[Mesa-dev] [PATCH v2 1/6] gallium: add new opcodes for ARB_gs5 bit manipulation support

[Ilia Mirkin]

Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu>
---
 src/gallium/auxiliary/tgsi/tgsi_info.c     |  8 ++++
 src/gallium/docs/source/tgsi.rst           | 75 ++++++++++++++++++++++++++++++
 src/gallium/include/pipe/p_shader_tokens.h | 11 ++++-
 3 files changed, 93 insertions(+), 1 deletion(-)

diff --git a/src/gallium/auxiliary/tgsi/tgsi_info.c b/src/gallium/auxiliary/tgsi/tgsi_info.c
index 5bcc3c9..d03a920 100644
--- a/src/gallium/auxiliary/tgsi/tgsi_info.c
+++ b/src/gallium/auxiliary/tgsi/tgsi_info.c
@@ -223,6 +223,14 @@ static const struct tgsi_opcode_info opcode_info[TGSI_OPCODE_LAST] =
    { 1, 2, 0, 0, 0, 0, COMP, "UMUL_HI", TGSI_OPCODE_UMUL_HI },
    { 1, 3, 1, 0, 0, 0, OTHR, "TG4", TGSI_OPCODE_TG4 },
    { 1, 2, 1, 0, 0, 0, OTHR, "LODQ", TGSI_OPCODE_LODQ },
+   { 1, 3, 0, 0, 0, 0, COMP, "IBFE", TGSI_OPCODE_IBFE },
+   { 1, 3, 0, 0, 0, 0, COMP, "UBFE", TGSI_OPCODE_UBFE },
+   { 1, 4, 0, 0, 0, 0, COMP, "BFI", TGSI_OPCODE_BFI },
+   { 1, 1, 0, 0, 0, 0, COMP, "BREV", TGSI_OPCODE_BREV },
+   { 1, 1, 0, 0, 0, 0, COMP, "POPC", TGSI_OPCODE_POPC },
+   { 1, 1, 0, 0, 0, 0, COMP, "LSB", TGSI_OPCODE_LSB },
+   { 1, 1, 0, 0, 0, 0, COMP, "IMSB", TGSI_OPCODE_IMSB },
+   { 1, 1, 0, 0, 0, 0, COMP, "UMSB", TGSI_OPCODE_UMSB },
 };
 
 const struct tgsi_opcode_info *
diff --git a/src/gallium/docs/source/tgsi.rst b/src/gallium/docs/source/tgsi.rst
index 0ea0759..9500b9d 100644
--- a/src/gallium/docs/source/tgsi.rst
+++ b/src/gallium/docs/source/tgsi.rst
@@ -1558,6 +1558,81 @@ Support for these opcodes indicated by PIPE_SHADER_CAP_INTEGERS (all of them?)
 
   dst.w = |src.w|
 
+Bitwise ISA
+^^^^^^^^^^^
+These opcodes are used for bit-level manipulation of integers.
+
+.. opcode:: IBFE - Signed Bitfield Extract
+
+  See SM5 instruction of the same name. Extracts a set of bits from the input,
+  and sign-extends them if the high bit of the extracted window is set.
+
+  Pseudocode::
+
+    def ibfe(value, offset, bits):
+      offset = offset & 0x1f
+      bits = bits & 0x1f
+      if bits == 0: return 0
+      # Note: >> sign-extends
+      if width + offset < 32:
+        return (value << (32 - offset - bits)) >> (32 - bits)
+      else:
+        return value >> offset
+
+.. opcode:: UBFE - Unsigned Bitfield Extract
+
+  See SM5 instruction of the same name. Extracts a set of bits from the input,
+  without any sign-extension.
+
+  Pseudocode::
+
+    def ubfe(value, offset, bits):
+      offset = offset & 0x1f
+      bits = bits & 0x1f
+      if bits == 0: return 0
+      # Note: >> does not sign-extend
+      if width + offset < 32:
+        return (value << (32 - offset - bits)) >> (32 - bits)
+      else:
+        return value >> offset
+
+.. opcode:: BFI - Bitfield Insert
+
+  See SM5 instruction of the same name. Replaces a bit region of 'base' with
+  the low bits of 'insert'.
+
+  Pseudocode::
+
+    def bfi(base, insert, offset, bits):
+      offset = offset & 0x1f
+      bits = bits & 0x1f
+      mask = ((1 << bits) - 1) << offset
+      return ((insert << offset) & mask) | (base & ~mask)
+
+.. opcode:: BREV - Bitfield Reverse
+
+  See SM5 instruction BFREV. Reverses the bits of the argument.
+
+.. opcode:: POPC - Population Count
+
+  See SM5 instruction COUNTBITS. Counts the number of set bits in the argument.
+
+.. opcode:: LSB - Index of lowest set bit
+
+  See SM5 instruction FIRSTBIT_LO. Computes the 0-based index of the first set
+  bit of the argument. Returns -1 if none are set.
+
+.. opcode:: IMSB - Index of highest non-sign bit
+
+  See SM5 instruction FIRSTBIT_SHI. Computes the 0-based index of the highest
+  non-sign bit of the argument (i.e. highest 0 bit for negative numbers,
+  highest 1 bit for positive numbers). Returns -1 if all bits are the same
+  (i.e. for inputs 0 and -1).
+
+.. opcode:: UMSB - Index of highest set bit
+
+  See SM5 instruction FIRSTBIT_HI. Computes the 0-based index of the highest
+  set bit of the argument. Returns -1 if none are set.
 
 Geometry ISA
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
diff --git a/src/gallium/include/pipe/p_shader_tokens.h b/src/gallium/include/pipe/p_shader_tokens.h
index b537166..d095bd3 100644
--- a/src/gallium/include/pipe/p_shader_tokens.h
+++ b/src/gallium/include/pipe/p_shader_tokens.h
@@ -462,7 +462,16 @@ struct tgsi_property_data {
 
 #define TGSI_OPCODE_LODQ                183
 
-#define TGSI_OPCODE_LAST                184
+#define TGSI_OPCODE_IBFE                184
+#define TGSI_OPCODE_UBFE                185
+#define TGSI_OPCODE_BFI                 186
+#define TGSI_OPCODE_BREV                187
+#define TGSI_OPCODE_POPC                188
+#define TGSI_OPCODE_LSB                 189
+#define TGSI_OPCODE_IMSB                190
+#define TGSI_OPCODE_UMSB                191
+
+#define TGSI_OPCODE_LAST                192
 
 #define TGSI_SAT_NONE            0  /* do not saturate */
 #define TGSI_SAT_ZERO_ONE        1  /* clamp to [0,1] */
-- 
1.8.3.2