summaryrefslogtreecommitdiffstats
path: root/src/compiler/nir/nir_opcodes.py
diff options
context:
space:
mode:
authorIago Toral Quiroga <[email protected]>2018-04-17 10:07:40 +0200
committerIago Toral Quiroga <[email protected]>2018-05-03 11:40:26 +0200
commitc9653cc14cac7b5de1a82307624dbb52dba2e178 (patch)
tree0d7e6b4b7558dd18e89fdae3ca24d2783d7fa3f9 /src/compiler/nir/nir_opcodes.py
parent6318808a0559f7b2a8152592f0ae4e5ccc6953a9 (diff)
nir: add opcodes for 16-bit packing and unpacking
Noitice that we don't need 'split' versions of the 64-bit to / from 16-bit opcodes which we require during pack lowering to implement these operations. This is because these operations can be expressed as a collection of 32-bit from / to 16-bit and 64-bit to / from 32-bit operations, so we don't need new opcodes specifically for them. Reviewed-by: Jason Ekstrand <[email protected]>
Diffstat (limited to 'src/compiler/nir/nir_opcodes.py')
-rw-r--r--src/compiler/nir/nir_opcodes.py19
1 files changed, 19 insertions, 0 deletions
diff --git a/src/compiler/nir/nir_opcodes.py b/src/compiler/nir/nir_opcodes.py
index 89a6c6becc2..3c3316dcaa8 100644
--- a/src/compiler/nir/nir_opcodes.py
+++ b/src/compiler/nir/nir_opcodes.py
@@ -91,6 +91,7 @@ tfloat = "float"
tint = "int"
tbool = "bool32"
tuint = "uint"
+tuint16 = "uint16"
tfloat32 = "float32"
tint32 = "int32"
tuint32 = "uint32"
@@ -282,12 +283,24 @@ dst.x = (src0.x << 0) |
(src0.w << 24);
""")
+unop_horiz("pack_32_2x16", 1, tuint32, 2, tuint16,
+ "dst.x = src0.x | ((uint32_t)src0.y << 16);")
+
unop_horiz("pack_64_2x32", 1, tuint64, 2, tuint32,
"dst.x = src0.x | ((uint64_t)src0.y << 32);")
+unop_horiz("pack_64_4x16", 1, tuint64, 4, tuint16,
+ "dst.x = src0.x | ((uint64_t)src0.y << 16) | ((uint64_t)src0.z << 32) | ((uint64_t)src0.w << 48);")
+
unop_horiz("unpack_64_2x32", 2, tuint32, 1, tuint64,
"dst.x = src0.x; dst.y = src0.x >> 32;")
+unop_horiz("unpack_64_4x16", 4, tuint16, 1, tuint64,
+ "dst.x = src0.x; dst.y = src0.x >> 16; dst.z = src0.x >> 32; dst.w = src0.w >> 48;")
+
+unop_horiz("unpack_32_2x16", 2, tuint16, 1, tuint32,
+ "dst.x = src0.x; dst.y = src0.x >> 16;")
+
# Lowered floating point unpacking operations.
@@ -296,6 +309,9 @@ 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_32_2x16_split_x", tuint16, tuint32, "src0")
+unop_convert("unpack_32_2x16_split_y", tuint16, tuint32, "src0 >> 16")
+
unop_convert("unpack_64_2x32_split_x", tuint32, tuint64, "src0")
unop_convert("unpack_64_2x32_split_y", tuint32, tuint64, "src0 >> 32")
@@ -608,6 +624,9 @@ binop_horiz("pack_half_2x16_split", 1, tuint32, 1, tfloat32, 1, tfloat32,
binop_convert("pack_64_2x32_split", tuint64, tuint32, "",
"src0 | ((uint64_t)src1 << 32)")
+binop_convert("pack_32_2x16_split", tuint32, tuint16, "",
+ "src0 | ((uint32_t)src1 << 16)")
+
# bfm implements the behavior of the first operation of the SM5 "bfi" assembly
# and that of the "bfi1" i965 instruction. That is, it has undefined behavior
# if either of its arguments are 32.