nir: add component level support to remove_unused_io_vars()

[mesa.git] / src / compiler / nir / nir_opcodes.py

diff --git a/src/compiler/nir/nir_opcodes.py b/src/compiler/nir/nir_opcodes.py
index 0f6dd0add8393f3bf6ca9cf3eb4423f58279d0af..28a04672285e58209ef2ba3e0a3e09d2b13f7c53 100644 (file)
--- a/src/compiler/nir/nir_opcodes.py
+++ b/src/compiler/nir/nir_opcodes.py
@@ -1,4 +1,3 @@
-#! /usr/bin/env python
 #
 # Copyright (C) 2014 Connor Abbott
 #
@@ -157,7 +156,7 @@ unop("fsign", tfloat, ("bit_size == 64 ? " +
                        "((src0 == 0.0f) ? 0.0f : ((src0 > 0.0f) ? 1.0f : -1.0f))"))
 unop("isign", tint, "(src0 == 0) ? 0 : ((src0 > 0) ? 1 : -1)")
 unop("iabs", tint, "(src0 < 0) ? -src0 : src0")
-unop("fabs", tfloat, "bit_size == 64 ? fabs(src0) : fabsf(src0)")
+unop("fabs", tfloat, "fabs(src0)")
 unop("fsat", tfloat, ("bit_size == 64 ? " +
                       "((src0 > 1.0) ? 1.0 : ((src0 <= 0.0) ? 0.0 : src0)) : " +
                       "((src0 > 1.0f) ? 1.0f : ((src0 <= 0.0f) ? 0.0f : src0))"))
@@ -166,41 +165,30 @@ unop("frsq", tfloat, "bit_size == 64 ? 1.0 / sqrt(src0) : 1.0f / sqrtf(src0)")
 unop("fsqrt", tfloat, "bit_size == 64 ? sqrt(src0) : sqrtf(src0)")
 unop("fexp2", tfloat, "exp2f(src0)")
 unop("flog2", tfloat, "log2f(src0)")
-unop_convert("f2i", tint32, tfloat32, "src0") # Float-to-integer conversion.
-unop_convert("f2u", tuint32, tfloat32, "src0") # Float-to-unsigned conversion
-unop_convert("d2i", tint32, tfloat64, "src0") # Double-to-integer conversion.
-unop_convert("d2u", tuint32, tfloat64, "src0") # Double-to-unsigned conversion.
-unop_convert("i2f", tfloat32, tint32, "src0") # Integer-to-float conversion.
-unop_convert("i2d", tfloat64, tint32, "src0") # Integer-to-double conversion.
-unop_convert("i2i32", tint32, tint, "src0")    # General int (int8_t, int64_t, etc.) to int32_t conversion
-unop_convert("u2i32", tint32, tuint, "src0")   # General uint (uint8_t, uint64_t, etc.) to int32_t conversion
-unop_convert("i2u32", tuint32, tint, "src0")   # General int (int8_t, int64_t, etc.) to uint32_t conversion
-unop_convert("u2u32", tuint32, tuint, "src0")  # General uint (uint8_t, uint64_t, etc.) to uint32_t conversion
-unop_convert("i2i64", tint64, tint, "src0")    # General int (int8_t, int32_t, etc.) to int64_t conversion
-unop_convert("u2i64", tint64, tuint, "src0")   # General uint (uint8_t, uint64_t, etc.) to int64_t conversion
-unop_convert("f2i64", tint64, tfloat, "src0")  # General float (float or double) to int64_t conversion
-unop_convert("i2u64", tuint64, tint,  "src0")  # General int (int8_t, int64_t, etc.) to uint64_t conversion
-unop_convert("u2u64", tuint64, tuint, "src0")  # General uint (uint8_t, uint32_t, etc.) to uint64_t conversion
-unop_convert("f2u64", tuint64, tfloat, "src0") # General float (float or double) to uint64_t conversion
-unop_convert("i642f", tfloat32, tint64, "src0")  # int64_t-to-float conversion.
-unop_convert("i642d", tfloat64, tint64, "src0")  # int64_t-to-double conversion.
-unop_convert("u642f", tfloat32, tuint64, "src0") # uint64_t-to-float conversion.
-unop_convert("u642d", tfloat64, tuint64, "src0") # uint64_t-to-double conversion.
-
-# Float-to-boolean conversion
-unop_convert("f2b", tbool, tfloat32, "src0 != 0.0f")
-unop_convert("d2b", tbool, tfloat64, "src0 != 0.0")
-# Boolean-to-float conversion
-unop_convert("b2f", tfloat32, tbool, "src0 ? 1.0f : 0.0f")
-# Int-to-boolean conversion
+
+# Generate all of the numeric conversion opcodes
+for src_t in [tint, tuint, tfloat]:
+   if src_t in (tint, tuint):
+      dst_types = [tfloat, src_t]
+   elif src_t == tfloat:
+      dst_types = [tint, tuint, tfloat]
+
+   for dst_t in dst_types:
+      if dst_t == tfloat:
+         bit_sizes = [16, 32, 64]
+      else:
+         bit_sizes = [8, 16, 32, 64]
+      for bit_size in bit_sizes:
+         unop_convert("{0}2{1}{2}".format(src_t[0], dst_t[0], bit_size),
+                      dst_t + str(bit_size), src_t, "src0")
+
+# We'll hand-code the to/from bool conversion opcodes.  Because bool doesn't
+# have multiple bit-sizes, we can always infer the size from the other type.
+unop_convert("f2b", tbool, tfloat, "src0 != 0.0")
 unop_convert("i2b", tbool, tint, "src0 != 0")
-unop_convert("b2i", tint32, tbool, "src0 ? 1 : 0") # Boolean-to-int conversion
-unop_convert("b2i64", tint64, tbool, "src0 ? 1 : 0")  # Boolean-to-int64_t conversion.
-unop_convert("u2f", tfloat32, tuint32, "src0") # Unsigned-to-float conversion.
-unop_convert("u2d", tfloat64, tuint32, "src0") # Unsigned-to-double conversion.
-# double-to-float conversion
-unop_convert("d2f", tfloat32, tfloat64, "src0") # Double to single precision
-unop_convert("f2d", tfloat64, tfloat32, "src0") # Single to double precision
+unop_convert("b2f", tfloat, tbool, "src0 ? 1.0 : 0.0")
+unop_convert("b2i", tint, tbool, "src0 ? 1 : 0")
+
 
 # Unary floating-point rounding operations.
 
@@ -284,16 +272,10 @@ dst.x = (src0.x <<  0) |
         (src0.w << 24);
 """)
 
-unop_horiz("pack_double_2x32", 1, tuint64, 2, tuint32,
+unop_horiz("pack_64_2x32", 1, tuint64, 2, tuint32,
            "dst.x = src0.x | ((uint64_t)src0.y << 32);")
 
-unop_horiz("pack_int_2x32", 1, tint64, 2, tint32,
-           "dst.x = src0.x | ((int64_t)src0.y << 32);")
-
-unop_horiz("unpack_double_2x32", 2, tuint32, 1, tuint64,
-           "dst.x = src0.x; dst.y = src0.x >> 32;")
-
-unop_horiz("unpack_int_2x32", 2, tint32, 1, tint64,
+unop_horiz("unpack_64_2x32", 2, tuint32, 1, tuint64,
            "dst.x = src0.x; dst.y = src0.x >> 32;")
 
 # Lowered floating point unpacking operations.
@@ -304,10 +286,8 @@ unop_horiz("unpack_half_2x16_split_x", 1, tfloat32, 1, tuint32,
 unop_horiz("unpack_half_2x16_split_y", 1, tfloat32, 1, tuint32,
            "unpack_half_1x16((uint16_t)(src0.x >> 16))")
 
-unop_convert("unpack_double_2x32_split_x", tuint32, tuint64, "src0")
-unop_convert("unpack_double_2x32_split_y", tuint32, tuint64, "src0 >> 32")
-unop_convert("unpack_int_2x32_split_x", tuint32, tuint64, "src0")
-unop_convert("unpack_int_2x32_split_y", tuint32, tuint64, "src0 >> 32")
+unop_convert("unpack_64_2x32_split_x", tuint32, tuint64, "src0")
+unop_convert("unpack_64_2x32_split_y", tuint32, tuint64, "src0 >> 32")
 
 # Bit operations, part of ARB_gpu_shader5.
 
@@ -328,7 +308,7 @@ for (unsigned bit = 0; bit < 32; bit++) {
 
 unop_convert("ufind_msb", tint32, tuint32, """
 dst = -1;
-for (int bit = 31; bit > 0; bit--) {
+for (int bit = 31; bit >= 0; bit--) {
    if ((src0 >> bit) & 1) {
       dst = bit;
       break;
@@ -487,7 +467,7 @@ binop_reduce("fany_nequal", 1, tfloat32, tfloat32, "{src0} != {src1}",
 # and false respectively
 
 binop("slt", tfloat32, "", "(src0 < src1) ? 1.0f : 0.0f") # Set on Less Than
-binop("sge", tfloat32, "", "(src0 >= src1) ? 1.0f : 0.0f") # Set on Greater or Equal
+binop("sge", tfloat, "", "(src0 >= src1) ? 1.0f : 0.0f") # Set on Greater or Equal
 binop("seq", tfloat32, commutative, "(src0 == src1) ? 1.0f : 0.0f") # Set on Equal
 binop("sne", tfloat32, commutative, "(src0 != src1) ? 1.0f : 0.0f") # Set on Not Equal
 
@@ -587,10 +567,7 @@ binop("fpow", tfloat, "", "bit_size == 64 ? powf(src0, src1) : pow(src0, src1)")
 binop_horiz("pack_half_2x16_split", 1, tuint32, 1, tfloat32, 1, tfloat32,
             "pack_half_1x16(src0.x) | (pack_half_1x16(src1.x) << 16)")
 
-binop_convert("pack_double_2x32_split", tuint64, tuint32, "",
-              "src0 | ((uint64_t)src1 << 32)")
-
-binop_convert("pack_int_2x32_split", tuint64, tuint32, "",
+binop_convert("pack_64_2x32_split", tuint64, tuint32, "",
               "src0 | ((uint64_t)src1 << 32)")
 
 # bfm implements the behavior of the first operation of the SM5 "bfi" assembly