From 27dfc3428a7016e2d05dd67b6d8b88c0b982baa9 Mon Sep 17 00:00:00 2001
From: Konstantin <const@const.me>
Date: Mon, 23 Jan 2023 14:38:12 +0100
Subject: Performance improvement, `softMax` shader

---
 ComputeShaders/softMaxLong.hlsl | 6 ++++++
 1 file changed, 6 insertions(+)
 create mode 100644 ComputeShaders/softMaxLong.hlsl

(limited to 'ComputeShaders/softMaxLong.hlsl')

diff --git a/ComputeShaders/softMaxLong.hlsl b/ComputeShaders/softMaxLong.hlsl
new file mode 100644
index 0000000..1f2c2be
--- /dev/null
+++ b/ComputeShaders/softMaxLong.hlsl
@@ -0,0 +1,6 @@
+// This version is for the "dec.probs" shader tag
+// The input tensor has a size [ 51865, 3 ], a very long tensor with just 3 rows.
+// Despite the shader only runs on 3 GPU cores, large count of threads helps substantially, this shader is about 50% faster.
+#define THREADS 1024
+
+#include "softMax.hlsl"
\ No newline at end of file
-- 
cgit v1.2.3