nir: Add a new ALU nir_op_imad24_ir3

ir3 compiler has a signed integer multiply-add instruction (MAD_S24)
that is used for different offset calculations in the backend.
Since we intend to move some of these calculations to NIR, we need
a new ALU op that can directly represent it.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Eduardo Lima Mitev <elima@igalia.com>

diff --git a/src/compiler/nir/nir_opcodes.py b/src/compiler/nir/nir_opcodes.py
index 5d589ee..b759910 100644 (file)
--- a/src/compiler/nir/nir_opcodes.py
+++ b/src/compiler/nir/nir_opcodes.py
@@ -1054,3 +1054,10 @@ opcode("imadsh_mix16", 1, tint32,
        [1, 1, 1], [tint32, tint32, tint32], False, "", """
 dst.x = ((((src0.x & 0xffff0000) >> 16) * (src1.x & 0x0000ffff)) << 16) + src2.x;
 """)
+
+# ir3-specific instruction that maps directly to ir3 mad.s24.
+#
+# 24b multiply into 32b result (with sign extension) plus 32b int
+triop("imad24_ir3", tint32, _2src_commutative,
+      "(((int32_t)src0 << 8) >> 8) * (((int32_t)src1 << 8) >> 8) + src2")
+