From: Chris Forbes <chrisf@ijw.co.nz>
Date: Sat, 12 Jul 2014 23:43:11 +0000 (+1200)
Subject: i965/vec4: Generate indirect sends for nonconstant UBO array access
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=a55eae9b6d822ab1d5e61b400426b9350e152cc4;p=mesa.git

i965/vec4: Generate indirect sends for nonconstant UBO array access

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
---

diff --git a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
index c63b47add59..f5e459a573d 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp
@@ -840,23 +840,70 @@ vec4_generator::generate_pull_constant_load_gen7(vec4_instruction *inst,
                                                  struct brw_reg surf_index,
                                                  struct brw_reg offset)
 {
-   assert(surf_index.file == BRW_IMMEDIATE_VALUE &&
-	  surf_index.type == BRW_REGISTER_TYPE_UD);
+   assert(surf_index.type == BRW_REGISTER_TYPE_UD);
 
-   brw_inst *insn = brw_next_insn(p, BRW_OPCODE_SEND);
-   brw_set_dest(p, insn, dst);
-   brw_set_src0(p, insn, offset);
-   brw_set_sampler_message(p, insn,
-                           surf_index.dw1.ud,
-                           0, /* LD message ignores sampler unit */
-                           GEN5_SAMPLER_MESSAGE_SAMPLE_LD,
-                           1, /* rlen */
-                           1, /* mlen */
-                           false, /* no header */
-                           BRW_SAMPLER_SIMD_MODE_SIMD4X2,
-                           0);
+   if (surf_index.file == BRW_IMMEDIATE_VALUE) {
 
-   brw_mark_surface_used(&prog_data->base, surf_index.dw1.ud);
+      brw_inst *insn = brw_next_insn(p, BRW_OPCODE_SEND);
+      brw_set_dest(p, insn, dst);
+      brw_set_src0(p, insn, offset);
+      brw_set_sampler_message(p, insn,
+                              surf_index.dw1.ud,
+                              0, /* LD message ignores sampler unit */
+                              GEN5_SAMPLER_MESSAGE_SAMPLE_LD,
+                              1, /* rlen */
+                              1, /* mlen */
+                              false, /* no header */
+                              BRW_SAMPLER_SIMD_MODE_SIMD4X2,
+                              0);
+
+      brw_mark_surface_used(&prog_data->base, surf_index.dw1.ud);
+
+   } else {
+
+      struct brw_reg addr = vec1(retype(brw_address_reg(0), BRW_REGISTER_TYPE_UD));
+
+      brw_push_insn_state(p);
+      brw_set_default_mask_control(p, BRW_MASK_DISABLE);
+      brw_set_default_access_mode(p, BRW_ALIGN_1);
+
+      /* a0.0 = surf_index & 0xff */
+      brw_inst *insn_and = brw_next_insn(p, BRW_OPCODE_AND);
+      brw_inst_set_exec_size(p->brw, insn_and, BRW_EXECUTE_1);
+      brw_set_dest(p, insn_and, addr);
+      brw_set_src0(p, insn_and, vec1(retype(surf_index, BRW_REGISTER_TYPE_UD)));
+      brw_set_src1(p, insn_and, brw_imm_ud(0x0ff));
+
+
+      /* a0.0 |= <descriptor> */
+      brw_inst *insn_or = brw_next_insn(p, BRW_OPCODE_OR);
+      brw_set_sampler_message(p, insn_or,
+                              0 /* surface */,
+                              0 /* sampler */,
+                              GEN5_SAMPLER_MESSAGE_SAMPLE_LD,
+                              1 /* rlen */,
+                              1 /* mlen */,
+                              false /* header */,
+                              BRW_SAMPLER_SIMD_MODE_SIMD4X2,
+                              0);
+      brw_inst_set_exec_size(p->brw, insn_or, BRW_EXECUTE_1);
+      brw_inst_set_src1_reg_type(p->brw, insn_or, BRW_REGISTER_TYPE_UD);
+      brw_set_src0(p, insn_or, addr);
+      brw_set_dest(p, insn_or, addr);
+
+
+      /* dst = send(offset, a0.0) */
+      brw_inst *insn_send = brw_next_insn(p, BRW_OPCODE_SEND);
+      brw_set_dest(p, insn_send, dst);
+      brw_set_src0(p, insn_send, offset);
+      brw_set_indirect_send_descriptor(p, insn_send, BRW_SFID_SAMPLER, addr);
+
+      brw_pop_insn_state(p);
+
+      /* visitor knows more than we do about the surface limit required,
+       * so has already done marking.
+       */
+   }
 }
 
 void