[gcc r15-4888] target: Fix asm codegen for vfpclasss* and vcvtph2* instructions

[Antoni Boucher via Gcc-cvs]

https://gcc.gnu.org/g:9141bfdd483e2838f5dce767f1c1657710ef2daf

commit r15-4888-g9141bfdd483e2838f5dce767f1c1657710ef2daf
Author: Antoni Boucher <boua...@zoho.com>
Date:   Mon Sep 23 18:58:47 2024 -0400

    target: Fix asm codegen for vfpclasss* and vcvtph2* instructions
    
    This only happens when using -masm=intel.
    
    gcc/ChangeLog:
            PR target/116725
            * config/i386/sse.md: Fix asm generation.
    
    gcc/testsuite/ChangeLog:
            PR target/116725
            * gcc.target/i386/pr116725.c: Add test using those AVX builtins.

Diff:
---
 gcc/config/i386/sse.md                   | 10 ++++++--
 gcc/testsuite/gcc.target/i386/pr116725.c | 40 ++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 22c6c817dd75..15ed8ff99cbd 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -1312,6 +1312,12 @@
    (V8HF "w") (V8BF "w") (V4SF "k") (V2DF "q")
    (HF "w") (BF "w") (SF "k") (DF "q")])
 
+;; Pointer size override for 16-bit upper-convert modes (Intel asm dialect)
+(define_mode_attr iptrh
+ [(V32HI "") (V16SI "") (V8DI "")
+  (V16HI "") (V8SI "") (V4DI "q")
+  (V8HI "") (V4SI "q") (V2DI "k")])
+
 ;; Mapping of vector modes to VPTERNLOG suffix
 (define_mode_attr ternlogsuffix
   [(V8DI "q") (V4DI "q") (V2DI "q")
@@ -7606,7 +7612,7 @@
           [(match_operand:<ssePHmode> 1 "<round_nimm_predicate>" 
"<round_constraint>")]
           UNSPEC_US_FIX_NOTRUNC))]
   "TARGET_AVX512FP16 && <round_mode_condition>"
-  "vcvtph2<sseintconvertsignprefix><sseintconvert>\t{<round_mask_op2>%1, 
%0<mask_operand2>|%0<mask_operand2>, %1<round_mask_op2>}"
+  "vcvtph2<sseintconvertsignprefix><sseintconvert>\t{<round_mask_op2>%1, 
%0<mask_operand2>|%0<mask_operand2>, %<iptrh>1<round_mask_op2>}"
   [(set_attr "type" "ssecvt")
    (set_attr "prefix" "evex")
    (set_attr "mode" "<sseinsnmode>")])
@@ -29840,7 +29846,7 @@
            UNSPEC_FPCLASS)
          (const_int 1)))]
    "TARGET_AVX512DQ || VALID_AVX512FP16_REG_MODE(<MODE>mode)"
-   "vfpclass<ssescalarmodesuffix>\t{%2, %1, 
%0<mask_scalar_merge_operand3>|%0<mask_scalar_merge_operand3>, %1, %2}";
+   "vfpclass<ssescalarmodesuffix>\t{%2, %1, 
%0<mask_scalar_merge_operand3>|%0<mask_scalar_merge_operand3>, %<iptr>1, %2}";
   [(set_attr "type" "sse")
    (set_attr "length_immediate" "1")
    (set_attr "prefix" "evex")
diff --git a/gcc/testsuite/gcc.target/i386/pr116725.c 
b/gcc/testsuite/gcc.target/i386/pr116725.c
new file mode 100644
index 000000000000..9e5070e16e71
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr116725.c
@@ -0,0 +1,40 @@
+/* PR gcc/116725 */
+/* { dg-do assemble } */
+/* { dg-options "-masm=intel -mavx512dq -mavx512fp16 -mavx512vl" } */
+/* { dg-require-effective-target masm_intel } */
+
+#include <stdio.h>
+
+typedef double __m128d __attribute__ ((__vector_size__ (16)));
+typedef float __m128f __attribute__ ((__vector_size__ (16)));
+typedef int __v16si __attribute__ ((__vector_size__ (64)));
+typedef _Float16 __m256h __attribute__ ((__vector_size__ (32)));
+typedef long long __m512i __attribute__((__vector_size__(64)));
+typedef _Float16 __m128h __attribute__ ((__vector_size__ (16), __may_alias__));
+typedef int __v4si __attribute__ ((__vector_size__ (16)));
+typedef long long __m128i __attribute__ ((__vector_size__ (16)));
+
+int main(void) {
+    __m128d vec = {1.0, 2.0};
+    char res = __builtin_ia32_fpclasssd_mask(vec, 1, 1);
+    printf("%d\n", res);
+
+    __m128f vec2 = {1.0, 2.0, 3.0, 4.0};
+    char res2 = __builtin_ia32_fpclassss_mask(vec2, 1, 1);
+    printf("%d\n", res2);
+
+    __m128h vec3 = {2.0, 1.0, 3.0};
+    __v4si vec4 = {};
+    __v4si res3 = __builtin_ia32_vcvtph2dq128_mask(vec3, vec4, -1);
+    printf("%d\n", res3[0]);
+
+    __v4si res4 = __builtin_ia32_vcvtph2udq128_mask(vec3, vec4, -1);
+    printf("%d\n", res4[0]);
+
+    __m128i vec5 = {};
+    __m128i res5 = __builtin_ia32_vcvtph2qq128_mask(vec3, vec5, -1);
+    printf("%d\n", res5[0]);
+
+    __m128i res6 = __builtin_ia32_vcvtph2uqq128_mask(vec3, vec5, -1);
+    printf("%d\n", res6[0]);
+}