(CFLAGS-tst-align.c): Add -mpreferred-stack-boundary=4.

1 files changed, 44 insertions, 25 deletions

diff --git a/sysdeps/ia64/fpu/e_sqrtf.S b/sysdeps/ia64/fpu/e_sqrtf.S
index daa20454d7..1799845d6d 100644
--- a/sysdeps/ia64/fpu/e_sqrtf.S
+++ b/sysdeps/ia64/fpu/e_sqrtf.S
@@ -1,10 +1,10 @@
 .file "sqrtf.s"
 
-
-// Copyright (c) 2000 - 2003, Intel Corporation
+// Copyright (C) 2000, 2001, Intel Corporation
 // All rights reserved.
-//
-// Contributed 2000 by the Intel Numerics Group, Intel Corporation
+// 
+// Contributed 2/2/2000 by John Harrison, Ted Kubaska, Bob Norin, Shane Story,
+// and Ping Tak Peter Tang of the Computational Software Lab, Intel Corporation.
 //
 // Redistribution and use in source and binary forms, with or without
 // modification, are permitted provided that the following conditions are
@@ -20,7 +20,7 @@
 // * The name of Intel Corporation may not be used to endorse or promote
 // products derived from this software without specific prior written
 // permission.
-
+//
 // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 
 // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 
 // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
@@ -35,29 +35,27 @@
 // 
 // Intel Corporation is the author of this code, and requests that all
 // problem reports or change requests be submitted to it directly at 
-// http://www.intel.com/software/products/opensource/libraries/num.htm.
+// http://developer.intel.com/opensource.
 //
-//*********************************************************************
+// *********************************************************************
 // History:
 //
-// 02/02/00 Initial version
-// 04/04/00 Unwind support added
-// 08/15/00 Bundle added after call to __libm_error_support to properly
+// 2/02/00  Initial version
+// 4/04/00  Unwind support added
+// 8/15/00  Bundle added after call to __libm_error_support to properly
 //          set [the previously overwritten] GR_Parameter_RESULT.
-// 05/20/02 Cleaned up namespace and sf0 syntax
-// 02/10/03 Reordered header: .section, .global, .proc, .align
 //
-//*********************************************************************
+// *********************************************************************
 //
 // Function:   Combined sqrtf(x), where
 //                         _
 //             sqrtf(x) = |x, for single precision x values
 //
-//********************************************************************
+// ********************************************************************
 //
 // Accuracy:       Correctly Rounded 
 //
-//********************************************************************
+// ********************************************************************
 //
 // Resources Used:
 //
@@ -70,7 +68,7 @@
 //
 //    Predicate Registers:      p6, p7, p8
 //
-//********************************************************************
+// ********************************************************************
 //
 // IEEE Special Conditions:
 //
@@ -80,14 +78,15 @@
 //    sqrtf(+/-0) = +/-0 
 //    sqrtf(negative) = QNaN and error handling is called
 //
-//********************************************************************
+// ********************************************************************
 //
 // Implementation:
 //
 //  Modified Newton-Raphson Algorithm
 //
-//********************************************************************
+// ********************************************************************
 
+#include "libm_support.h"
 
 GR_SAVE_B0                    = r34
 GR_SAVE_PFS                   = r33
@@ -103,8 +102,21 @@ FR_Y             = f0
 FR_RESULT        = f8
 
 
+
 .section .text
-GLOBAL_IEEE754_ENTRY(sqrtf)
+.proc sqrtf#
+.global sqrtf#
+.align 64 
+
+sqrtf: 
+#ifdef _LIBC
+.global __sqrtf
+.type __sqrtf,@function
+__sqrtf:
+.global __ieee754_sqrtf
+.type __ieee754_sqrtf,@function
+__ieee754_sqrtf:
+#endif
 { .mlx
   // BEGIN SINGLE PRECISION MINIMUM LATENCY SQUARE ROOT ALGORITHM
   alloc r32= ar.pfs,0,5,4,0
@@ -185,7 +197,7 @@ GLOBAL_IEEE754_ENTRY(sqrtf)
   // Step (10)
   // d1 = a - S1 * S1 in f9
   (p6) fnma.s1 f9=f7,f7,f8
-  nop.i 0;;
+  nop.i 0;;;
 } { .mfb
   nop.m 0
   // Step (11)
@@ -195,21 +207,27 @@ GLOBAL_IEEE754_ENTRY(sqrtf)
 // END SINGLE PRECISION MINIMUM LATENCY SQUARE ROOT ALGORITHM
 } { .mfb
   nop.m 0
-       mov   f8 = f7
+  (p0) mov   f8 = f7
   (p8) br.ret.sptk b0 ;;
 }
 //
 // This branch includes all those special values that are not negative,
 // with the result equal to frcpa(x)
 //
-GLOBAL_IEEE754_END(sqrtf)
+.endp sqrtf
+ASM_SIZE_DIRECTIVE(sqrtf)
+#ifdef _LIBC
+ASM_SIZE_DIRECTIVE(__sqrtf)
+ASM_SIZE_DIRECTIVE(__ieee754_sqrtf)
+#endif
 
 
-LOCAL_LIBM_ENTRY(__libm_error_region)
+.proc __libm_error_region
+__libm_error_region:
 .prologue
 { .mii
         add   GR_Parameter_Y=-32,sp             // Parameter 2 value
-        mov   GR_Parameter_TAG = 50                   
+(p0)    mov   GR_Parameter_TAG = 50                   
 .save   ar.pfs,GR_SAVE_PFS
         mov  GR_SAVE_PFS=ar.pfs                 // Save ar.pfs
 }
@@ -253,7 +271,8 @@ LOCAL_LIBM_ENTRY(__libm_error_region)
         br.ret.sptk     b0                     // Return
 };; 
 
-LOCAL_LIBM_END(__libm_error_region)
+.endp __libm_error_region
+ASM_SIZE_DIRECTIVE(__libm_error_region)
 
 
 .type   __libm_error_support#,@function