Description
set_directive_performance applies to loops and loop nests, and requires a known
loop tripcount to determine the performance. If your loop has a variable tripcount then you
must also specify set_directive_tripcount.The set_directive_performance lets you
specify a high-level constraint (target_ti) defining the
number of clock cycles between successive starts of a loop, and lets the tool infer
lower-level UNROLL, PIPELINE, ARRAY_PARTITION, and INLINE directives needed to achieve the
desired result. The set_directive_performance does not
guarantee the specified value will be achieved, and so it is only a target.
set_directive_inline is applied automatically to functions inside any pipelined
loop that has II=1 to improve throughput. If you apply the PERFORMANCE directive that infers
a pipeline with II=1, it will also trigger the auto-inline optimization. You can disable
this for specific functions by using set_directive_inline
off.The target transaction interval (target_ti) specifies a performance target for loops, where a transaction is a
complete set of loop iterations (tripcount) and the interval is the time between when the
first transaction starts and the second transaction starts.
- Target Transaction Interval (
target_ti) - Specifies the number of clock cycles from the first transaction of a loop, or nested loop, and the start of the next transaction of the loop. Specified as the cycles needed for the loop to complete all iterations and begin the next transaction.
The transaction interval is the initiation interval (II) of the loop times
the number of iterations, or tripcount: target_ti = II *
loop tripcount. Conversely, target_ti
= FreqHz / Operations per second.
For example, assuming an image processing function that processes a single
frame per invocation with a throughput goal of 60 fps, then the target throughput for the
function is 60 invocations per second. If the clock frequency is 180 MHz, then target_ti is 180M/60, or 3 million clock cycles per function
invocation.
Vitis HLS always tries to achieve the
specified performance target in the design. When set_directive_performance is specified, the tool automatically applies pragmas
or directives such as PIPELINE, UNROLL, or ARRAY_PARTITION to achieve the target_ti.
Syntax
Specify the directive for a function, or a labeled loop, or region of code.
set_directive_performance <label> -target_ti=<value>Where:
-
-target_ti=<value> - Specifies a target transaction interval defined as the number of clock
cycles for the loop to complete an iteration. The <value> can be specified as an
integer, floating point, or constant expression that is resolved by the tool as an
integer. Note: A warning will be returned if truncation occurs.
Example 1
The loop labeled loop_1 is specified to
have target transaction interval of 4 clock cycles:
set_directive_performance loop_1-target_ti=4