diff --git a/docs/regmap/adi_regmap_spi_engine.txt b/docs/regmap/adi_regmap_spi_engine.txt
index 681c37d45d..908b04bf33 100644
--- a/docs/regmap/adi_regmap_spi_engine.txt
+++ b/docs/regmap/adi_regmap_spi_engine.txt
@@ -9,7 +9,7 @@ ENDTITLE
 REG
 0x00
 VERSION
-Version of the peripheral. Follows semantic versioning. Current version 1.03.00.
+Version of the peripheral. Follows semantic versioning. Current version 1.03.01.
 ENDREG
 
 FIELD
@@ -25,7 +25,7 @@ RO
 ENDFIELD
 
 FIELD
-[7:0] 0x00000000
+[7:0] 0x00000001
 VERSION_PATCH
 RO
 ENDFIELD
diff --git a/library/spi_engine/axi_spi_engine/axi_spi_engine.v b/library/spi_engine/axi_spi_engine/axi_spi_engine.v
index f91e00eb26..2c0a9f37c9 100644
--- a/library/spi_engine/axi_spi_engine/axi_spi_engine.v
+++ b/library/spi_engine/axi_spi_engine/axi_spi_engine.v
@@ -133,7 +133,7 @@ module axi_spi_engine #(
   input [7:0] offload_sync_data
 );
 
-  localparam PCORE_VERSION = 'h010300;
+  localparam PCORE_VERSION = 'h010301;
   localparam S_AXI = 0;
   localparam UP_FIFO = 1;
 
diff --git a/library/spi_engine/spi_engine_execution/spi_engine_execution.v b/library/spi_engine/spi_engine_execution/spi_engine_execution.v
index 12876729f4..f0a58bcc93 100644
--- a/library/spi_engine/spi_engine_execution/spi_engine_execution.v
+++ b/library/spi_engine/spi_engine_execution/spi_engine_execution.v
@@ -163,6 +163,8 @@ module spi_engine_execution #(
 
   wire end_of_sdi_latch;
 
+  wire sample_sdo;
+
   (* direct_enable = "yes" *) wire cs_gen;
 
   spi_engine_execution_shiftreg #(
@@ -186,10 +188,12 @@ module spi_engine_execution #(
     .sdi_data_ready(sdi_data_ready),
     .sdo_enabled(sdo_enabled),
     .sdi_enabled(sdi_enabled),
-    .current_instr(inst_d1),
+    .current_cmd(cmd_d1),
     .sdo_idle_state(sdo_idle_state),
     .left_aligned(left_aligned),
     .word_length(word_length),
+    .sample_sdo(sample_sdo),
+    .sdo_io_ready(sdo_io_ready),
     .transfer_active(transfer_active),
     .trigger_tx(trigger_tx),
     .trigger_rx(trigger_rx),
@@ -197,6 +201,8 @@ module spi_engine_execution #(
     .cs_activate(cs_activate),
     .end_of_sdi_latch(end_of_sdi_latch));
 
+  assign sample_sdo = sdo_data_valid && ((trigger_tx && last_bit) || (wait_for_io || exec_transfer_cmd));
+
   assign cs_gen = inst_d1 == CMD_CHIPSELECT
                   && ((cs_sleep_counter_compare == 1'b1) || cs_sleep_early_exit)
                   && (cs_sleep_repeat == 1'b0)
@@ -380,7 +386,7 @@ module spi_engine_execution #(
   assign sync = cmd_d1[7:0];
 
   assign io_ready1 = (sdi_data_valid == 1'b0 || sdi_data_ready == 1'b1) &&
-          (sdo_enabled == 1'b0 || last_transfer == 1'b1 || sdo_data_valid == 1'b1);
+          (sdo_enabled == 1'b0 || last_transfer == 1'b1 || sdo_io_ready == 1'b1);
   assign io_ready2 = (sdi_enabled == 1'b0 || sdi_data_ready == 1'b1) &&
           (sdo_enabled == 1'b0 || last_transfer == 1'b1 || sdo_data_valid == 1'b1);
 
diff --git a/library/spi_engine/spi_engine_execution/spi_engine_execution_shiftreg.v b/library/spi_engine/spi_engine_execution/spi_engine_execution_shiftreg.v
index 6f3e999177..428c09797d 100644
--- a/library/spi_engine/spi_engine_execution/spi_engine_execution_shiftreg.v
+++ b/library/spi_engine/spi_engine_execution/spi_engine_execution_shiftreg.v
@@ -48,7 +48,7 @@ module spi_engine_execution_shiftreg #(
   input resetn,
 
   // spi io
-  input sdi,
+  input [NUM_OF_SDI-1:0] sdi,
   output sdo_int,
   input echo_sclk,
 
@@ -63,12 +63,14 @@ module spi_engine_execution_shiftreg #(
   // cfg and status
   input sdo_enabled,
   input sdi_enabled,
-  input [2:0] current_instr,
+  input [15:0] current_cmd,
   input sdo_idle_state,
   input [7:0] left_aligned,
   input [7:0] word_length,
 
   // timing from main fsm
+  input sample_sdo,
+  output reg sdo_io_ready,
   input transfer_active,
   input trigger_tx,
   input trigger_rx,
@@ -79,17 +81,37 @@ module spi_engine_execution_shiftreg #(
 
   reg [7:0] sdi_counter = 8'b0;
   reg [(DATA_WIDTH-1):0] data_sdo_shift = 'h0;
+  reg [(DATA_WIDTH-1):0] aligned_sdo_data, sdo_data_d;
   wire last_sdi_bit;
   reg [SDI_DELAY+1:0] trigger_rx_d = {(SDI_DELAY+2){1'b0}};
   wire trigger_rx_s;
+  wire [2:0] current_instr = current_cmd[14:12];
 
   always @(posedge clk) begin
-    if (resetn == 1'b0)
+    if (resetn == 1'b0) begin
       sdo_data_ready <= 1'b0;
-    else if (sdo_enabled == 1'b1 && first_bit == 1'b1 && trigger_tx == 1'b1 && transfer_active == 1'b1)
+    end else if (sdo_toshiftreg) begin
       sdo_data_ready <= 1'b1;
-    else if (sdo_data_valid == 1'b1)
+    end else if (sdo_data_valid == 1'b1) begin
       sdo_data_ready <= 1'b0;
+    end
+  end
+
+  // pipelined shifter for sdo_data
+  always @(posedge clk ) begin
+    if (resetn == 1'b0) begin
+      aligned_sdo_data <= 0;
+      sdo_io_ready <= 1'b0;
+    end else begin
+      if (transfer_active == 1'b1 && trigger_tx == 1'b1) begin
+        sdo_io_ready <= 1'b0;
+      end
+      if (sample_sdo) begin
+        sdo_data_d <= sdo_data;
+        sdo_io_ready <= 1'b1;
+      end
+      aligned_sdo_data <= sdo_data_d << left_aligned;
+    end
   end
 
   // Load the SDO parallel data into the SDO shift register. In case of a custom
@@ -98,13 +120,16 @@ module spi_engine_execution_shiftreg #(
     if (!sdo_enabled || (current_instr != CMD_TRANSFER)) begin
       data_sdo_shift <= {DATA_WIDTH{sdo_idle_state}};
     end else if (transfer_active == 1'b1 && trigger_tx == 1'b1) begin
-      if (first_bit == 1'b1)
-      data_sdo_shift <= sdo_data << left_aligned; //TODO: check if this could/should be pipelined
-      else
-      data_sdo_shift <= {data_sdo_shift[(DATA_WIDTH-2):0], 1'b0};
+      if (first_bit == 1'b1) begin
+        data_sdo_shift <= aligned_sdo_data;
+      end else begin
+        data_sdo_shift <= {data_sdo_shift[(DATA_WIDTH-2):0], 1'b0};
+      end
     end
   end
   assign sdo_int = data_sdo_shift[DATA_WIDTH-1];
+  assign sdo_toshiftreg = (transfer_active && trigger_tx && first_bit && sdo_enabled);
+
 
   // In case of an interface with high clock rate (SCLK > 50MHz), the latch of
   // the SDI line can be delayed with 1, 2 or 3 SPI core clock cycle.
@@ -203,7 +228,7 @@ module spi_engine_execution_shiftreg #(
     // sdi_data_valid is synchronous to SPI clock, so synchronize the
     // last_sdi_bit to SPI clock
 
-    reg [3:0] last_sdi_bit_m = 4'b0; //FIXME: bad synchronizer (cs_activate shouldn't be connected here), also why not just use sync_bits?
+    reg [3:0] last_sdi_bit_m = 4'b0; //FIXME: why not just use sync_bits?
     always @(posedge clk) begin
       if (cs_activate) begin
         last_sdi_bit_m <= 4'b0;
@@ -228,8 +253,8 @@ module spi_engine_execution_shiftreg #(
       if (cs_activate) begin
         num_of_transfers <= 8'b0;
       end else begin
-        if (cmd_d1[15:12] == 4'b0) begin
-          num_of_transfers <= cmd_d1[7:0] + 1'b1; // cmd_d1 contains the NUM_OF_TRANSFERS - 1
+        if (current_instr == CMD_TRANSFER) begin
+          num_of_transfers <= current_cmd[7:0] + 1'b1; // current_cmd contains the NUM_OF_TRANSFERS - 1
         end
       end
     end