax_fused"
+ [(set (match_operand:SVE_FULL_F 0 "register_operand" "=w")
+ (unspec:SVE_FULL_F
+ [(match_operand:<VPRED> 1 "register_operand" "Upl")
+ (match_operand:SI 4 "aarch64_sve_gp_strictness" "w")
+ (unspec:SVE_FULL_F
+ [(match_operand 5)
+ (const_int SVE_RELAXED_GP)
+ (match_operand:SVE_FULL_F 2 "register_operand" "w")]
+ UNSPEC_COND_FABS)
+ (unspec:SVE_FULL_F
+ [(match_operand 6)
+ (const_int SVE_RELAXED_GP)
+ (match_operand:SVE_FULL_F 3 "register_operand" "w")]
+ UNSPEC_COND_FABS)]
+ SVE_COND_FP_MAXMIN))]
+ "TARGET_SVE_FAMINMAX"
+ "<faminmax_cond_uns_op>\t%0.<Vetype>, %1/m, %0.<Vetype>, %3.<Vetype>”
This output pattern is missing operand 2.
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/faminmax.c
b/gcc/testsuite/gcc.target/aarch64/sve/faminmax.c
new file mode 100644
index 00000000000..b70e19fa276
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/faminmax.c
@@ -0,0 +1,85 @@
+/* { dg-do assemble} */
I think dejagnu is pedantic about wanting the space between “assemble” and “}"
+/* { dg-additional-options "-O3 -ffast-math -march=armv9-a+sve+faminmax" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include “arm_sve.h"
+
+#pragma GCC target "+sve"
+
You already force +sve in the additional-options (though -march=armv9-a already
implies sve2 and therefore sve). I think we want one or the other.
Maybe just use the target pragma “+sve+faminmax”?
Thanks,
Kyrill
+)
