public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
From: Bernd Edlinger <bernd.edlinger@hotmail.de>
To: "gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Cc: Ramana Radhakrishnan <ramana.radhakrishnan@arm.com>,
	Richard Earnshaw	<richard.earnshaw@arm.com>,
	Kyrill Tkachov <kyrylo.tkachov@foss.arm.com>,
	Wilco Dijkstra <wilco.dijkstra@arm.com>
Subject: [PATCH, ARM] Further improve stack usage in sha512, part 2 (PR 77308)
Date: Sun, 18 Dec 2016 13:32:00 -0000	[thread overview]
Message-ID: <AM4PR0701MB216257873FAD30D4E8975FF0E49E0@AM4PR0701MB2162.eurprd07.prod.outlook.com> (raw)

[-- Attachment #1: Type: text/plain, Size: 555 bytes --]

Hi,

this splits the *arm_negdi2, *arm_cmpdi_insn and *arm_cmpdi_unsigned
also at split1 except for TARGET_NEON and TARGET_IWMMXT.

In the new test case the stack is reduced to about 270 bytes, except
for neon and iwmmxt, where this does not change anything.

This patch depends on [1] and [2] before it can be applied.

Bootstrapped and reg-tested on arm-linux-gnueabihf.
Is it OK for trunk?


Thanks
Bernd.



[1] https://gcc.gnu.org/ml/gcc-patches/2016-11/msg02796.html
[2] https://gcc.gnu.org/ml/gcc-patches/2016-12/msg01562.html

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: patch-pr77308-4.diff --]
[-- Type: text/x-patch; name="patch-pr77308-4.diff", Size: 9756 bytes --]

2016-12-18  Bernd Edlinger  <bernd.edlinger@hotmail.de>

	PR target/77308
	* config/arm/arm.md (*arm_negdi2, *arm_cmpdi_insn,
	*arm_cmpdi_unsigned): Split early except for TARGET_NEON and
	TARGET_IWMMXT.

testsuite:
2016-12-18  Bernd Edlinger  <bernd.edlinger@hotmail.de>

	PR target/77308
	* gcc.target/arm/pr77308-2.c: New test.

Index: gcc/config/arm/arm.md
===================================================================
--- gcc/config/arm/arm.md	(revision 243782)
+++ gcc/config/arm/arm.md	(working copy)
@@ -4689,7 +4689,7 @@
   "TARGET_32BIT"
   "#"	; rsbs %Q0, %Q1, #0; rsc %R0, %R1, #0	       (ARM)
 	; negs %Q0, %Q1    ; sbc %R0, %R1, %R1, lsl #1 (Thumb-2)
-  "&& reload_completed"
+  "&& ((!TARGET_NEON && !TARGET_IWMMXT) || reload_completed)"
   [(parallel [(set (reg:CC CC_REGNUM)
 		   (compare:CC (const_int 0) (match_dup 1)))
 	      (set (match_dup 0) (minus:SI (const_int 0) (match_dup 1)))])
@@ -7359,7 +7359,7 @@
    (clobber (match_scratch:SI 2 "=r"))]
   "TARGET_32BIT"
   "#"   ; "cmp\\t%Q0, %Q1\;sbcs\\t%2, %R0, %R1"
-  "&& reload_completed"
+  "&& ((!TARGET_NEON && !TARGET_IWMMXT) || reload_completed)"
   [(set (reg:CC CC_REGNUM)
         (compare:CC (match_dup 0) (match_dup 1)))
    (parallel [(set (reg:CC CC_REGNUM)
@@ -7383,7 +7383,10 @@
         operands[5] = gen_rtx_MINUS (SImode, operands[3], operands[4]);
       }
     operands[1] = gen_lowpart (SImode, operands[1]);
-    operands[2] = gen_lowpart (SImode, operands[2]);
+    if (can_create_pseudo_p ())
+      operands[2] = gen_reg_rtx (SImode);
+    else
+      operands[2] = gen_lowpart (SImode, operands[2]);
   }
   [(set_attr "conds" "set")
    (set_attr "length" "8")
@@ -7397,7 +7400,7 @@
 
   "TARGET_32BIT"
   "#"   ; "cmp\\t%R0, %R1\;it eq\;cmpeq\\t%Q0, %Q1"
-  "&& reload_completed"
+  "&& ((!TARGET_NEON && !TARGET_IWMMXT) || reload_completed)"
   [(set (reg:CC CC_REGNUM)
         (compare:CC (match_dup 2) (match_dup 3)))
    (cond_exec (eq:SI (reg:CC CC_REGNUM) (const_int 0))
Index: gcc/testsuite/gcc.target/arm/pr77308-2.c
===================================================================
--- gcc/testsuite/gcc.target/arm/pr77308-2.c	(revision 0)
+++ gcc/testsuite/gcc.target/arm/pr77308-2.c	(working copy)
@@ -0,0 +1,169 @@
+/* { dg-do compile } */
+/* { dg-options "-Os -Wstack-usage=2500" } */
+
+/* This is a modified algorithm with 64bit cmp and neg at the Sigma-blocks.
+   It improves the test coverage of cmpdi and negdi2 patterns.
+   Unlike the original test case these insns can reach the reload pass,
+   which may result in large stack usage.  */
+
+#define SHA_LONG64 unsigned long long
+#define U64(C)     C##ULL
+
+#define SHA_LBLOCK      16
+#define SHA512_CBLOCK   (SHA_LBLOCK*8)
+
+typedef struct SHA512state_st {
+    SHA_LONG64 h[8];
+    SHA_LONG64 Nl, Nh;
+    union {
+        SHA_LONG64 d[SHA_LBLOCK];
+        unsigned char p[SHA512_CBLOCK];
+    } u;
+    unsigned int num, md_len;
+} SHA512_CTX;
+
+static const SHA_LONG64 K512[80] = {
+    U64(0x428a2f98d728ae22), U64(0x7137449123ef65cd),
+    U64(0xb5c0fbcfec4d3b2f), U64(0xe9b5dba58189dbbc),
+    U64(0x3956c25bf348b538), U64(0x59f111f1b605d019),
+    U64(0x923f82a4af194f9b), U64(0xab1c5ed5da6d8118),
+    U64(0xd807aa98a3030242), U64(0x12835b0145706fbe),
+    U64(0x243185be4ee4b28c), U64(0x550c7dc3d5ffb4e2),
+    U64(0x72be5d74f27b896f), U64(0x80deb1fe3b1696b1),
+    U64(0x9bdc06a725c71235), U64(0xc19bf174cf692694),
+    U64(0xe49b69c19ef14ad2), U64(0xefbe4786384f25e3),
+    U64(0x0fc19dc68b8cd5b5), U64(0x240ca1cc77ac9c65),
+    U64(0x2de92c6f592b0275), U64(0x4a7484aa6ea6e483),
+    U64(0x5cb0a9dcbd41fbd4), U64(0x76f988da831153b5),
+    U64(0x983e5152ee66dfab), U64(0xa831c66d2db43210),
+    U64(0xb00327c898fb213f), U64(0xbf597fc7beef0ee4),
+    U64(0xc6e00bf33da88fc2), U64(0xd5a79147930aa725),
+    U64(0x06ca6351e003826f), U64(0x142929670a0e6e70),
+    U64(0x27b70a8546d22ffc), U64(0x2e1b21385c26c926),
+    U64(0x4d2c6dfc5ac42aed), U64(0x53380d139d95b3df),
+    U64(0x650a73548baf63de), U64(0x766a0abb3c77b2a8),
+    U64(0x81c2c92e47edaee6), U64(0x92722c851482353b),
+    U64(0xa2bfe8a14cf10364), U64(0xa81a664bbc423001),
+    U64(0xc24b8b70d0f89791), U64(0xc76c51a30654be30),
+    U64(0xd192e819d6ef5218), U64(0xd69906245565a910),
+    U64(0xf40e35855771202a), U64(0x106aa07032bbd1b8),
+    U64(0x19a4c116b8d2d0c8), U64(0x1e376c085141ab53),
+    U64(0x2748774cdf8eeb99), U64(0x34b0bcb5e19b48a8),
+    U64(0x391c0cb3c5c95a63), U64(0x4ed8aa4ae3418acb),
+    U64(0x5b9cca4f7763e373), U64(0x682e6ff3d6b2b8a3),
+    U64(0x748f82ee5defb2fc), U64(0x78a5636f43172f60),
+    U64(0x84c87814a1f0ab72), U64(0x8cc702081a6439ec),
+    U64(0x90befffa23631e28), U64(0xa4506cebde82bde9),
+    U64(0xbef9a3f7b2c67915), U64(0xc67178f2e372532b),
+    U64(0xca273eceea26619c), U64(0xd186b8c721c0c207),
+    U64(0xeada7dd6cde0eb1e), U64(0xf57d4f7fee6ed178),
+    U64(0x06f067aa72176fba), U64(0x0a637dc5a2c898a6),
+    U64(0x113f9804bef90dae), U64(0x1b710b35131c471b),
+    U64(0x28db77f523047d84), U64(0x32caab7b40c72493),
+    U64(0x3c9ebe0a15c9bebc), U64(0x431d67c49c100d4c),
+    U64(0x4cc5d4becb3e42b6), U64(0x597f299cfc657e2a),
+    U64(0x5fcb6fab3ad6faec), U64(0x6c44198c4a475817)
+};
+
+#define B(x,j)    (((SHA_LONG64)(*(((const unsigned char *)(&x))+j)))<<((7-j)*8))
+#define PULL64(x) (B(x,0)|B(x,1)|B(x,2)|B(x,3)|B(x,4)|B(x,5)|B(x,6)|B(x,7))
+#define ROTR(x,s)       (((x)>>s) | (x)<<(64-s))
+#define Sigma0(x)       (ROTR((x),28) ^ ROTR((x),34) ^ (ROTR((x),39) == (x)) ? -(x) : (x))
+#define Sigma1(x)       (ROTR((x),14) ^ ROTR(-(x),18) ^ ((long long)ROTR((x),41) < (long long)(x)) ? -(x) : (x))
+#define sigma0(x)       (ROTR((x),1)  ^ ROTR((x),8)  ^ (((x)>>7) > (x)) ? -(x) : (x))
+#define sigma1(x)       (ROTR((x),19) ^ ROTR((x),61) ^ ((long long)((x)>>6) < (long long)(x)) ? -(x) : (x))
+#define Ch(x,y,z)       (((x) & (y)) ^ ((~(x)) & (z)))
+#define Maj(x,y,z)      (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z)))
+
+#define ROUND_00_15(i,a,b,c,d,e,f,g,h)          do {    \
+        T1 += h + Sigma1(e) + Ch(e,f,g) + K512[i];      \
+        h = Sigma0(a) + Maj(a,b,c);                     \
+        d += T1;        h += T1;                } while (0)
+#define ROUND_16_80(i,j,a,b,c,d,e,f,g,h,X)      do {    \
+        s0 = X[(j+1)&0x0f];     s0 = sigma0(s0);        \
+        s1 = X[(j+14)&0x0f];    s1 = sigma1(s1);        \
+        T1 = X[(j)&0x0f] += s0 + s1 + X[(j+9)&0x0f];    \
+        ROUND_00_15(i+j,a,b,c,d,e,f,g,h);               } while (0)
+void sha512_block_data_order(SHA512_CTX *ctx, const void *in,
+                                    unsigned int num)
+{
+    const SHA_LONG64 *W = in;
+    SHA_LONG64 a, b, c, d, e, f, g, h, s0, s1, T1;
+    SHA_LONG64 X[16];
+    int i;
+
+    while (num--) {
+
+        a = ctx->h[0];
+        b = ctx->h[1];
+        c = ctx->h[2];
+        d = ctx->h[3];
+        e = ctx->h[4];
+        f = ctx->h[5];
+        g = ctx->h[6];
+        h = ctx->h[7];
+
+        T1 = X[0] = PULL64(W[0]);
+        ROUND_00_15(0, a, b, c, d, e, f, g, h);
+        T1 = X[1] = PULL64(W[1]);
+        ROUND_00_15(1, h, a, b, c, d, e, f, g);
+        T1 = X[2] = PULL64(W[2]);
+        ROUND_00_15(2, g, h, a, b, c, d, e, f);
+        T1 = X[3] = PULL64(W[3]);
+        ROUND_00_15(3, f, g, h, a, b, c, d, e);
+        T1 = X[4] = PULL64(W[4]);
+        ROUND_00_15(4, e, f, g, h, a, b, c, d);
+        T1 = X[5] = PULL64(W[5]);
+        ROUND_00_15(5, d, e, f, g, h, a, b, c);
+        T1 = X[6] = PULL64(W[6]);
+        ROUND_00_15(6, c, d, e, f, g, h, a, b);
+        T1 = X[7] = PULL64(W[7]);
+        ROUND_00_15(7, b, c, d, e, f, g, h, a);
+        T1 = X[8] = PULL64(W[8]);
+        ROUND_00_15(8, a, b, c, d, e, f, g, h);
+        T1 = X[9] = PULL64(W[9]);
+        ROUND_00_15(9, h, a, b, c, d, e, f, g);
+        T1 = X[10] = PULL64(W[10]);
+        ROUND_00_15(10, g, h, a, b, c, d, e, f);
+        T1 = X[11] = PULL64(W[11]);
+        ROUND_00_15(11, f, g, h, a, b, c, d, e);
+        T1 = X[12] = PULL64(W[12]);
+        ROUND_00_15(12, e, f, g, h, a, b, c, d);
+        T1 = X[13] = PULL64(W[13]);
+        ROUND_00_15(13, d, e, f, g, h, a, b, c);
+        T1 = X[14] = PULL64(W[14]);
+        ROUND_00_15(14, c, d, e, f, g, h, a, b);
+        T1 = X[15] = PULL64(W[15]);
+        ROUND_00_15(15, b, c, d, e, f, g, h, a);
+
+        for (i = 16; i < 80; i += 16) {
+            ROUND_16_80(i, 0, a, b, c, d, e, f, g, h, X);
+            ROUND_16_80(i, 1, h, a, b, c, d, e, f, g, X);
+            ROUND_16_80(i, 2, g, h, a, b, c, d, e, f, X);
+            ROUND_16_80(i, 3, f, g, h, a, b, c, d, e, X);
+            ROUND_16_80(i, 4, e, f, g, h, a, b, c, d, X);
+            ROUND_16_80(i, 5, d, e, f, g, h, a, b, c, X);
+            ROUND_16_80(i, 6, c, d, e, f, g, h, a, b, X);
+            ROUND_16_80(i, 7, b, c, d, e, f, g, h, a, X);
+            ROUND_16_80(i, 8, a, b, c, d, e, f, g, h, X);
+            ROUND_16_80(i, 9, h, a, b, c, d, e, f, g, X);
+            ROUND_16_80(i, 10, g, h, a, b, c, d, e, f, X);
+            ROUND_16_80(i, 11, f, g, h, a, b, c, d, e, X);
+            ROUND_16_80(i, 12, e, f, g, h, a, b, c, d, X);
+            ROUND_16_80(i, 13, d, e, f, g, h, a, b, c, X);
+            ROUND_16_80(i, 14, c, d, e, f, g, h, a, b, X);
+            ROUND_16_80(i, 15, b, c, d, e, f, g, h, a, X);
+        }
+
+        ctx->h[0] += a;
+        ctx->h[1] += b;
+        ctx->h[2] += c;
+        ctx->h[3] += d;
+        ctx->h[4] += e;
+        ctx->h[5] += f;
+        ctx->h[6] += g;
+        ctx->h[7] += h;
+
+        W += SHA_LBLOCK;
+    }
+}

             reply	other threads:[~2016-12-18 13:15 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-12-18 13:32 Bernd Edlinger [this message]
2016-12-20 15:29 ` Wilco Dijkstra
2016-12-20 18:52   ` Bernd Edlinger
2016-12-21 15:20     ` Wilco Dijkstra
2017-04-29 20:09 ` Bernd Edlinger
2017-05-12 16:55   ` [PING**2] " Bernd Edlinger
2017-06-01 16:02     ` [PING**3] " Bernd Edlinger
     [not found]     ` <d2793404-f5c5-fe88-cb16-51a38ffa05c0@hotmail.de>
2017-06-14 12:39       ` [PING**4] " Bernd Edlinger
2017-09-04 16:20   ` Kyrill Tkachov

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=AM4PR0701MB216257873FAD30D4E8975FF0E49E0@AM4PR0701MB2162.eurprd07.prod.outlook.com \
    --to=bernd.edlinger@hotmail.de \
    --cc=gcc-patches@gcc.gnu.org \
    --cc=kyrylo.tkachov@foss.arm.com \
    --cc=ramana.radhakrishnan@arm.com \
    --cc=richard.earnshaw@arm.com \
    --cc=wilco.dijkstra@arm.com \
    /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).