|
|
@@ -72,6 +72,14 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
|
|
#ifndef PARAM_H |
|
|
|
#define PARAM_H |
|
|
|
|
|
|
|
#define LONGCAST (BLASLONG) |
|
|
|
#if defined(__BYTE_ORDER__) |
|
|
|
#if __GNUC__ < 9 |
|
|
|
#undef LONGCAST |
|
|
|
#define LONGCAST |
|
|
|
#endif |
|
|
|
#endif |
|
|
|
|
|
|
|
#define SBGEMM_DEFAULT_UNROLL_N 4 |
|
|
|
#define SBGEMM_DEFAULT_UNROLL_M 8 |
|
|
|
#define SBGEMM_DEFAULT_UNROLL_MN 32 |
|
|
@@ -2088,7 +2096,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
|
|
#ifdef PPCG4 |
|
|
|
#define GEMM_DEFAULT_OFFSET_A 0 |
|
|
|
#define GEMM_DEFAULT_OFFSET_B 1024 |
|
|
|
#define GEMM_DEFAULT_ALIGN (BLASLONG)0x0ffffUL |
|
|
|
#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL |
|
|
|
|
|
|
|
#define SGEMM_DEFAULT_UNROLL_M 16 |
|
|
|
#define SGEMM_DEFAULT_UNROLL_N 4 |
|
|
@@ -2119,7 +2127,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
|
|
|
|
|
|
#define GEMM_DEFAULT_OFFSET_A 2688 |
|
|
|
#define GEMM_DEFAULT_OFFSET_B 3072 |
|
|
|
#define GEMM_DEFAULT_ALIGN (BLASLONG)0x03fffUL |
|
|
|
#define GEMM_DEFAULT_ALIGN LONGCAST 0x03fffUL |
|
|
|
|
|
|
|
#if defined(__BYTE_ORDER__)&&(__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__) |
|
|
|
#define SGEMM_DEFAULT_UNROLL_M 4 |
|
|
@@ -2168,7 +2176,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
|
|
|
|
|
|
#define GEMM_DEFAULT_OFFSET_A (32 * 0) |
|
|
|
#define GEMM_DEFAULT_OFFSET_B (32 * 0) |
|
|
|
#define GEMM_DEFAULT_ALIGN (BLASLONG)0x0ffffUL |
|
|
|
#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL |
|
|
|
|
|
|
|
#define SGEMM_DEFAULT_UNROLL_M 4 |
|
|
|
#define SGEMM_DEFAULT_UNROLL_N 4 |
|
|
@@ -2204,7 +2212,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
|
|
|
|
|
|
#define GEMM_DEFAULT_OFFSET_A (32 * 0) |
|
|
|
#define GEMM_DEFAULT_OFFSET_B (32 * 0) |
|
|
|
#define GEMM_DEFAULT_ALIGN (BLASLONG)0x0ffffUL |
|
|
|
#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL |
|
|
|
|
|
|
|
#define SGEMM_DEFAULT_UNROLL_M 8 |
|
|
|
#define SGEMM_DEFAULT_UNROLL_N 4 |
|
|
@@ -2239,7 +2247,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
|
|
#if defined(POWER3) || defined(POWER4) || defined(POWER5) |
|
|
|
#define GEMM_DEFAULT_OFFSET_A 0 |
|
|
|
#define GEMM_DEFAULT_OFFSET_B 2048 |
|
|
|
#define GEMM_DEFAULT_ALIGN (BLASLONG)0x0ffffUL |
|
|
|
#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL |
|
|
|
|
|
|
|
#define SGEMM_DEFAULT_UNROLL_M 4 |
|
|
|
#define SGEMM_DEFAULT_UNROLL_N 4 |
|
|
@@ -2312,7 +2320,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
|
|
|
|
|
|
#define GEMM_DEFAULT_OFFSET_A 384 |
|
|
|
#define GEMM_DEFAULT_OFFSET_B 1024 |
|
|
|
#define GEMM_DEFAULT_ALIGN (BLASLONG)0x03fffUL |
|
|
|
#define GEMM_DEFAULT_ALIGN LONGCAST 0x03fffUL |
|
|
|
|
|
|
|
#define SGEMM_DEFAULT_UNROLL_M 4 |
|
|
|
#define SGEMM_DEFAULT_UNROLL_N 4 |
|
|
@@ -2345,7 +2353,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
|
|
#define GEMM_DEFAULT_OFFSET_A 0 |
|
|
|
#define GEMM_DEFAULT_OFFSET_B 65536 |
|
|
|
|
|
|
|
#define GEMM_DEFAULT_ALIGN (BLASLONG)0x0ffffUL |
|
|
|
#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL |
|
|
|
#if defined(__32BIT__) |
|
|
|
#warning using BINARY32==POWER6 |
|
|
|
#define SGEMM_DEFAULT_UNROLL_M 4 |
|
|
@@ -2398,7 +2406,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
|
|
|
|
|
|
#define GEMM_DEFAULT_OFFSET_A 0 |
|
|
|
#define GEMM_DEFAULT_OFFSET_B 65536 |
|
|
|
#define GEMM_DEFAULT_ALIGN 0x0ffffUL |
|
|
|
#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL |
|
|
|
|
|
|
|
#define SWITCH_RATIO 16 |
|
|
|
#define GEMM_PREFERED_SIZE 16 |
|
|
@@ -2437,7 +2445,7 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
|
|
|
|
|
|
#define GEMM_DEFAULT_OFFSET_A 0 |
|
|
|
#define GEMM_DEFAULT_OFFSET_B 65536 |
|
|
|
#define GEMM_DEFAULT_ALIGN 0x0ffffUL |
|
|
|
#define GEMM_DEFAULT_ALIGN LONGCAST 0x0ffffUL |
|
|
|
|
|
|
|
#define SWITCH_RATIO 16 |
|
|
|
#define GEMM_PREFERED_SIZE 16 |
|
|
|