qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: berrange@redhat.com, ardb@kernel.org
Subject: [PATCH 11/18] target/s390x: Use clmul_32* routines
Date: Thu, 13 Jul 2023 22:14:28 +0100	[thread overview]
Message-ID: <20230713211435.13505-12-richard.henderson@linaro.org> (raw)
In-Reply-To: <20230713211435.13505-1-richard.henderson@linaro.org>

Use generic routines for 32-bit carry-less multiply.
Remove our local version of galois_multiply32.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/s390x/tcg/vec_int_helper.c | 70 ++++++++-----------------------
 1 file changed, 17 insertions(+), 53 deletions(-)

diff --git a/target/s390x/tcg/vec_int_helper.c b/target/s390x/tcg/vec_int_helper.c
index 523d6375bb..f5eea2330a 100644
--- a/target/s390x/tcg/vec_int_helper.c
+++ b/target/s390x/tcg/vec_int_helper.c
@@ -165,22 +165,6 @@ DEF_VCTZ(8)
 DEF_VCTZ(16)
 
 /* like binary multiplication, but XOR instead of addition */
-#define DEF_GALOIS_MULTIPLY(BITS, TBITS)                                       \
-static uint##TBITS##_t galois_multiply##BITS(uint##TBITS##_t a,                \
-                                             uint##TBITS##_t b)                \
-{                                                                              \
-    uint##TBITS##_t res = 0;                                                   \
-                                                                               \
-    while (b) {                                                                \
-        if (b & 0x1) {                                                         \
-            res = res ^ a;                                                     \
-        }                                                                      \
-        a = a << 1;                                                            \
-        b = b >> 1;                                                            \
-    }                                                                          \
-    return res;                                                                \
-}
-DEF_GALOIS_MULTIPLY(32, 64)
 
 static S390Vector galois_multiply64(uint64_t a, uint64_t b)
 {
@@ -244,24 +228,24 @@ void HELPER(gvec_vgfma16)(void *v1, const void *v2, const void *v3,
     *(Int128 *)v1 = int128_xor(r, *(Int128 *)v4);
 }
 
-#define DEF_VGFM(BITS, TBITS)                                                  \
-void HELPER(gvec_vgfm##BITS)(void *v1, const void *v2, const void *v3,         \
-                             uint32_t desc)                                    \
-{                                                                              \
-    int i;                                                                     \
-                                                                               \
-    for (i = 0; i < (128 / TBITS); i++) {                                      \
-        uint##BITS##_t a = s390_vec_read_element##BITS(v2, i * 2);             \
-        uint##BITS##_t b = s390_vec_read_element##BITS(v3, i * 2);             \
-        uint##TBITS##_t d = galois_multiply##BITS(a, b);                       \
-                                                                               \
-        a = s390_vec_read_element##BITS(v2, i * 2 + 1);                        \
-        b = s390_vec_read_element##BITS(v3, i * 2 + 1);                        \
-        d = d ^ galois_multiply32(a, b);                                       \
-        s390_vec_write_element##TBITS(v1, i, d);                               \
-    }                                                                          \
+static Int128 do_gfm32(Int128 n, Int128 m)
+{
+    Int128 e = clmul_32x2_even(n, m);
+    Int128 o = clmul_32x2_odd(n, m);
+    return int128_xor(e, o);
+}
+
+void HELPER(gvec_vgfm32)(void *v1, const void *v2, const void *v3, uint32_t d)
+{
+    *(Int128 *)v1 = do_gfm32(*(const Int128 *)v2, *(const Int128 *)v3);
+}
+
+void HELPER(gvec_vgfma32)(void *v1, const void *v2, const void *v3,
+                         const void *v4, uint32_t d)
+{
+    Int128 r = do_gfm32(*(const Int128 *)v2, *(const Int128 *)v3);
+    *(Int128 *)v1 = int128_xor(r, *(Int128 *)v4);
 }
-DEF_VGFM(32, 64)
 
 void HELPER(gvec_vgfm64)(void *v1, const void *v2, const void *v3,
                          uint32_t desc)
@@ -278,26 +262,6 @@ void HELPER(gvec_vgfm64)(void *v1, const void *v2, const void *v3,
     s390_vec_xor(v1, &tmp1, &tmp2);
 }
 
-#define DEF_VGFMA(BITS, TBITS)                                                 \
-void HELPER(gvec_vgfma##BITS)(void *v1, const void *v2, const void *v3,        \
-                              const void *v4, uint32_t desc)                   \
-{                                                                              \
-    int i;                                                                     \
-                                                                               \
-    for (i = 0; i < (128 / TBITS); i++) {                                      \
-        uint##BITS##_t a = s390_vec_read_element##BITS(v2, i * 2);             \
-        uint##BITS##_t b = s390_vec_read_element##BITS(v3, i * 2);             \
-        uint##TBITS##_t d = galois_multiply##BITS(a, b);                       \
-                                                                               \
-        a = s390_vec_read_element##BITS(v2, i * 2 + 1);                        \
-        b = s390_vec_read_element##BITS(v3, i * 2 + 1);                        \
-        d = d ^ galois_multiply32(a, b);                                       \
-        d = d ^ s390_vec_read_element##TBITS(v4, i);                           \
-        s390_vec_write_element##TBITS(v1, i, d);                               \
-    }                                                                          \
-}
-DEF_VGFMA(32, 64)
-
 void HELPER(gvec_vgfma64)(void *v1, const void *v2, const void *v3,
                           const void *v4, uint32_t desc)
 {
-- 
2.34.1



  parent reply	other threads:[~2023-07-13 21:15 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-07-13 21:14 [RFC PATCH for-8.2 00/18] crypto: Provide clmul.h and host accel Richard Henderson
2023-07-13 21:14 ` [PATCH 01/18] crypto: Add generic 8-bit carry-less multiply routines Richard Henderson
2023-07-13 21:14 ` [PATCH 02/18] target/arm: Use clmul_8* routines Richard Henderson
2023-07-13 21:43   ` Philippe Mathieu-Daudé
2023-07-13 21:14 ` [PATCH 03/18] target/s390x: " Richard Henderson
2023-07-13 21:14 ` [PATCH 04/18] target/ppc: " Richard Henderson
2023-07-13 21:14 ` [PATCH 05/18] crypto: Add generic 16-bit carry-less multiply routines Richard Henderson
2023-07-13 21:14 ` [PATCH 06/18] target/arm: Use clmul_16* routines Richard Henderson
2023-07-13 21:14 ` [PATCH 07/18] target/s390x: " Richard Henderson
2023-07-13 21:14 ` [PATCH 08/18] target/ppc: " Richard Henderson
2023-07-13 21:14 ` [PATCH 09/18] crypto: Add generic 32-bit carry-less multiply routines Richard Henderson
2023-07-13 21:14 ` [PATCH 10/18] target/arm: Use clmul_32* routines Richard Henderson
2023-07-13 21:14 ` Richard Henderson [this message]
2023-07-13 21:14 ` [PATCH 12/18] target/ppc: " Richard Henderson
2023-07-13 21:14 ` [PATCH 13/18] crypto: Add generic 64-bit carry-less multiply routine Richard Henderson
2023-07-13 21:14 ` [PATCH 14/18] target/arm: Use clmul_64 Richard Henderson
2023-07-13 21:14 ` [PATCH 15/18] target/s390x: " Richard Henderson
2023-07-13 21:14 ` [PATCH 16/18] target/ppc: " Richard Henderson
2023-07-13 21:14 ` [PATCH 17/18] host/include/i386: Implement clmul.h Richard Henderson
2023-07-19 11:52   ` Ilya Leoshkevich
2023-07-22 11:47     ` Richard Henderson
2023-07-13 21:14 ` [PATCH 18/18] host/include/aarch64: " Richard Henderson
2023-08-03 14:02 ` [RFC PATCH for-8.2 00/18] crypto: Provide clmul.h and host accel Ard Biesheuvel

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=20230713211435.13505-12-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=ardb@kernel.org \
    --cc=berrange@redhat.com \
    --cc=qemu-devel@nongnu.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 NNTP newsgroup(s).