From 26db39b1b7752644bdef449ed856632bea908479 Mon Sep 17 00:00:00 2001 From: NIIBE Yutaka Date: Tue, 24 Dec 2013 21:21:44 +0900 Subject: [PATCH] don't use r10 --- polarssl/include/polarssl/bn_mul.h | 54 +++++++++++++++--------------- polarssl/library/bignum.c | 40 +++++++++++----------- 2 files changed, 47 insertions(+), 47 deletions(-) diff --git a/polarssl/include/polarssl/bn_mul.h b/polarssl/include/polarssl/bn_mul.h index f5379e3..58afe0d 100644 --- a/polarssl/include/polarssl/bn_mul.h +++ b/polarssl/include/polarssl/bn_mul.h @@ -496,40 +496,40 @@ #if defined(__arm__) #define MULADDC_1024_CORE \ - "ldmia %0!, { r8, r9, r10 } \n\t" \ + "ldmia %0!, { r8, r9, r12 } \n\t" \ "ldmia %1, { r5, r6, r7 } \n\t" \ "adcs r5, r5, %2 \n\t" \ - "umull r4, r12, r8, %4 \n\t" \ - "adc %2, r12, #0 \n\t" \ - "adds r5, r5, r4 \n\t" \ + "umull r4, r8, r8, %4 \n\t" \ + "adc %2, r8, #0 \n\t" \ + "adds r5, r5, r4 \n\t" \ "adcs r6, r6, %2 \n\t" \ - "umull r4, r12, r9, %4 \n\t" \ - "adc %2, r12, #0 \n\t" \ - "adds r6, r6, r4 \n\t" \ + "umull r4, r8, r9, %4 \n\t" \ + "adc %2, r8, #0 \n\t" \ + "adds r6, r6, r4 \n\t" \ "adcs r7, r7, %2 \n\t" \ - "umull r4, r12, r10, %4 \n\t" \ - "adc %2, r12, #0 \n\t" \ - "adds r7, r7, r4 \n\t" \ + "umull r4, r8, r12, %4 \n\t" \ + "adc %2, r8, #0 \n\t" \ + "adds r7, r7, r4 \n\t" \ "stmia %1!, { r5, r6, r7 } \n\t" #define MULADDC_1024_LOOP \ asm( "tst %3, #0xfe0 \n\t" \ "beq 0f \n" \ "1: sub %3, %3, #32 \n\t" \ - "ldmia %0!, { r8, r9, r10 } \n\t" \ + "ldmia %0!, { r8, r9, r12 } \n\t" \ "ldmia %1, { r5, r6, r7 } \n\t" \ "adds r5, r5, %2 \n\t" \ - "umull r4, r12, %4, r8 \n\t" \ - "adc %2, r12, #0 \n\t" \ - "adds r5, r5, r4 \n\t" \ + "umull r4, r8, %4, r8 \n\t" \ + "adc %2, r8, #0 \n\t" \ + "adds r5, r5, r4 \n\t" \ "adcs r6, r6, %2 \n\t" \ - "umull r4, r12, %4, r9 \n\t" \ - "adc %2, r12, #0 \n\t" \ - "adds r6, r6, r4 \n\t" \ + "umull r4, r8, %4, r9 \n\t" \ + "adc %2, r8, #0 \n\t" \ + "adds r6, r6, r4 \n\t" \ "adcs r7, r7, %2 \n\t" \ - "umull r4, r12, %4, r10 \n\t" \ - "adc %2, r12, #0 \n\t" \ - "adds r7, r7, r4 \n\t" \ + "umull r4, r8, %4, r12 \n\t" \ + "adc %2, r8, #0 \n\t" \ + "adds r7, r7, r4 \n\t" \ "stmia %1!, { r5, r6, r7 } \n\t" \ MULADDC_1024_CORE MULADDC_1024_CORE \ MULADDC_1024_CORE MULADDC_1024_CORE \ @@ -539,13 +539,13 @@ "ldmia %0!, { r8, r9 } \n\t" \ "ldmia %1, { r5, r6 } \n\t" \ "adcs r5, r5, %2 \n\t" \ - "umull r4, r12, %4, r8 \n\t" \ - "adc %2, r12, #0 \n\t" \ - "adds r5, r5, r4 \n\t" \ + "umull r4, r8, %4, r8 \n\t" \ + "adc %2, r8, #0 \n\t" \ + "adds r5, r5, r4 \n\t" \ "adcs r6, r6, %2 \n\t" \ - "umull r4, r12, %4, r9 \n\t" \ - "adc %2, r12, #0 \n\t" \ - "adds r6, r6, r4 \n\t" \ + "umull r4, r8, %4, r9 \n\t" \ + "adc %2, r8, #0 \n\t" \ + "adds r6, r6, r4 \n\t" \ "stmia %1!, { r5, r6 } \n\t" \ "adc %2, %2, #0 \n\t" \ "tst %3, #0xfe0 \n\t" \ @@ -553,7 +553,7 @@ "0:" \ : "=r" (s), "=r" (d), "=r" (c), "=r" (i) \ : "r" (b), "0" (s), "1" (d), "2" (c), "3" (i) \ - : "r4", "r5", "r6", "r7", "r8", "r9", "r10", "r12", "memory", "cc" ); + : "r4", "r5", "r6", "r7", "r8", "r9", "r12", "memory", "cc" ); /* Just for reference (dead code) */ #define MULADDC_HUIT \ diff --git a/polarssl/library/bignum.c b/polarssl/library/bignum.c index dd04c02..f4af839 100644 --- a/polarssl/library/bignum.c +++ b/polarssl/library/bignum.c @@ -1467,53 +1467,53 @@ static void mpi_montsqr( size_t n, const t_uint *np, t_uint mm, t_uint *d ) asm (/* (C,R4,R5) := w_i_i + x_i*x_i; w_i_i := R5; */ "ldr r5, [%[wij]]\n\t" /* R5 := w_i_i; */ "mov %[c], #0\n\t" - "umull r6, r12, %[x_i], %[x_i]\n\t" - "adds r5, r5, r6\n\t" + "umull r7, r12, %[x_i], %[x_i]\n\t" + "adds r5, r5, r7\n\t" "adc r4, r12, #0\n\t" "str r5, [%[wij]], #4\n\t" "cmp %[xj], %[x_max1]\n\t" - "bhi 0f\n" + "bhi 0f\n\t" "mov r8, %[c]\n\t" /* R8 := 0, the constant ZERO from here. */ - "beq 1f\n\t" + "beq 1f\n" "2:\n\t" - "ldmia %[xj]!, { r9, r10 }\n\t" - "ldmia %[wij], { r5, r7 }\n\t" + "ldmia %[xj]!, { r7, r9 }\n\t" + "ldmia %[wij], { r5, r6 }\n\t" /* (C,R4,R5) := (C,R4) + w_i_j + 2*x_i*x_j; */ - "umull r6, r12, %[x_i], r9\n\t" + "umull r7, r12, %[x_i], r7\n\t" "adds r5, r5, r4\n\t" "adc r4, %[c], r8\n\t" - "adds r5, r5, r6\n\t" + "adds r5, r5, r7\n\t" "adcs r4, r4, r12\n\t" "adc %[c], r8, r8\n\t" - "adds r5, r5, r6\n\t" + "adds r5, r5, r7\n\t" "adcs r4, r4, r12\n\t" "adc %[c], %[c], r8\n\t" - /* (C,R4,R7) := (C,R4) + w_i_j + 2*x_i*x_j; */ - "adds r7, r7, r4\n\t" + /* (C,R4,R6) := (C,R4) + w_i_j + 2*x_i*x_j; */ + "adds r6, r6, r4\n\t" "adc r4, %[c], r8\n\t" - "umull r6, r12, %[x_i], r10\n\t" - "adds r7, r7, r6\n\t" + "umull r7, r12, %[x_i], r9\n\t" + "adds r6, r6, r7\n\t" "adcs r4, r4, r12\n\t" "adc %[c], r8, r8\n\t" - "adds r7, r7, r6\n\t" + "adds r6, r6, r7\n\t" "adcs r4, r4, r12\n\t" "adc %[c], %[c], r8\n\t" /**/ - "stmia %[wij]!, { r5, r7 }\n\t" + "stmia %[wij]!, { r5, r6 }\n\t" "cmp %[xj], %[x_max1]\n\t" "bcc 2b\n\t" "bne 0f\n" "1:\n\t" /* (C,R4,R5) := (C,R4) + w_i_j + 2*x_i*x_j; */ "ldr r5, [%[wij]]\n\t" - "ldr r7, [%[xj]], #4\n\t" + "ldr r6, [%[xj]], #4\n\t" "adds r5, r5, r4\n\t" "adc r4, %[c], r8\n\t" - "umull r6, r12, %[x_i], r7\n\t" - "adds r5, r5, r6\n\t" + "umull r7, r12, %[x_i], r6\n\t" + "adds r5, r5, r7\n\t" "adcs r4, r4, r12\n\t" "adc %[c], r8, r8\n\t" - "adds r5, r5, r6\n\t" + "adds r5, r5, r7\n\t" "adcs r4, r4, r12\n\t" "adc %[c], %[c], r8\n\t" "str r5, [%[wij]], #4\n" @@ -1525,7 +1525,7 @@ static void mpi_montsqr( size_t n, const t_uint *np, t_uint mm, t_uint *d ) : [c] "=&r" (c), [wij] "=r" (wij), [xj] "=r" (xj) : [x_i] "r" (x_i), [x_max1] "r" (&d[n*2-1]), "[wij]" (wij), "[xj]" (xj) - : "r4", "r5", "r6", "r7", "r8", "r9", "r10", "r12", "memory", "cc"); + : "r4", "r5", "r6", "r7", "r8", "r9", "r12", "memory", "cc"); c += mpi_mul_hlp( n, np, &d[i], d[i] * mm ); }