r600: implement DDIV

Tested-by: Glenn Kennard <glenn.kennard@gmail.com>
Tested-by: James Harvey <lothmordor@gmail.com>
Cc: 17.0 <mesa-stable@lists.freedesktop.org>

diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c
index 5c4bc91b4989df52075993c7518989e346434e6d..eaabb042f971a04d1d8405048c8e2092d264d35a 100644 (file)
--- a/src/gallium/drivers/r600/r600_shader.c
+++ b/src/gallium/drivers/r600/r600_shader.c
@@ -4390,6 +4390,63 @@ static int cayman_mul_double_instr(struct r600_shader_ctx *ctx)
        return 0;
 }
 
+/*
+ * Emit RECIP_64 + MUL_64 to implement division.
+ */
+static int cayman_ddiv_instr(struct r600_shader_ctx *ctx)
+{
+       struct tgsi_full_instruction *inst = &ctx->parse.FullToken.FullInstruction;
+       int r;
+       struct r600_bytecode_alu alu;
+       int t1 = ctx->temp_reg;
+       int k;
+
+       /* Only support one double at a time. This is the same constraint as
+        * in DMUL lowering. */
+       assert(inst->Dst[0].Register.WriteMask == TGSI_WRITEMASK_XY ||
+              inst->Dst[0].Register.WriteMask == TGSI_WRITEMASK_ZW);
+
+       k = inst->Dst[0].Register.WriteMask == TGSI_WRITEMASK_XY ? 0 : 1;
+
+       r = cayman_emit_unary_double_raw(ctx->bc, ALU_OP2_RECIP_64, t1, &ctx->src[1], false);
+       if (r)
+               return r;
+
+       for (int i = 0; i < 4; i++) {
+               memset(&alu, 0, sizeof(struct r600_bytecode_alu));
+               alu.op = ALU_OP2_MUL_64;
+
+               r600_bytecode_src(&alu.src[0], &ctx->src[0], k * 2 + ((i == 3) ? 0 : 1));
+
+               alu.src[1].sel = t1;
+               alu.src[1].chan = (i == 3) ? 0 : 1;
+
+               alu.dst.sel = t1;
+               alu.dst.chan = i;
+               alu.dst.write = 1;
+               if (i == 3)
+                       alu.last = 1;
+               r = r600_bytecode_add_alu(ctx->bc, &alu);
+               if (r)
+                       return r;
+       }
+
+       for (int i = 0; i < 2; i++) {
+               memset(&alu, 0, sizeof(struct r600_bytecode_alu));
+               alu.op = ALU_OP1_MOV;
+               alu.src[0].sel = t1;
+               alu.src[0].chan = i;
+               tgsi_dst(ctx, &inst->Dst[0], k * 2 + i, &alu.dst);
+               alu.dst.write = 1;
+               if (i == 1)
+                       alu.last = 1;
+               r = r600_bytecode_add_alu(ctx->bc, &alu);
+               if (r)
+                       return r;
+       }
+       return 0;
+}
+
 /*
  * r600 - trunc to -PI..PI range
  * r700 - normalize by dividing by 2PI
@@ -9400,6 +9457,7 @@ static const struct r600_shader_tgsi_instruction eg_shader_tgsi_instruction[] =
        [TGSI_OPCODE_DNEG]      = { ALU_OP2_ADD_64, tgsi_dneg},
        [TGSI_OPCODE_DADD]      = { ALU_OP2_ADD_64, tgsi_op2_64},
        [TGSI_OPCODE_DMUL]      = { ALU_OP2_MUL_64, cayman_mul_double_instr},
+       [TGSI_OPCODE_DDIV]      = { 0, cayman_ddiv_instr },
        [TGSI_OPCODE_DMAX]      = { ALU_OP2_MAX_64, tgsi_op2_64},
        [TGSI_OPCODE_DMIN]      = { ALU_OP2_MIN_64, tgsi_op2_64},
        [TGSI_OPCODE_DSLT]      = { ALU_OP2_SETGT_64, tgsi_op2_64_single_dest_s},
@@ -9622,6 +9680,7 @@ static const struct r600_shader_tgsi_instruction cm_shader_tgsi_instruction[] =
        [TGSI_OPCODE_DNEG]      = { ALU_OP2_ADD_64, tgsi_dneg},
        [TGSI_OPCODE_DADD]      = { ALU_OP2_ADD_64, tgsi_op2_64},
        [TGSI_OPCODE_DMUL]      = { ALU_OP2_MUL_64, cayman_mul_double_instr},
+       [TGSI_OPCODE_DDIV]      = { 0, cayman_ddiv_instr },
        [TGSI_OPCODE_DMAX]      = { ALU_OP2_MAX_64, tgsi_op2_64},
        [TGSI_OPCODE_DMIN]      = { ALU_OP2_MIN_64, tgsi_op2_64},
        [TGSI_OPCODE_DSLT]      = { ALU_OP2_SETGT_64, tgsi_op2_64_single_dest_s},