tgsi: add DDIV instruction

Double-precision division, to allow more precision than a DRCP + DMUL
sequence.

Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>

diff --git a/src/gallium/auxiliary/gallivm/lp_bld_tgsi_action.c b/src/gallium/auxiliary/gallivm/lp_bld_tgsi_action.c
index 91e959f3451d23d347acec8b9bd564d009c2bcee..937170fec1ffbda48817fbfecd457ffe0215694f 100644 (file)
--- a/src/gallium/auxiliary/gallivm/lp_bld_tgsi_action.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_tgsi_action.c
@@ -1355,6 +1355,7 @@ lp_set_default_actions(struct lp_build_tgsi_context * bld_base)
    bld_base->op_actions[TGSI_OPCODE_DMAX].emit = fmax_emit;
    bld_base->op_actions[TGSI_OPCODE_DMIN].emit = fmin_emit;
    bld_base->op_actions[TGSI_OPCODE_DMUL].emit = mul_emit;
+   bld_base->op_actions[TGSI_OPCODE_DDIV].emit = fdiv_emit;
 
    bld_base->op_actions[TGSI_OPCODE_D2F].emit = d2f_emit;
    bld_base->op_actions[TGSI_OPCODE_D2I].emit = d2i_emit;
@@ -2623,6 +2624,7 @@ lp_set_default_actions_cpu(
    bld_base->op_actions[TGSI_OPCODE_DSLT].emit = dslt_emit_cpu;
    bld_base->op_actions[TGSI_OPCODE_DSNE].emit = dsne_emit_cpu;
 
+   bld_base->op_actions[TGSI_OPCODE_DDIV].emit = div_emit_cpu;
    bld_base->op_actions[TGSI_OPCODE_DRSQ].emit = drecip_sqrt_emit_cpu;
    bld_base->op_actions[TGSI_OPCODE_DSQRT].emit = dsqrt_emit_cpu;
 

diff --git a/src/gallium/auxiliary/tgsi/tgsi_info.c b/src/gallium/auxiliary/tgsi/tgsi_info.c
index a339ec281c7841f8f1029df69d12b9e829cd2367..3bec56119b8d68fe57693bf3e6ef54cd5f9758a5 100644 (file)
--- a/src/gallium/auxiliary/tgsi/tgsi_info.c
+++ b/src/gallium/auxiliary/tgsi/tgsi_info.c
@@ -287,6 +287,7 @@ static const struct tgsi_opcode_info opcode_info[TGSI_OPCODE_LAST] =
    { 1, 2, 0, 0, 0, 0, 0, COMP, "U64DIV", TGSI_OPCODE_U64DIV },
    { 1, 2, 0, 0, 0, 0, 0, COMP, "I64MOD", TGSI_OPCODE_I64MOD },
    { 1, 2, 0, 0, 0, 0, 0, COMP, "U64MOD", TGSI_OPCODE_U64MOD },
+   { 1, 2, 0, 0, 0, 0, 0, COMP, "DDIV", TGSI_OPCODE_DDIV },
 };
 
 const struct tgsi_opcode_info *
@@ -417,6 +418,7 @@ tgsi_opcode_infer_type( uint opcode )
    case TGSI_OPCODE_DNEG:
    case TGSI_OPCODE_DMUL:
    case TGSI_OPCODE_DMAX:
+   case TGSI_OPCODE_DDIV:
    case TGSI_OPCODE_DMIN:
    case TGSI_OPCODE_DRCP:
    case TGSI_OPCODE_DSQRT:

diff --git a/src/gallium/docs/source/tgsi.rst b/src/gallium/docs/source/tgsi.rst
index d2d30b41d00b9434de84150f55c8f049e8465bf6..3e2d0e9fac2be37cef0ccf55c4ae96f346679205 100644 (file)
--- a/src/gallium/docs/source/tgsi.rst
+++ b/src/gallium/docs/source/tgsi.rst
@@ -2005,6 +2005,15 @@ Perform a * b + c with no intermediate rounding step.
   dst.zw = src0.zw \times src1.zw + src2.zw
 
 
+.. opcode:: DDIV - Divide
+
+.. math::
+
+  dst.xy = \frac{src0.xy}{src1.xy}
+
+  dst.zw = \frac{src0.zw}{src1.zw}
+
+
 .. opcode:: DRCP - Reciprocal
 
 .. math::

diff --git a/src/gallium/include/pipe/p_shader_tokens.h b/src/gallium/include/pipe/p_shader_tokens.h
index 3384035a71189a870eab8161f26c953a841bcc56..a867d13914402d8e0b9ccac4bfd86b8f0542591a 100644 (file)
--- a/src/gallium/include/pipe/p_shader_tokens.h
+++ b/src/gallium/include/pipe/p_shader_tokens.h
@@ -601,7 +601,10 @@ struct tgsi_property_data {
 #define TGSI_OPCODE_U64DIV              245
 #define TGSI_OPCODE_I64MOD              246
 #define TGSI_OPCODE_U64MOD              247
-#define TGSI_OPCODE_LAST                248
+
+#define TGSI_OPCODE_DDIV                248
+
+#define TGSI_OPCODE_LAST                249
 
 /**
  * Opcode is the operation code to execute. A given operation defines the