From: Carl Love <cel@linux.ibm.com>
To: gcc-patches@gcc.gnu.org,
Segher Boessenkool <segher@kernel.crashing.org>,
"Kewen.Lin" <linkw@linux.ibm.com>,
"bergner@linux.ibm.com" <bergner@linux.ibm.com>
Subject: Re: [PATCH 11/13 ver 3] rs6000, extend vec_xxpermdi built-in for __int128 args
Date: Wed, 29 May 2024 09:10:01 -0700 [thread overview]
Message-ID: <7136f814-60fd-450b-a885-c2f53400b9b4@linux.ibm.com> (raw)
In-Reply-To: <59db7e45-e780-4d20-a364-526f9e45800b@linux.ibm.com>
This was patch 10 from the previous series. The patch was updated to address feedback comments.
Carl
---------------------------------------------------
rs6000, extend vec_xxpermdi built-in for __int128 args
Add a new signed and unsigned overloaded instances for vec_xxpermdi
__int128 vec_xxpermdi (__int128, __int128, const int);
__uint128 vec_xxpermdi (__uint128, __uint128, const int);
Update the documentation to include a reference to the new built-in
instances.
Add test cases for the new overloaded instances.
gcc/ChangeLog:
* config/rs6000/rs6000-overload.def (vec_xxpermdi): Add new
overloaded built-in instances.
* doc/extend.texi: Add documentation for new overloaded built-in
instances.
gcc/testsuite/ChangeLog:gcc/testsuite/ChangeLog:
* gcc.target/powerpc/vec_perm-runnable-i128.c: New test file.
---
gcc/config/rs6000/rs6000-overload.def | 4 +
gcc/doc/extend.texi | 2 +
.../powerpc/vec_perm-runnable-i128.c | 229 ++++++++++++++++++
3 files changed, 235 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/powerpc/vec_perm-runnable-i128.c
diff --git a/gcc/config/rs6000/rs6000-overload.def b/gcc/config/rs6000/rs6000-overload.def
index a210c5ad10d..45000f161e4 100644
--- a/gcc/config/rs6000/rs6000-overload.def
+++ b/gcc/config/rs6000/rs6000-overload.def
@@ -4932,6 +4932,10 @@
XXPERMDI_4SF XXPERMDI_VF
vd __builtin_vsx_xxpermdi (vd, vd, const int);
XXPERMDI_2DF XXPERMDI_VD
+ vsq __builtin_vsx_xxpermdi (vsq, vsq, const int);
+ XXPERMDI_1TI XXPERMDI_1TI
+ vuq __builtin_vsx_xxpermdi (vuq, vuq, const int);
+ XXPERMDI_1TI XXPERMDI_1TUI
[VEC_XXSLDWI, vec_xxsldwi, __builtin_vsx_xxsldwi]
vsc __builtin_vsx_xxsldwi (vsc, vsc, const int);
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index 0756230b19e..edfef1bdab7 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -22555,6 +22555,8 @@ void vec_vsx_st (vector bool char, int, signed char *);
vector double vec_xxpermdi (vector double, vector double, const int);
vector float vec_xxpermdi (vector float, vector float, const int);
vector long long vec_xxpermdi (vector long long, vector long long, const int);
+vector __int128 vec_xxpermdi (vector __int128, vector __int128, const int);
+vector __int128 vec_xxpermdi (vector __uint128, vector __uint128, const int);
vector unsigned long long vec_xxpermdi (vector unsigned long long,
vector unsigned long long, const int);
vector int vec_xxpermdi (vector int, vector int, const int);
diff --git a/gcc/testsuite/gcc.target/powerpc/vec_perm-runnable-i128.c b/gcc/testsuite/gcc.target/powerpc/vec_perm-runnable-i128.c
new file mode 100644
index 00000000000..2d5dce09404
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_perm-runnable-i128.c
@@ -0,0 +1,229 @@
+/* { dg-do run } */
+/* { dg-require-effective-target vmx_hw } */
+/* { dg-options "-save-temps" } */
+
+#include <altivec.h>
+
+#define DEBUG 0
+
+#if DEBUG
+#include <stdio.h>
+void print_i128 (unsigned __int128 val)
+{
+ printf(" 0x%016llx%016llx",
+ (unsigned long long)(val >> 64),
+ (unsigned long long)(val & 0xFFFFFFFFFFFFFFFF));
+}
+#endif
+
+extern void abort (void);
+
+union convert_union {
+ vector signed __int128 s128;
+ vector unsigned __int128 u128;
+ char val[16];
+} convert;
+
+int check_u128_result(vector unsigned __int128 vresult_u128,
+ vector unsigned __int128 expected_vresult_u128)
+{
+ /* Use a for loop to check each byte manually so the test case will
+ run with ISA 2.06.
+
+ Return 1 if they match, 0 otherwise. */
+
+ int i;
+
+ union convert_union result;
+ union convert_union expected;
+
+ result.u128 = vresult_u128;
+ expected.u128 = expected_vresult_u128;
+
+ /* Check if each byte of the result and expected match. */
+ for (i = 0; i < 16; i++)
+ {
+ if (result.val[i] != expected.val[i])
+ return 0;
+ }
+ return 1;
+}
+
+int check_s128_result(vector signed __int128 vresult_s128,
+ vector signed __int128 expected_vresult_s128)
+{
+ /* Convert the arguments to unsigned, then check equality. */
+ union convert_union result;
+ union convert_union expected;
+
+ result.s128 = vresult_s128;
+ expected.s128 = expected_vresult_s128;
+
+ return check_u128_result (result.u128, expected.u128);
+}
+
+
+int
+main (int argc, char *argv [])
+{
+ int i;
+
+ vector signed __int128 src_va_s128;
+ vector signed __int128 src_vb_s128;
+ vector signed __int128 vresult_s128;
+ vector signed __int128 expected_vresult_s128;
+
+ vector unsigned __int128 src_va_u128;
+ vector unsigned __int128 src_vb_u128;
+ vector unsigned __int128 src_vc_u128;
+ vector unsigned __int128 vresult_u128;
+ vector unsigned __int128 expected_vresult_u128;
+
+ src_va_s128 = (vector signed __int128) {0x123456789ABCDEF0};
+ src_va_s128 = src_va_s128 << 64;
+ src_va_s128 |= (vector signed __int128) {0x22446688AACCEE00};
+ src_vb_s128 = (vector signed __int128) {0xFEDCBA9876543210};
+ src_vb_s128 = src_vb_s128 << 64;
+ src_vb_s128 |= (vector signed __int128) {0x3333333333333333};
+
+ src_va_u128 = (vector unsigned __int128) {0x13579ACE02468BDF};
+ src_va_u128 = src_va_u128 << 64;
+ src_va_u128 |= (vector unsigned __int128) {0x1133557799BBDD00};
+ src_vb_u128 = (vector unsigned __int128) {0xA987654FEDCB3210};
+ src_vb_u128 = src_vb_u128 << 64;
+ src_vb_u128 |= (vector unsigned __int128) {0x5555555555555555};
+
+
+ /* Signed 128-bit arguments. */
+ vresult_s128 = vec_xxpermdi (src_va_s128, src_vb_s128, 0x1);
+
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+ /* BE expected results */
+ expected_vresult_s128 = (vector signed __int128) {0x123456789ABCDEF0};
+ expected_vresult_s128 = expected_vresult_s128 << 64;
+ expected_vresult_s128 |= (vector signed __int128) {0x3333333333333333};
+#else
+ /* LE expected results */
+ expected_vresult_s128 = (vector signed __int128) {0xFEDCBA9876543210};
+ expected_vresult_s128 = expected_vresult_s128 << 64;
+ expected_vresult_s128 |= (vector signed __int128) {0x22446688AACCEE00};
+#endif
+
+ if (!check_s128_result (vresult_s128, expected_vresult_s128))
+#if DEBUG
+ {
+ printf ("ERROR, vec_xxpermdi (src_va_s128, src_vb_s128, 0x1) result does not match expected output.\n");
+ printf (" src_va_s128: ");
+ print_i128 ((unsigned __int128) src_va_s128);
+ printf ("\n src_vb_s128: ");
+ print_i128 ((unsigned __int128) src_vb_s128);
+ printf ("\n Result: ");
+ print_i128 ((unsigned __int128) vresult_s128);
+ printf ("\n Expected result: ");
+ print_i128 ((unsigned __int128) expected_vresult_s128);
+ printf ("\n");
+ }
+#else
+ abort ();
+#endif
+
+ vresult_s128 = vec_xxpermdi (src_va_s128, src_vb_s128, 0x2);
+
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+ /* BE expected results */
+ expected_vresult_s128 = (vector signed __int128) {0x22446688AACCEE00};
+ expected_vresult_s128 = expected_vresult_s128 << 64;
+ expected_vresult_s128 |= (vector signed __int128) {0xFEDCBA9876543210};
+#else
+ /* LE expected results */
+ expected_vresult_s128 = (vector signed __int128) {0x3333333333333333};
+ expected_vresult_s128 = expected_vresult_s128 << 64;
+ expected_vresult_s128 |= (vector signed __int128) {0x123456789ABCDEF0};
+#endif
+
+ if (!check_s128_result (vresult_s128, expected_vresult_s128))
+#if DEBUG
+ {
+ printf ("ERROR, vec_xxpermdi (src_va_s128, src_vb_s128, 0x2) result does not match expected output.\n");
+ printf (" src_va_s128: ");
+ print_i128 ((unsigned __int128) src_va_s128);
+ printf ("\n src_vb_s128: ");
+ print_i128 ((unsigned __int128) src_vb_s128);
+ printf ("\n Result: ");
+ print_i128 ((unsigned __int128) vresult_s128);
+ printf ("\n Expected result: ");
+ print_i128 ((unsigned __int128) expected_vresult_s128);
+ printf ("\n");
+ }
+#else
+ abort ();
+#endif
+
+ /* Unigned arguments. */
+ vresult_u128 = vec_xxpermdi (src_va_u128, src_vb_u128, 0x1);
+
+ #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+ /* BE expected results */
+ expected_vresult_u128 = (vector unsigned __int128) {0x13579ACE02468BDF};
+ expected_vresult_u128 = expected_vresult_u128 << 64;
+ expected_vresult_u128 |= (vector unsigned __int128) {0x5555555555555555};
+#else
+ /* LE expected results */
+ expected_vresult_u128 = (vector unsigned __int128) {0xA987654FEDCB3210};
+ expected_vresult_u128 = expected_vresult_u128 << 64;
+ expected_vresult_u128 |= (vector unsigned __int128) {0x1133557799BBDD00};
+#endif
+
+ if (!check_u128_result (vresult_u128, expected_vresult_u128))
+#if DEBUG
+ {
+ printf ("ERROR, vec_xxpermdi (src_va_u128, src_vb_u128, 0x1) result does not match expected output.\n");
+ printf (" src_va_s128: ");
+ print_i128 ((unsigned __int128) src_va_s128);
+ printf ("\n src_vb_s128: ");
+ print_i128 ((unsigned __int128) src_vb_s128);
+ printf ("\n Result: ");
+ print_i128 ((unsigned __int128) vresult_u128);
+ printf ("\n Expected result: ");
+ print_i128 ((unsigned __int128) expected_vresult_u128);
+ printf ("\n");
+ }
+#else
+ abort ();
+#endif
+
+ /* Unigned arguments. */
+ vresult_u128 = vec_xxpermdi (src_va_u128, src_vb_u128, 0x2);
+
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+ /* BE expected results */
+ expected_vresult_u128 = (vector unsigned __int128) {0x1133557799BBDD00};
+ expected_vresult_u128 = expected_vresult_u128 << 64;
+ expected_vresult_u128 |= (vector unsigned __int128) {0xA987654FEDCB3210};
+#else
+ /* LE expected results */
+ expected_vresult_u128 = (vector unsigned __int128) {0x5555555555555555};
+ expected_vresult_u128 = expected_vresult_u128 << 64;
+ expected_vresult_u128 |= (vector unsigned __int128) {0x13579ACE02468BDF};
+#endif
+
+ if (!check_u128_result (vresult_u128, expected_vresult_u128))
+#if DEBUG
+ {
+ printf ("ERROR, vec_xxpermdi (src_va_u128, src_vb_u128, 0x2) result does not match expected output.\n");
+ printf (" src_va_s128: ");
+ print_i128 ((unsigned __int128) src_va_s128);
+ printf ("\n src_vb_s128: ");
+ print_i128 ((unsigned __int128) src_vb_s128);
+ printf ("\n Result: ");
+ print_i128 ((unsigned __int128) vresult_u128);
+ printf ("\n Expected result: ");
+ print_i128 ((unsigned __int128) expected_vresult_u128);
+ printf ("\n");
+ }
+#else
+ abort ();
+#endif
+
+ return 0;
+}
--
2.45.0
next prev parent reply other threads:[~2024-05-29 16:10 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-29 15:48 [PATCH 0/13 ver 3] rs6000, built-in cleanup patch series Carl Love
2024-05-29 15:52 ` [PATCH 1/13 ver 3] s6000, Remove __builtin_vsx_cmple* builtins Carl Love
2024-06-04 6:00 ` [PATCH 1/13 ver 3] rs6000, " Kewen.Lin
2024-06-05 22:25 ` Carl Love
2024-06-06 2:40 ` Kewen.Lin
2024-05-29 15:55 ` [PATCH 2/13 ver 3] rs6000, Remove __builtin_vsx_xvcvspsxws built-in Carl Love
2024-05-29 15:56 ` [PATCH 3/13 ver 3] rs6000, fix error in unsigned vector float to unsigned int built-in definition Carl Love
2024-06-04 5:58 ` Kewen.Lin
2024-05-29 15:58 ` [PATCH 4/13 ver 3] rs6000, extend the current vec_{un,}signed{e,o} built-ins Carl Love
2024-06-04 7:19 ` Kewen.Lin
2024-06-13 15:35 ` Carl Love
2024-05-29 16:00 ` [PATCH 5/13 ver 3] rs6000, Remove redundant float/double type conversions Carl Love
2024-06-04 6:20 ` Kewen.Lin
2024-05-29 16:01 ` [PATCH 6/13 ver 3] rs6000, remove duplicated built-ins of vecmergl and, vec_mergeh Carl Love
2024-05-29 16:03 ` [PATCH 7/13 ver 3] rs6000, add overloaded vec_sel with int128 arguments Carl Love
2024-06-04 5:58 ` Kewen.Lin
2024-06-13 15:35 ` Carl Love
2024-05-29 16:05 ` [PATCH 8/13 ver 3] rs6000, remove the vec_xxsel built-ins, they are, duplicates Carl Love
2024-06-04 5:58 ` Kewen.Lin
2024-05-29 16:06 ` [PATCH 9/13 ver 3] rs6000, remove __builtin_vsx_vperm_* built-ins Carl Love
2024-06-04 5:58 ` Kewen.Lin
2024-05-29 16:08 ` [PATCH 10/13 ver 3] rs6000, remove __builtin_vsx_xvnegdp and, __builtin_vsx_xvnegsp built-ins Carl Love
2024-05-29 16:10 ` Carl Love [this message]
2024-06-04 5:58 ` [PATCH 11/13 ver 3] rs6000, extend vec_xxpermdi built-in for __int128 args Kewen.Lin
2024-06-13 15:35 ` Carl Love
2024-05-29 16:11 ` [PATCH 12/13 ver 3] rs6000, remove __builtin_vsx_xvcmpeqsp_p built-in Carl Love
2024-06-04 5:59 ` Kewen.Lin
2024-05-29 16:16 ` [PATCH 13/13 ver 3] rs6000, remove vector set and vector init built-ins Carl Love
2024-06-04 5:59 ` Kewen.Lin
2024-06-13 15:35 ` Carl Love
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=7136f814-60fd-450b-a885-c2f53400b9b4@linux.ibm.com \
--to=cel@linux.ibm.com \
--cc=bergner@linux.ibm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=linkw@linux.ibm.com \
--cc=segher@kernel.crashing.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).