Consistently use arm_arch.h constants in armcap assembly code.

[openssl.git] / crypto / bn / asm / ia64.S

diff --git a/crypto/bn/asm/ia64.S b/crypto/bn/asm/ia64.S
index 951abc53ea5bbae8e308643147fcaa26182e560b..9e090ab8fda3fc82039333cf38a292fb3d2036a8 100644 (file)
--- a/crypto/bn/asm/ia64.S
+++ b/crypto/bn/asm/ia64.S
@@ -422,7 +422,7 @@ bn_mul_add_words:
 
 // This loop spins in 3*(n+10) ticks on Itanium and in 2*(n+10) on
 // Itanium 2. Yes, unlike previous versions it scales:-) Previous
-// version was peforming *all* additions in IALU and was starving
+// version was performing *all* additions in IALU and was starving
 // for those even on Itanium 2. In this version one addition is
 // moved to FPU and is folded with multiplication. This is at cost
 // of propogating the result from previous call to this subroutine
@@ -495,7 +495,7 @@ bn_sqr_words:
 // scalability. The decision will very likely be reconsidered after the
 // benchmark program is profiled. I.e. if perfomance gain on Itanium
 // will appear larger than loss on "wider" IA-64, then the loop should
-// be explicitely split and the epilogue compressed.
+// be explicitly split and the epilogue compressed.
 .L_bn_sqr_words_ctop:
 { .mfi;        (p16)   ldf8            f32=[r33],8
        (p25)   xmpy.lu         f42=f41,f41
@@ -568,7 +568,7 @@ bn_sqr_comba8:
 // I've estimated this routine to run in ~120 ticks, but in reality
 // (i.e. according to ar.itc) it takes ~160 ticks. Are those extra
 // cycles consumed for instructions fetch? Or did I misinterpret some
-// clause in Itanium µ-architecture manual? Comments are welcomed and
+// clause in Itanium µ-architecture manual? Comments are welcomed and
 // highly appreciated.
 //
 // On Itanium 2 it takes ~190 ticks. This is because of stalls on