fixfor avx update: removing vifelse

Tractables · Mar 3, 2021 · ce7f164 · ce7f164
1 parent d3c9767
commit ce7f164
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 6 deletions.
diff --git a/src/Logistic/parameters.jl b/src/Logistic/parameters.jl
@@ -1,7 +1,6 @@
 export learn_parameters, to_onehot
 
 using CUDA
-using LoopVectorization: @avx, vifelse
 
 """
 LogisticCircuit Parameter learning through gradient descents
@@ -49,9 +48,9 @@ function update_parameters_cpu(bc, data, labels, cl, step_size)
 
     @inline function on_edge_float(flows, values, prime, sub, element, grandpa, single_child, weights)
         lock(params_lock) do # TODO: move lock to inner loop?
-            @avx for i = 1:size(flows, 1)
+            @simd for i = 1:size(flows, 1) # adding @avx here might give incorrect results
                 @inbounds edge_flow = values[i, prime] * values[i, sub] / values[i, grandpa] * flows[i, grandpa]
-                edge_flow = vifelse(isfinite(edge_flow), edge_flow, zero(eltype(flows)))
+                edge_flow = ifelse(isfinite(edge_flow), edge_flow, zero(eltype(flows)))
                 for class = 1:nc
                     @inbounds bc.parames[element, class] -= (cl[i, class] - labels[i, class]) * edge_flow * step_size
                 end

diff --git a/src/Logistic/queries.jl b/src/Logistic/queries.jl
@@ -1,7 +1,7 @@
 export class_likelihood_per_instance, class_weights_per_instance
 
 using CUDA
-using LoopVectorization: @avx, vifelse
+using LoopVectorization: @avx
 
 
 """
@@ -59,9 +59,9 @@ function class_weights_per_instance_cpu(bc, data)
 
     @inline function on_edge_float(flows, values, prime, sub, element, grandpa, single_child, weights)
         lock(cw_lock) do # TODO: move lock to inner loop?
-            @avx for i = 1:size(flows, 1)
+            @simd for i = 1:size(flows, 1) # adding @avx here might give incorrect results
                 @inbounds edge_flow = values[i, prime] * values[i, sub] / values[i, grandpa] * flows[i, grandpa]
-                edge_flow = vifelse(isfinite(edge_flow), edge_flow, zero(eltype(flows)))
+                edge_flow = ifelse(isfinite(edge_flow), edge_flow, zero(eltype(flows)))
                 for class = 1:nc
                     @inbounds cw[i, class] += edge_flow * bc.params[element, class]
                 end