diff options
Diffstat (limited to 'doc/timesoftfloat.html')
| -rw-r--r-- | doc/timesoftfloat.html | 202 |
1 files changed, 202 insertions, 0 deletions
diff --git a/doc/timesoftfloat.html b/doc/timesoftfloat.html new file mode 100644 index 0000000..b214611 --- /dev/null +++ b/doc/timesoftfloat.html @@ -0,0 +1,202 @@ + +<HTML> + +<HEAD> +<TITLE>timesoftfloat</TITLE> +</HEAD> + +<BODY> + +<H1>Berkeley TestFloat Release 3: <CODE>timesoftfloat</CODE></H1> + +<P> +John R. Hauser<BR> +2014 ______<BR> +</P> + +<P> +*** CONTENT DONE. +</P> + +<P> +*** REPLACE QUOTATION MARKS. +<BR> +*** REPLACE APOSTROPHES. +<BR> +*** REPLACE EM DASH. +</P> + + +<H2>Overview</H2> + +<P> +The <CODE>timesoftfloat</CODE> program provides a simple way to evaluate the +speed of the floating-point operations of the Berkeley SoftFloat library. +Program <CODE>timesoftfloat</CODE> is included with the Berkeley TestFloat +package, a small collection of programs for testing that an implementation of +floating-point conforms to the IEEE Standard for Binary Floating-Point +Arithmetic. +Although <CODE>timesoftfloat</CODE> does not test floating-point correctness +like other TestFloat programs, nevertheless <CODE>timesoftfloat</CODE> is a +partner to TestFloat's <CODE>testsoftfloat</CODE> program. +For more about TestFloat generally and <CODE>testsoftfloat</CODE> specifically, +see file +<A HREF="TestFloat-general.html"><NOBR><CODE>TestFloat-general.html</CODE></NOBR></A>. +</P> + +<P> +Ordinarily, <CODE>timesoftfloat</CODE> will measure a function's speed +separately for each rounding mode defined by the IEEE Floating-Point Standard, +one after the other. +If an operation is not supposed to require rounding, it will by default be +timed only with the rounding mode set to <CODE>near_even</CODE> (nearest/even). +In the same way, if an operation is affected by the way in which underflow +tininess is detected, <CODE>timesoftfloat</CODE> times the function with +tininess detected both before rounding and after rounding. +For <NOBR>80-bit</NOBR> double-extended-precision operations affected by +rounding precision control, <CODE>timesoftfloat</CODE> also times the function +for each of the three rounding precision modes, one after the other. +Evaluation of a function can be limited to a single rounding mode, a single +tininess mode, and/or a single rounding precision with appropriate command-line +options. +</P> + +<P> +For each function and mode evaluated, <CODE>timesoftfloat</CODE> reports the +measured speed of the function in Mops/s, or ``millions of operations per +second''. +The speeds reported by <CODE>timesoftfloat</CODE> may be affected somewhat by +other software executing at the same time as <CODE>timesoftfloat</CODE>. +Be aware also that the exact execution time of any SoftFloat function depends +partly on the values of arguments and the state of the processor's caches at +the time the function is called. +Your actual experience with SoftFloat may differ from the speeds reported by +<CODE>timesoftfloat</CODE> for all these reasons. +</P> + +<P> +Note that the remainder operations (<CODE>f32_rem</CODE>, <CODE>f64_rem</CODE>, +<CODE>extF80_rem</CODE>, and <CODE>f128_rem</CODE>) will be markedly slower +than other operations, particularly for double-extended-precision +(<CODE>extF80_rem</CODE>) and quadruple precision (<CODE>f128_rem</CODE>). +This is inherent to the remainder operation itself and is not a failing of the +SoftFloat implementation. +</P> + + +<H2>Command Syntax</H2> + +<P> +The <CODE>timesoftfloat</CODE> program is executed as a command with this +syntax: +<PRE> + timesoftfloat [<option>...] <function> +</PRE> +Square brackets (<CODE>[ ]</CODE>) denote optional arguments, +<CODE><option></CODE> is a supported option, and +<CODE><function></CODE> is the name of either a testable function or a +function set. +The available options and function sets are documented below. +If <CODE>timesoftfloat</CODE> is executed without any arguments, a summary of +usage is written. +</P> + + +<H2>Options</H2> + +<P> +The <CODE>timesoftfloat</CODE> program accepts several command options. +If mutually contradictory options are given, the last one has priority. +</P> + +<H3><CODE>-help</CODE></H3> + +<P> +The <CODE>-help</CODE> option causes a summary of program usage to be written, +after which the program exits. +</P> + +<H3><CODE>-precision32, -precision64, -precision80</CODE></H3> + +<P> +For <NOBR>80-bit</NOBR> double-extended-precision funcions affected by +rounding precision control, the <CODE>-precision32</CODE> option restricts +timing of an operation to only the cases in which the rounding precision is +<NOBR>32 bits</NOBR>, equivalent to <NOBR>32-bit</NOBR> single-precision. +Other rounding precision choices are not timed. +Likewise, <CODE>-precision64</CODE> fixes the rounding precision to +<NOBR>64 bits</NOBR>, equivalent to <NOBR>64-bit</NOBR> double-precision; +and <CODE>-precision80</CODE> fixes the rounding precision to the full +<NOBR>80 bits</NOBR> of the double-extended-precision format. +All these options are ignored for operations not affected by rounding precision +control. +</P> + +<H3><CODE>-rnear_even, -rnear_maxMag, -rminMag, -rmin, -rmax</CODE></H3> + +<P> +The <CODE>-rnear_even</CODE> option restricts timing of an operation to only +the cases in which the rounding mode is nearest/even. +Other rounding mode choices are not timed. +Likewise, <CODE>-rnear_maxMag</CODE> forces rounding to nearest/maximum +magnitude (nearest-away), <CODE>-rminMag</CODE> forces rounding to minimum +magnitude (toward zero), <CODE>-rmin</CODE> forces rounding to minimum (down, +toward negative infinity), and <CODE>-rmax</CODE> forces rounding to maximum +(up, toward positive infinity). +These options are ignored for operations that are exact and thus do not round. +</P> + +<H3><CODE>-tininessbefore, -tininessafter</CODE></H3> + +<P> +The <CODE>-tininessbefore</CODE> option restricts timing of an operation to +only the cases in which tininess on underflow is detected before rounding. +Likewise, <CODE>-tininessafter</CODE> restricts measurement to only the cases +in which tininess on underflow is detected after rounding. +</P> + +<H3><CODE>-notexact, -exact</CODE></H3> + +<P> +For functions that round to an integer (conversions to integer types and the +<CODE>roundToInt</CODE> functions), the <CODE>-notexact</CODE> option restricts +timing of an operation to only the cases for which the +<CODE><I>exact</I></CODE> operand (specifying whether the <I>inexact</I> +exception flag may be raised) is <CODE>false</CODE>. +Likewise, the <CODE>-exact</CODE> option restricts measurement to only the +cases for which the <CODE><I>exact</I></CODE> operand is <CODE>true</CODE>. +</P> + + +<H2>Function Sets</H2> + +<P> +Just as <CODE>timesoftfloat</CODE> can time a function for all five rounding +modes in sequence, multiple functions can be timed with a single execution of +<CODE>timesoftfloat</CODE>. +Three sets are recognized: +<CODE>-all1</CODE>, <CODE>-all2</CODE>, and <CODE>-all</CODE>. +The set <CODE>-all1</CODE> comprises all one-operand operations, +<CODE>-all2</CODE> is all two-operand operations, and <CODE>-all</CODE> is +obviously all operations. +A function set is used in place of a function name in the +<CODE>timesoftfloat</CODE> command line, such as +<PRE> + timesoftfloat [<option>...] -all1 +</PRE> +</P> + +<P> +For the purpose of deciding the number of operands of an operation, any +<CODE><I>roundingMode</I></CODE> and <CODE><I>exact</I></CODE> arguments are +ignored. +(Such arguments specify the rounding mode and whether the <I>inexact</I> +exception flag may be raised, respectively.) +Thus, functions that convert to integer type and the <CODE>roundToInt</CODE> +functions are included in the set of one-operand operations timed by +<CODE>-all1</CODE>. +</P> + + +</BODY> + |