diff --git a/gcc/config/i386/x86-tune-costs.h b/gcc/config/i386/x86-tune-costs.h
index e655e668c7a..db03738313e 100644
--- a/gcc/config/i386/x86-tune-costs.h
+++ b/gcc/config/i386/x86-tune-costs.h
@@ -1767,11 +1767,11 @@ struct processor_costs znver3_cost = {
   2, 2, 3,				/* cost of moving XMM,YMM,ZMM
 					   register.  */
   6,					/* cost of moving SSE register to integer.  */
-  /* VGATHERDPD is 23 uops and throughput is 9, VGATHERDPD is 35 uops,
-     throughput 12.  Approx 9 uops do not depend on vector size and every load
-     is 7 uops.  */
-  18, 8,				/* Gather load static, per_elt.  */
-  18, 10,				/* Gather store static, per_elt.  */
+  /* VGATHERDPD is 15 uops and throughput is 4, VGATHERDPS is 23 uops,
+     throughput 9.  Approx 7 uops do not depend on vector size and every load
+     is 4 uops.  */
+  14, 8,				/* Gather load static, per_elt.  */
+  14, 10,				/* Gather store static, per_elt.  */
   32,					/* size of l1 cache.  */
   512,					/* size of l2 cache.  */
   64,					/* size of prefetch block.  */
diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index 140ccb3d921..caebf76736e 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -436,7 +436,7 @@ DEF_TUNE (X86_TUNE_AVOID_4BYTE_PREFIXES, "avoid_4byte_prefixes",
 
 /* X86_TUNE_USE_GATHER: Use gather instructions.  */
 DEF_TUNE (X86_TUNE_USE_GATHER, "use_gather",
-	  ~(m_ZNVER | m_GENERIC))
+	  ~(m_ZNVER1 | m_ZNVER2 | m_GENERIC))
 
 /* X86_TUNE_AVOID_128FMA_CHAINS: Avoid creating loops with tight 128bit or
    smaller FMA chain.  */