We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 1733f92 commit 211ab03Copy full SHA for 211ab03
kernel/x86_64/dgemm_kernel_4x8_haswell.S
@@ -267,23 +267,24 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
267
268
.macro SAVE4x12
269
270
+ prefetcht0 128(%rsp) /*BUFFER 1*/
271
vbroadcastsd ALPHA, %ymm0
272
273
vmulpd %ymm0 , %ymm4 , %ymm4
274
vmulpd %ymm0 , %ymm5 , %ymm5
275
vmulpd %ymm0 , %ymm6 , %ymm6
276
vmulpd %ymm0 , %ymm7 , %ymm7
-
277
+ prefetcht0 192(%rsp)
278
vmulpd %ymm0 , %ymm8 , %ymm8
279
vmulpd %ymm0 , %ymm9 , %ymm9
280
vmulpd %ymm0 , %ymm10, %ymm10
281
vmulpd %ymm0 , %ymm11, %ymm11
282
+ prefetcht0 256(%rsp)
283
vmulpd %ymm0 , %ymm12, %ymm12
284
vmulpd %ymm0 , %ymm13, %ymm13
285
vmulpd %ymm0 , %ymm14, %ymm14
286
vmulpd %ymm0 , %ymm15, %ymm15
287
+ prefetcht0 320(%rsp)
288
vpermilpd $ 0x05 , %ymm5, %ymm5
289
vpermilpd $ 0x05 , %ymm7, %ymm7
290
0 commit comments