Mesa (main): aco: Add note about v_alignbyte in the ISA README.

[GitLab Mirror]

Module: Mesa
Branch: main
Commit: 228169c87c62caaa8770482d95b2b79a904075ff
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=228169c87c62caaa8770482d95b2b79a904075ff

Author: Timur Kristóf <timur.kristof at gmail.com>
Date:   Fri May 28 21:52:31 2021 +0200

aco: Add note about v_alignbyte in the ISA README.

We tried to use this instruction for a more optimal sequence,
but it turned out that it doesn't exactly work as it was
supposed to. This note is to help others who want to use it.

Signed-off-by: Timur Kristóf <timur.kristof at gmail.com>
Reviewed-by: Tony Wasserka <tony.wasserka at gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11072>

---

 src/amd/compiler/README-ISA.md | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/src/amd/compiler/README-ISA.md b/src/amd/compiler/README-ISA.md
index c692fdf7e16..296ba7a864a 100644
--- a/src/amd/compiler/README-ISA.md
+++ b/src/amd/compiler/README-ISA.md
@@ -44,6 +44,18 @@ is written in the GCN3 reference guide:
 D.u = CountOneBits(S0.u) + S1.u.
 ```
 
+## `v_alignbyte_b32`
+
+All versions of the ISA document are vague about it, but after some trial and
+error we discovered that only 2 bits of the 3rd operand are used.
+Therefore, this instruction can't shift more than 24 bits.
+
+The correct description of `v_alignbyte_b32` is probably the following:
+
+```
+D.u = ({S0, S1} >> (8 * S2.u[1:0])) & 0xffffffff
+```
+
 ## SMEM stores
 
 The Vega ISA references doesn't say this (or doesn't make it clear), but