changes requested

Author: sun-9545sunoj

lib/simulator_cuda.h

@@ -375,7 +375,7 @@ class SimulatorCUDA final {
     IndicesL<G> d_i(d_ws);
 
     ApplyGateL_Kernel<G><<<CreateGrid(blocks), threads>>>(
-        (fp_type*)d_ws, d_i.xss, d_i.ms, d_i.qis, d_i.tis,
+        (fp_type*) d_ws, d_i.xss, d_i.ms, d_i.qis, d_i.tis,
         1 << num_effective_qs, state.get());
   }
 
@@ -408,7 +408,7 @@ class SimulatorCUDA final {
     IndicesH<G> d_i(d_ws);
 
     ApplyControlledGateH_Kernel<G><<<CreateGrid(blocks), threads>>>(
-        (fp_type*)d_ws, d_i.xss, d_i.ms, num_aqs + 1, cvalsh, state.get());
+        (fp_type*) d_ws, d_i.xss, d_i.ms, num_aqs + 1, cvalsh, state.get());
   }
 
   template <unsigned G>
@@ -433,7 +433,7 @@ class SimulatorCUDA final {
     IndicesL<G> d_i(d_ws);
 
     ApplyControlledGateLH_Kernel<G><<<CreateGrid(blocks), threads>>>(
-        (fp_type*)d_ws, d_i.xss, d_i.ms, d_i.qis, d_i.tis, d.num_aqs + 1,
+        (fp_type*) d_ws, d_i.xss, d_i.ms, d_i.qis, d_i.tis, d.num_aqs + 1,
         d.cvalsh, 1 << d.num_effective_qs, state.get());
   }
 
@@ -459,7 +459,7 @@ class SimulatorCUDA final {
     IndicesLC<G> d_i(d_ws);
 
     ApplyControlledGateL_Kernel<G><<<CreateGrid(blocks), threads>>>(
-        (fp_type*)d_ws, d_i.xss, d_i.ms, d_i.qis, d_i.tis, d_i.cis,
+        (fp_type*) d_ws, d_i.xss, d_i.ms, d_i.qis, d_i.tis, d_i.cis,
         d.num_aqs + 1, d.cvalsh, 1 << d.num_effective_qs,
         1 << (5 - d.remaining_low_cqs), state.get());
   }
@@ -494,7 +494,7 @@ class SimulatorCUDA final {
     IndicesH<G> d_i(d_ws);
 
     ExpectationValueH_Kernel<G><<<CreateGrid(blocks), threads>>>(
-        (fp_type*)d_ws, d_i.xss, d_i.ms, num_iterations_per_block, state.get(),
+        (fp_type*) d_ws, d_i.xss, d_i.ms, num_iterations_per_block, state.get(),
         Plus<double>(), d_res1);
 
     double mul = size == 1 ? 0.5 : 1.0;
@@ -532,7 +532,7 @@ class SimulatorCUDA final {
     IndicesL<G> d_i(d_ws);
 
     ExpectationValueL_Kernel<G><<<CreateGrid(blocks), threads>>>(
-        (fp_type*)d_ws, d_i.xss, d_i.ms, d_i.qis, d_i.tis,
+        (fp_type*) d_ws, d_i.xss, d_i.ms, d_i.qis, d_i.tis,
         num_iterations_per_block, state.get(), Plus<double>(), d_res1);
 
     double mul = double(1 << (5 + num_effective_qs - G)) / 32;