diff --git a/docs/envvars.rst b/docs/envvars.rst
index e1fff2c4ae2..346c68b2f81 100644
--- a/docs/envvars.rst
+++ b/docs/envvars.rst
@@ -527,6 +527,8 @@ Intel driver environment variables
    ``sync``
       after sending each batch, wait on the CPU for that batch to
       finish rendering
+   ``swsb-stall``
+      Insert sync NOP after each instruction. This is only valid for Gfx12+.
    ``task``
       dump shader assembly for task shaders
    ``tcs``
diff --git a/src/intel/compiler/brw_fs_generator.cpp b/src/intel/compiler/brw_fs_generator.cpp
index eee62e5769e..95227e9655d 100644
--- a/src/intel/compiler/brw_fs_generator.cpp
+++ b/src/intel/compiler/brw_fs_generator.cpp
@@ -30,6 +30,7 @@
 #include "brw_eu.h"
 #include "brw_fs.h"
 #include "brw_cfg.h"
+#include "dev/intel_debug.h"
 #include "util/mesa-sha1.h"
 #include "util/half_float.h"
 
@@ -2387,6 +2388,14 @@ fs_generator::generate_code(const cfg_t *cfg, int dispatch_width,
             brw_inst_set_no_dd_check(p->devinfo, last, inst->no_dd_check);
          }
       }
+
+      /* When enabled, insert sync NOP after every instruction and make sure
+       * that current instruction depends on the previous instruction.
+       */
+      if (INTEL_DEBUG(DEBUG_SWSB_STALL) && devinfo->ver >= 12) {
+         brw_set_default_swsb(p, tgl_swsb_regdist(1));
+         brw_SYNC(p, TGL_SYNC_NOP);
+      }
    }
 
    brw_set_uip_jip(p, start_offset);
diff --git a/src/intel/dev/intel_debug.c b/src/intel/dev/intel_debug.c
index aa7a8d08f77..8aaddfc5185 100644
--- a/src/intel/dev/intel_debug.c
+++ b/src/intel/dev/intel_debug.c
@@ -100,6 +100,7 @@ static const struct debug_control debug_control[] = {
    { "stall",       DEBUG_STALL },
    { "capture-all", DEBUG_CAPTURE_ALL },
    { "perf-symbol-names", DEBUG_PERF_SYMBOL_NAMES },
+   { "swsb-stall",  DEBUG_SWSB_STALL },
    { NULL,    0 }
 };
 
diff --git a/src/intel/dev/intel_debug.h b/src/intel/dev/intel_debug.h
index ed90d3edb4b..08d50f57b65 100644
--- a/src/intel/dev/intel_debug.h
+++ b/src/intel/dev/intel_debug.h
@@ -90,6 +90,7 @@ extern uint64_t intel_debug;
 #define DEBUG_MESH                (1ull << 42)
 #define DEBUG_CAPTURE_ALL         (1ull << 43)
 #define DEBUG_PERF_SYMBOL_NAMES   (1ull << 44)
+#define DEBUG_SWSB_STALL          (1ull << 45)
 
 #define DEBUG_ANY                 (~0ull)