re PR target/77308 (surprisingly large stack usage for sha512 on arm)

2016-10-17  Bernd Edlinger  <bernd.edlinger@hotmail.de>

        PR target/77308
        * config/arm/arm.c (arm_emit_coreregs_64bit_shift): Clear the result
        register explicitly.
        * config/arm/arm.md (ashldi3, ashrdi3, lshrdi3): Don't FAIL if
        optimizing for size.

testsuite:
2016-10-17  Bernd Edlinger  <bernd.edlinger@hotmail.de>

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

From-SVN: r241273

5 files changed, 182 insertions, 14 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 92d06ce..3cad7bb 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2016-10-17  Bernd Edlinger  <bernd.edlinger@hotmail.de>
+
+	PR target/77308
+	* config/arm/arm.c (arm_emit_coreregs_64bit_shift): Clear the result
+	register explicitly.
+	* config/arm/arm.md (ashldi3, ashrdi3, lshrdi3): Don't FAIL if
+	optimizing for size.
+
 2016-10-17  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
 
 	* config/aarch64/aarch64.c: Delete inclusion of
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 39e3aa8..a758839 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -29216,6 +29216,10 @@ arm_emit_coreregs_64bit_shift (enum rtx_code code, rtx out, rtx in,
 	  /* Shifts by a constant less than 32.  */
 	  rtx reverse_amount = GEN_INT (32 - INTVAL (amount));
 
+	  /* Clearing the out register in DImode first avoids lots
+	     of spilling and results in less stack usage.
+	     Later this redundant insn is completely removed.  */
+	  emit_insn (SET (out, const0_rtx));
 	  emit_insn (SET (out_down, LSHIFT (code, in_down, amount)));
 	  emit_insn (SET (out_down,
 			  ORR (REV_LSHIFT (code, in_up, reverse_amount),
@@ -29227,12 +29231,11 @@ arm_emit_coreregs_64bit_shift (enum rtx_code code, rtx out, rtx in,
 	  /* Shifts by a constant greater than 31.  */
 	  rtx adj_amount = GEN_INT (INTVAL (amount) - 32);
 
+	  emit_insn (SET (out, const0_rtx));
 	  emit_insn (SET (out_down, SHIFT (code, in_up, adj_amount)));
 	  if (code == ASHIFTRT)
 	    emit_insn (gen_ashrsi3 (out_up, in_up,
 				    GEN_INT (31)));
-	  else
-	    emit_insn (SET (out_up, const0_rtx));
 	}
     }
   else
diff --git a/gcc/config/arm/arm.md b/gcc/config/arm/arm.md
index 374b54e..8393f65 100644
--- a/gcc/config/arm/arm.md
+++ b/gcc/config/arm/arm.md
@@ -4016,10 +4016,6 @@
          cheaper to have the alternate code being generated than moving
          values to iwmmxt regs and back.  */
 
-      /* If we're optimizing for size, we prefer the libgcc calls.  */
-      if (optimize_function_for_size_p (cfun))
-	FAIL;
-
       /* Expand operation using core-registers.
 	 'FAIL' would achieve the same thing, but this is a bit smarter.  */
       scratch1 = gen_reg_rtx (SImode);
@@ -4089,10 +4085,6 @@
          cheaper to have the alternate code being generated than moving
          values to iwmmxt regs and back.  */
 
-      /* If we're optimizing for size, we prefer the libgcc calls.  */
-      if (optimize_function_for_size_p (cfun))
-	FAIL;
-
       /* Expand operation using core-registers.
 	 'FAIL' would achieve the same thing, but this is a bit smarter.  */
       scratch1 = gen_reg_rtx (SImode);
@@ -4159,10 +4151,6 @@
          cheaper to have the alternate code being generated than moving
          values to iwmmxt regs and back.  */
 
-      /* If we're optimizing for size, we prefer the libgcc calls.  */
-      if (optimize_function_for_size_p (cfun))
-	FAIL;
-
       /* Expand operation using core-registers.
 	 'FAIL' would achieve the same thing, but this is a bit smarter.  */
       scratch1 = gen_reg_rtx (SImode);
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 4c5b0d4..595bd4c 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2016-09-29  Bernd Edlinger  <bernd.edlinger@hotmail.de>
+
+	PR target/77308
+	* gcc.target/arm/pr77308.c: New test.
+
 2016-10-17  David Edelsohn  <dje.gcc@gmail.com>
 
 	* lib/target-supports.exp
diff --git a/gcc/testsuite/gcc.target/arm/pr77308.c b/gcc/testsuite/gcc.target/arm/pr77308.c
new file mode 100644
index 0000000..01da80c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/pr77308.c
@@ -0,0 +1,164 @@
+/* { dg-do compile } */
+/* { dg-options "-Os -Wstack-usage=2500" } */
+
+#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))
+#define Sigma1(x)       (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41))
+#define sigma0(x)       (ROTR((x),1)  ^ ROTR((x),8)  ^ ((x)>>7))
+#define sigma1(x)       (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
+#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;
+    }
+}