diff options
Diffstat (limited to 'src/shaders/vme/intra_frame.asm')
-rw-r--r-- | src/shaders/vme/intra_frame.asm | 182 |
1 files changed, 0 insertions, 182 deletions
diff --git a/src/shaders/vme/intra_frame.asm b/src/shaders/vme/intra_frame.asm deleted file mode 100644 index a833623..0000000 --- a/src/shaders/vme/intra_frame.asm +++ /dev/null @@ -1,182 +0,0 @@ -/* - * Copyright © <2010>, Intel Corporation. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the - * "Software"), to deal in the Software without restriction, including - * without limitation the rights to use, copy, modify, merge, publish, - * distribute, sub license, and/or sell copies of the Software, and to - * permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice (including the - * next paragraph) shall be included in all copies or substantial portions - * of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS - * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. - * IN NO EVENT SHALL PRECISION INSIGHT AND/OR ITS SUPPLIERS BE LIABLE FOR - * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, - * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE - * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. - * - */ -// Modual name: IntraFrame.asm -// -// Make intra predition estimation for Intra frame -// - -// -// Now, begin source code.... -// - -/* - * __START - */ -__INTRA_START: -mov (16) tmp_reg0.0<1>:UD 0x0:UD {align1}; -mov (16) tmp_reg2.0<1>:UD 0x0:UD {align1}; -mov (16) tmp_reg4.0<1>:UD 0x0:UD {align1} ; - -shl (2) read0_header.0<1>:D orig_xy_ub<2,2,1>:UB 4:UW {align1}; /* (x, y) * 16 */ -add (1) read0_header.0<1>:D read0_header.0<0,1,0>:D -8:W {align1}; /* X offset */ -add (1) read0_header.4<1>:D read0_header.4<0,1,0>:D -1:W {align1}; /* Y offset */ -mov (1) read0_header.8<1>:UD BLOCK_32X1 {align1}; -mov (1) read0_header.20<1>:UB thread_id_ub {align1}; /* dispatch id */ - -shl (2) read1_header.0<1>:D orig_xy_ub<2,2,1>:UB 4:UW {align1}; /* (x, y) * 16 */ -add (1) read1_header.0<1>:D read1_header.0<0,1,0>:D -4:W {align1}; /* X offset */ -mov (1) read1_header.8<1>:UD BLOCK_4X16 {align1}; -mov (1) read1_header.20<1>:UB thread_id_ub {align1}; /* dispatch id */ - -shl (2) vme_m0.8<1>:UW orig_xy_ub<2,2,1>:UB 4:UW {align1}; /* (x, y) * 16 */ -mov (1) vme_m0.20<1>:UB thread_id_ub {align1}; /* dispatch id */ - -mul (1) obw_m0.8<1>:UD w_in_mb_uw<0,1,0>:UW orig_y_ub<0,1,0>:UB {align1}; -add (1) obw_m0.8<1>:UD obw_m0.8<0,1,0>:UD orig_x_ub<0,1,0>:UB {align1}; -mov (1) obw_m0.20<1>:UB thread_id_ub {align1}; /* dispatch id */ - -/* - * Media Read Message -- fetch neighbor edge pixels - */ -/* ROW */ -__INTRA_LOOP: -mov (8) msg_reg0.0<1>:UD read0_header.0<8,8,1>:UD {align1}; -send (8) msg_ind INEP_ROW<1>:UB null read(BIND_IDX_INEP, 0, 0, 4) mlen 1 rlen 1 {align1}; - -/* COL */ -mov (8) msg_reg0.0<1>:UD read1_header.0<8,8,1>:UD {align1}; -send (8) msg_ind INEP_COL0<1>:UB null read(BIND_IDX_INEP, 0, 0, 4) mlen 1 rlen 2 {align1}; - -/* - * VME message - */ -/* m0 */ -mov (8) vme_msg_0.0<1>:UD vme_m0.0<8,8,1>:UD {align1}; - -/* m1 */ -mov (1) intra_flag<1>:UW 0x0:UW {align1} ; -and.z.f0.0 (1) null<1>:UW transform_8x8_ub<0,1,0>:UB 1:UW {align1}; -(f0.0) mov (1) intra_part_mask_ub<1>:UB LUMA_INTRA_8x8_DISABLE {align1}; - -cmp.nz.f0.0 (1) null<1>:UW orig_x_ub<0,1,0>:UB 0:UW {align1}; /* X != 0 */ -(f0.0) add (1) mb_intra_struct_ub<1>:UB mb_intra_struct_ub<0,1,0>:UB INTRA_PRED_AVAIL_FLAG_AE {align1}; /* A */ - -cmp.nz.f0.0 (1) null<1>:UW orig_y_ub<0,1,0>:UB 0:UW {align1}; /* Y != 0 */ -(f0.0) add (1) mb_intra_struct_ub<1>:UB mb_intra_struct_ub<0,1,0>:UB INTRA_PRED_AVAIL_FLAG_B {align1}; /* B */ - -mul.nz.f0.0 (1) null<1>:UW orig_x_ub<0,1,0>:UB orig_y_ub<0,1,0>:UB {align1}; /* X * Y != 0 */ -(f0.0) add (1) mb_intra_struct_ub<1>:UB mb_intra_struct_ub<0,1,0>:UB INTRA_PRED_AVAIL_FLAG_D {align1}; /* D */ - -add (1) tmp_x_w<1>:W orig_x_ub<0,1,0>:UB 1:UW {align1}; /* X + 1 */ -add (1) tmp_x_w<1>:W w_in_mb_uw<0,1,0>:UW -tmp_x_w<0,1,0>:W {align1}; /* width - (X + 1) */ -mul.nz.f0.0 (1) null<1>:UD tmp_x_w<0,1,0>:W orig_y_ub<0,1,0>:UB {align1}; /* (width - (X + 1)) * Y != 0 */ -(f0.0) add (1) mb_intra_struct_ub<1>:UB mb_intra_struct_ub<0,1,0>:UB INTRA_PRED_AVAIL_FLAG_C {align1}; /* C */ - -and.nz.f0.0 (1) null<1>:UW slice_edge_ub<0,1,0>:UB 2:UW {align1}; -(f0.0) and (1) mb_intra_struct_ub<1>:UB mb_intra_struct_ub<0,1,0>:UB 0xE0 {align1}; /* slice edge disable B,C,D*/ - - -mov (8) vme_msg_1<1>:UD vme_m1.0<8,8,1>:UD {align1}; - -/* m2 */ -mov (8) vme_msg_2<1>:UD 0x0:UD {align1}; - -/* m3 */ -mov (1) INEP_ROW.0<1>:UD 0x0:UD {align1}; -and (1) INEP_ROW.4<1>:UD INEP_ROW.4<0,1,0>:UD 0xFF000000:UD {align1}; -mov (8) vme_msg_3<1>:UD INEP_ROW.0<8,8,1>:UD {align1}; - -/* m4 */ -mov (8) vme_msg_4<1>:UD 0x0 {align1}; -mov (16) vme_msg_4.0<1>:UB INEP_COL0.3<32,8,4>:UB {align1}; -mov (1) vme_msg_4.16<1>:UD INTRA_PREDICTORE_MODE {align1}; - -send (8) - vme_msg_ind - vme_wb - null - vme( - BIND_IDX_VME, - 0, - 0, - VME_MESSAGE_TYPE_INTRA - ) - mlen vme_msg_length - rlen vme_intra_wb_length - {align1}; - -/* - * Oword Block Write message - */ -mov (8) msg_reg0.0<1>:UD obw_m0<8,8,1>:UD {align1}; - -mov (1) msg_reg1.0<1>:UD vme_wb.0<0,1,0>:UD {align1}; -mov (1) msg_reg1.4<1>:UD vme_wb.16<0,1,0>:UD {align1}; -mov (1) msg_reg1.8<1>:UD vme_wb.20<0,1,0>:UD {align1}; -mov (1) msg_reg1.12<1>:UD vme_wb.24<0,1,0>:UD {align1}; -/* bind index 3, write 1 oword, msg type: 8(OWord Block Write) */ -send (16) - msg_ind - obw_wb - null - data_port( - OBW_CACHE_TYPE, - OBW_MESSAGE_TYPE, - OBW_CONTROL_0, - OBW_BIND_IDX, - OBW_WRITE_COMMIT_CATEGORY, - OBW_HEADER_PRESENT - ) - mlen 2 - rlen obw_wb_length - {align1}; - -add (1) read0_header.0<1>:D read0_header.0<0,1,0>:D 16:W {align1}; /* X offset: X += 16 */ -add (1) read1_header.0<1>:D read1_header.0<0,1,0>:D 16:W {align1}; /* X offset: X += 16 */ -add (1) vme_m0.8<1>:UW vme_m0.8<0,1,0>:UW 16:UW {align1}; /* Y = Y, X += 16 */ - -add (1) orig_x_ub<1>:ub orig_x_ub<0,1,0>:ub 1:uw {align1} ; -cmp.e.f0.0 (1) null<1>:uw w_in_mb_uw<0,1,0>:uw orig_x_ub<0,1,0>:ub {align1}; -(f0.0)mov (1) orig_x_ub<1>:ub 0:uw {align1} ; -(f0.0)add (1) orig_y_ub<1>:ub orig_y_ub<0,1,0>:ub 1:uw {align1} ; -(f0.0)mov (1) read0_header.0<1>:D -8:W {align1}; /* X offset */ -(f0.0)add (1) read0_header.4<1>:D read0_header.4<0,1,0>:D 16:W {align1}; /* Y offset */ -(f0.0)mov (1) read1_header.0<1>:D -4:W {align1}; /* X offset */ -(f0.0)add (1) read1_header.4<1>:D read1_header.4<0,1,0>:D 16:W {align1}; /* Y offset */ -/* X = 0, Y += 16 */ -(f0.0)mov (1) vme_m0.8<1>:UW 0:UW {align1}; -(f0.0)add (1) vme_m0.10<1>:UW vme_m0.10<0,1,0>:UW 16:UW {align1}; - -add (1) obw_m0.8<1>:UD obw_m0.8<0,1,0>:UD 1:uw {align1}; /* the new offset */ - -add.z.f0.0 (1) num_macroblocks<1>:w num_macroblocks<0,1,0>:w -1:w {align1} ; -(-f0.0)jmpi (1) __INTRA_LOOP ; - -__EXIT: -/* - * kill thread - */ -mov (8) msg_reg0<1>:UD r0<8,8,1>:UD {align1}; -send (16) msg_ind acc0<1>UW null thread_spawner(0, 0, 1) mlen 1 rlen 0 {align1 EOT}; |