Merge pull request #156 from p12nGH/noncontiguous_harts

[riscv-isa-sim.git] / softfloat / s_approxRecip32_1.c

diff --git a/softfloat/s_approxRecip32_1.c b/softfloat/s_approxRecip32_1.c
index 14ddd9545a134bf1a9f255594cf8fe014325b495..a06192ed5b10b59c09e7af08f850e026e61203f2 100644 (file)
--- a/softfloat/s_approxRecip32_1.c
+++ b/softfloat/s_approxRecip32_1.c
@@ -2,9 +2,9 @@
 /*============================================================================
 
 This C source file is part of the SoftFloat IEEE Floating-Point Arithmetic
-Package, Release 3a, by John R. Hauser.
+Package, Release 3d, by John R. Hauser.
 
-Copyright 2011, 2012, 2013, 2014, 2015 The Regents of the University of
+Copyright 2011, 2012, 2013, 2014, 2015, 2016 The Regents of the University of
 California.  All rights reserved.
 
 Redistribution and use in source and binary forms, with or without
@@ -39,30 +39,25 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 #ifndef softfloat_approxRecip32_1
 
+extern const uint16_t softfloat_approxRecip_1k0s[16];
+extern const uint16_t softfloat_approxRecip_1k1s[16];
+
 uint32_t softfloat_approxRecip32_1( uint32_t a )
 {
     int index;
-    uint16_t eps;
-    static const uint16_t k0s[] = {
-        0xFFC4, 0xF0BE, 0xE363, 0xD76F, 0xCCAD, 0xC2F0, 0xBA16, 0xB201,
-        0xAA97, 0xA3C6, 0x9D7A, 0x97A6, 0x923C, 0x8D32, 0x887E, 0x8417
-    };
-    static const uint16_t k1s[] = {
-        0xF0F1, 0xD62C, 0xBFA1, 0xAC77, 0x9C0A, 0x8DDB, 0x8185, 0x76BA,
-        0x6D3B, 0x64D4, 0x5D5C, 0x56B1, 0x50B6, 0x4B55, 0x4679, 0x4211
-    };
-    uint16_t r0;
-    uint32_t delta0;
+    uint16_t eps, r0;
+    uint32_t sigma0;
     uint_fast32_t r;
-    uint32_t sqrDelta0;
+    uint32_t sqrSigma0;
 
     index = a>>27 & 0xF;
     eps = (uint16_t) (a>>11);
-    r0 = k0s[index] - ((k1s[index] * (uint_fast32_t) eps)>>20);
-    delta0 = ~(uint_fast32_t) ((r0 * (uint_fast64_t) a)>>7);
-    r = ((uint_fast32_t) r0<<16) + ((r0 * (uint_fast64_t) delta0)>>24);
-    sqrDelta0 = ((uint_fast64_t) delta0 * delta0)>>32;
-    r += ((uint32_t) r * (uint_fast64_t) sqrDelta0)>>48;
+    r0 = softfloat_approxRecip_1k0s[index]
+             - ((softfloat_approxRecip_1k1s[index] * (uint_fast32_t) eps)>>20);
+    sigma0 = ~(uint_fast32_t) ((r0 * (uint_fast64_t) a)>>7);
+    r = ((uint_fast32_t) r0<<16) + ((r0 * (uint_fast64_t) sigma0)>>24);
+    sqrSigma0 = ((uint_fast64_t) sigma0 * sigma0)>>32;
+    r += ((uint32_t) r * (uint_fast64_t) sqrSigma0)>>48;
     return r;
 
 }