diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td b/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
@@ -291,6 +291,14 @@
   (ops node:$src0), (srl_oneuse node:$src0, (i32 16))
 >;
 
+// TODO: smed3 should always be used probably? why do we need smin/smax?
+def clamp_s16_u8 : PatFrags<
+  (ops node:$src),
+  [
+    (i16 (smax (smin $src, (i16 255)), (i16 0))),
+    (i16 (AMDGPUsmed3 $src, (i16 0), (i16 255)))
+  ]
+>;
 
 def hi_i16_elt : PatFrag<
   (ops node:$src0), (i16 (trunc (i32 (srl_16 node:$src0))))
diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
--- a/llvm/lib/Target/AMDGPU/SIInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -10,9 +10,10 @@
 // that are not yet supported remain commented out.
 //===----------------------------------------------------------------------===//
 
-class GCNPat<dag pattern, dag result> : Pat<pattern, result>, GCNPredicateControl {
+class GCNPat<dag pattern, dag result> : Pat<pattern, result>, GCNPredicateControl, GISelFlags;
 
-}
+let GIIgnoreCopies = 1 in
+class GCNPatIgnoreCopies<dag pattern, dag result> : GCNPat<pattern, result>;
 
 class UniformSextInreg<ValueType VT> : PatFrag<
   (ops node:$src),
@@ -2925,6 +2926,31 @@
   (v2i16 (V_LSHL_OR_B32_e64 $src1, (i32 16), (i32 (V_AND_B32_e64 (i32 (V_MOV_B32_e32 (i32 0xffff))), $src0))))
 >;
 
+multiclass V_SAT_PK_Pat<Instruction inst> { 
+  def: GCNPat<
+    (v2i16 (build_vector (clamp_s16_u8 i16:$lo), (clamp_s16_u8 i16:$hi))),
+    (inst 
+      (V_LSHL_OR_B32_e64 VGPR_32:$hi, (S_MOV_B32 (i32 16)), 
+        (V_AND_B32_e64 VGPR_32:$lo, (S_MOV_B32 (i32 0xFFFF)))))
+  >;
+
+  def: GCNPatIgnoreCopies<
+    (v2i16 (smin (smax v2i16:$src, (build_vector (i16 0), (i16 0))), (build_vector (i16 255), (i16 255)))),
+    (inst VGPR_32:$src)
+  >;
+
+  def: GCNPatIgnoreCopies<
+    (v2i16 (smax (smin v2i16:$src, (build_vector (i16 255), (i16 255))), (build_vector (i16 0), (i16 0)))),
+    (inst VGPR_32:$src)
+  >;
+}
+
+let OtherPredicates = [HasTrue16BitInsts] in 
+defm : V_SAT_PK_Pat<V_SAT_PK_U8_I16_t16_e64>;
+
+let OtherPredicates = [NotHasTrue16BitInsts] in 
+defm : V_SAT_PK_Pat<V_SAT_PK_U8_I16_e64>;
+
 // With multiple uses of the shift, this will duplicate the shift and
 // increase register pressure.
 def : GCNPat <
diff --git a/llvm/test/CodeGen/AMDGPU/v_sat_pk_u8_i16.ll b/llvm/test/CodeGen/AMDGPU/v_sat_pk_u8_i16.ll
--- a/llvm/test/CodeGen/AMDGPU/v_sat_pk_u8_i16.ll
+++ b/llvm/test/CodeGen/AMDGPU/v_sat_pk_u8_i16.ll
@@ -1,11 +1,11 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefixes=SDAG-VI %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX9,SDAG-GFX9 %s
-; RUN: llc -march=amdgcn -mcpu=gfx1101 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11,SDAG-GFX11 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1101 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11 %s
 
 ; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs -global-isel < %s | FileCheck -check-prefixes=GISEL-VI %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -global-isel < %s | FileCheck -check-prefixes=GFX9,GISEL-GFX9 %s
-; RUN: llc -march=amdgcn -mcpu=gfx1101 -verify-machineinstrs -global-isel < %s | FileCheck -check-prefixes=GFX11,GISEL-GFX11 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -global-isel < %s | FileCheck -check-prefixes=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1101 -verify-machineinstrs -global-isel < %s | FileCheck -check-prefixes=GFX11 %s
 
 ; <GFX9 has no V_SAT_PK, GFX9+ has V_SAT_PK, GFX11 has V_SAT_PK with t16
 
@@ -31,21 +31,19 @@
 ; GFX9-LABEL: basic_smax_smin:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX9-NEXT:    v_mov_b32_e32 v2, 0xff
-; GFX9-NEXT:    v_med3_i16 v0, v0, 0, v2
-; GFX9-NEXT:    v_med3_i16 v1, v1, 0, v2
-; GFX9-NEXT:    s_mov_b32 s4, 0x5040100
-; GFX9-NEXT:    v_perm_b32 v0, v1, v0, s4
+; GFX9-NEXT:    v_and_b32_e32 v0, 0xffff, v0
+; GFX9-NEXT:    v_lshl_or_b32 v0, v1, 16, v0
+; GFX9-NEXT:    v_sat_pk_u8_i16_e32 v0, v0
 ; GFX9-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX11-LABEL: basic_smax_smin:
 ; GFX11:       ; %bb.0:
 ; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
-; GFX11-NEXT:    v_med3_i16 v0, v0, 0, 0xff
-; GFX11-NEXT:    v_med3_i16 v1, v1, 0, 0xff
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX11-NEXT:    v_perm_b32 v0, v1, v0, 0x5040100
+; GFX11-NEXT:    v_and_b32_e32 v0, 0xffff, v0
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-NEXT:    v_lshl_or_b32 v0, v1, 16, v0
+; GFX11-NEXT:    v_sat_pk_u8_i16_e32 v0, v0
 ; GFX11-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GISEL-VI-LABEL: basic_smax_smin:
@@ -79,29 +77,23 @@
 ; SDAG-VI-NEXT:    v_or_b32_e32 v0, v0, v1
 ; SDAG-VI-NEXT:    s_setpc_b64 s[30:31]
 ;
-; SDAG-GFX9-LABEL: basic_smin_smax:
-; SDAG-GFX9:       ; %bb.0:
-; SDAG-GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; SDAG-GFX9-NEXT:    v_min_i16_e32 v0, 0xff, v0
-; SDAG-GFX9-NEXT:    v_min_i16_e32 v1, 0xff, v1
-; SDAG-GFX9-NEXT:    v_max_i16_e32 v0, 0, v0
-; SDAG-GFX9-NEXT:    v_max_i16_e32 v1, 0, v1
-; SDAG-GFX9-NEXT:    s_mov_b32 s4, 0x5040100
-; SDAG-GFX9-NEXT:    v_perm_b32 v0, v1, v0, s4
-; SDAG-GFX9-NEXT:    s_setpc_b64 s[30:31]
+; GFX9-LABEL: basic_smin_smax:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    v_and_b32_e32 v0, 0xffff, v0
+; GFX9-NEXT:    v_lshl_or_b32 v0, v1, 16, v0
+; GFX9-NEXT:    v_sat_pk_u8_i16_e32 v0, v0
+; GFX9-NEXT:    s_setpc_b64 s[30:31]
 ;
-; SDAG-GFX11-LABEL: basic_smin_smax:
-; SDAG-GFX11:       ; %bb.0:
-; SDAG-GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; SDAG-GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
-; SDAG-GFX11-NEXT:    v_min_i16 v0, 0xff, v0
-; SDAG-GFX11-NEXT:    v_min_i16 v1, 0xff, v1
-; SDAG-GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
-; SDAG-GFX11-NEXT:    v_max_i16 v0, v0, 0
-; SDAG-GFX11-NEXT:    v_max_i16 v1, v1, 0
-; SDAG-GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; SDAG-GFX11-NEXT:    v_perm_b32 v0, v1, v0, 0x5040100
-; SDAG-GFX11-NEXT:    s_setpc_b64 s[30:31]
+; GFX11-LABEL: basic_smin_smax:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX11-NEXT:    v_and_b32_e32 v0, 0xffff, v0
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-NEXT:    v_lshl_or_b32 v0, v1, 16, v0
+; GFX11-NEXT:    v_sat_pk_u8_i16_e32 v0, v0
+; GFX11-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GISEL-VI-LABEL: basic_smin_smax:
 ; GISEL-VI:       ; %bb.0:
@@ -113,26 +105,6 @@
 ; GISEL-VI-NEXT:    v_max_i16_sdwa v1, v1, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
 ; GISEL-VI-NEXT:    v_or_b32_e32 v0, v0, v1
 ; GISEL-VI-NEXT:    s_setpc_b64 s[30:31]
-;
-; GISEL-GFX9-LABEL: basic_smin_smax:
-; GISEL-GFX9:       ; %bb.0:
-; GISEL-GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GISEL-GFX9-NEXT:    v_mov_b32_e32 v2, 0xff
-; GISEL-GFX9-NEXT:    v_med3_i16 v0, v0, 0, v2
-; GISEL-GFX9-NEXT:    v_med3_i16 v1, v1, 0, v2
-; GISEL-GFX9-NEXT:    s_mov_b32 s4, 0x5040100
-; GISEL-GFX9-NEXT:    v_perm_b32 v0, v1, v0, s4
-; GISEL-GFX9-NEXT:    s_setpc_b64 s[30:31]
-;
-; GISEL-GFX11-LABEL: basic_smin_smax:
-; GISEL-GFX11:       ; %bb.0:
-; GISEL-GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GISEL-GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
-; GISEL-GFX11-NEXT:    v_med3_i16 v0, v0, 0, 0xff
-; GISEL-GFX11-NEXT:    v_med3_i16 v1, v1, 0, 0xff
-; GISEL-GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GISEL-GFX11-NEXT:    v_perm_b32 v0, v1, v0, 0x5040100
-; GISEL-GFX11-NEXT:    s_setpc_b64 s[30:31]
   %src0.min = call i16 @llvm.smin.i16(i16 %src0, i16 255)
   %src0.clamp = call i16 @llvm.smax.i16(i16 %src0.min, i16 0)
   %src1.min = call i16 @llvm.smin.i16(i16 %src1, i16 255)
@@ -155,27 +127,23 @@
 ; SDAG-VI-NEXT:    v_or_b32_e32 v0, v0, v1
 ; SDAG-VI-NEXT:    s_setpc_b64 s[30:31]
 ;
-; SDAG-GFX9-LABEL: basic_smin_smax_combined:
-; SDAG-GFX9:       ; %bb.0:
-; SDAG-GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; SDAG-GFX9-NEXT:    v_min_i16_e32 v0, 0xff, v0
-; SDAG-GFX9-NEXT:    v_mov_b32_e32 v2, 0xff
-; SDAG-GFX9-NEXT:    v_max_i16_e32 v0, 0, v0
-; SDAG-GFX9-NEXT:    v_med3_i16 v1, v1, 0, v2
-; SDAG-GFX9-NEXT:    s_mov_b32 s4, 0x5040100
-; SDAG-GFX9-NEXT:    v_perm_b32 v0, v1, v0, s4
-; SDAG-GFX9-NEXT:    s_setpc_b64 s[30:31]
+; GFX9-LABEL: basic_smin_smax_combined:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    v_and_b32_e32 v0, 0xffff, v0
+; GFX9-NEXT:    v_lshl_or_b32 v0, v1, 16, v0
+; GFX9-NEXT:    v_sat_pk_u8_i16_e32 v0, v0
+; GFX9-NEXT:    s_setpc_b64 s[30:31]
 ;
-; SDAG-GFX11-LABEL: basic_smin_smax_combined:
-; SDAG-GFX11:       ; %bb.0:
-; SDAG-GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; SDAG-GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
-; SDAG-GFX11-NEXT:    v_min_i16 v0, 0xff, v0
-; SDAG-GFX11-NEXT:    v_med3_i16 v1, v1, 0, 0xff
-; SDAG-GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
-; SDAG-GFX11-NEXT:    v_max_i16 v0, v0, 0
-; SDAG-GFX11-NEXT:    v_perm_b32 v0, v1, v0, 0x5040100
-; SDAG-GFX11-NEXT:    s_setpc_b64 s[30:31]
+; GFX11-LABEL: basic_smin_smax_combined:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX11-NEXT:    v_and_b32_e32 v0, 0xffff, v0
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-NEXT:    v_lshl_or_b32 v0, v1, 16, v0
+; GFX11-NEXT:    v_sat_pk_u8_i16_e32 v0, v0
+; GFX11-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GISEL-VI-LABEL: basic_smin_smax_combined:
 ; GISEL-VI:       ; %bb.0:
@@ -187,26 +155,6 @@
 ; GISEL-VI-NEXT:    v_min_i16_sdwa v1, v1, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
 ; GISEL-VI-NEXT:    v_or_b32_e32 v0, v0, v1
 ; GISEL-VI-NEXT:    s_setpc_b64 s[30:31]
-;
-; GISEL-GFX9-LABEL: basic_smin_smax_combined:
-; GISEL-GFX9:       ; %bb.0:
-; GISEL-GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GISEL-GFX9-NEXT:    v_mov_b32_e32 v2, 0xff
-; GISEL-GFX9-NEXT:    v_med3_i16 v0, v0, 0, v2
-; GISEL-GFX9-NEXT:    v_med3_i16 v1, v1, 0, v2
-; GISEL-GFX9-NEXT:    s_mov_b32 s4, 0x5040100
-; GISEL-GFX9-NEXT:    v_perm_b32 v0, v1, v0, s4
-; GISEL-GFX9-NEXT:    s_setpc_b64 s[30:31]
-;
-; GISEL-GFX11-LABEL: basic_smin_smax_combined:
-; GISEL-GFX11:       ; %bb.0:
-; GISEL-GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GISEL-GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
-; GISEL-GFX11-NEXT:    v_med3_i16 v0, v0, 0, 0xff
-; GISEL-GFX11-NEXT:    v_med3_i16 v1, v1, 0, 0xff
-; GISEL-GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GISEL-GFX11-NEXT:    v_perm_b32 v0, v1, v0, 0x5040100
-; GISEL-GFX11-NEXT:    s_setpc_b64 s[30:31]
   %src0.min = call i16 @llvm.smin.i16(i16 %src0, i16 255)
   %src0.clamp = call i16 @llvm.smax.i16(i16 %src0.min, i16 0)
   %src1.max = call i16 @llvm.smax.i16(i16 %src1, i16 0)
@@ -229,21 +177,17 @@
 ; SDAG-VI-NEXT:    v_or_b32_sdwa v0, v1, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
 ; SDAG-VI-NEXT:    s_setpc_b64 s[30:31]
 ;
-; SDAG-GFX9-LABEL: vec_smax_smin:
-; SDAG-GFX9:       ; %bb.0:
-; SDAG-GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; SDAG-GFX9-NEXT:    v_pk_max_i16 v0, v0, 0
-; SDAG-GFX9-NEXT:    s_movk_i32 s4, 0xff
-; SDAG-GFX9-NEXT:    v_pk_min_i16 v0, v0, s4 op_sel_hi:[1,0]
-; SDAG-GFX9-NEXT:    s_setpc_b64 s[30:31]
+; GFX9-LABEL: vec_smax_smin:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    v_sat_pk_u8_i16_e32 v0, v0
+; GFX9-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX11-LABEL: vec_smax_smin:
 ; GFX11:       ; %bb.0:
 ; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
-; GFX11-NEXT:    v_pk_max_i16 v0, v0, 0
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX11-NEXT:    v_pk_min_i16 v0, 0xff, v0 op_sel_hi:[0,1]
+; GFX11-NEXT:    v_sat_pk_u8_i16_e32 v0, v0
 ; GFX11-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GISEL-VI-LABEL: vec_smax_smin:
@@ -257,14 +201,6 @@
 ; GISEL-VI-NEXT:    v_min_i16_sdwa v0, v0, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
 ; GISEL-VI-NEXT:    v_or_b32_e32 v0, v1, v0
 ; GISEL-VI-NEXT:    s_setpc_b64 s[30:31]
-;
-; GISEL-GFX9-LABEL: vec_smax_smin:
-; GISEL-GFX9:       ; %bb.0:
-; GISEL-GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GISEL-GFX9-NEXT:    v_pk_max_i16 v0, v0, 0
-; GISEL-GFX9-NEXT:    v_mov_b32_e32 v1, 0xff00ff
-; GISEL-GFX9-NEXT:    v_pk_min_i16 v0, v0, v1
-; GISEL-GFX9-NEXT:    s_setpc_b64 s[30:31]
   %src.max = call <2 x i16> @llvm.smax.v2i16(<2 x i16> %src, <2 x i16> <i16 0, i16 0>)
   %src.clamp = call <2 x i16> @llvm.smin.v2i16(<2 x i16> %src.max, <2 x i16> <i16 255, i16 255>)
   ret <2 x i16> %src.clamp
@@ -283,21 +219,17 @@
 ; SDAG-VI-NEXT:    v_or_b32_e32 v0, v0, v1
 ; SDAG-VI-NEXT:    s_setpc_b64 s[30:31]
 ;
-; SDAG-GFX9-LABEL: vec_smin_smax:
-; SDAG-GFX9:       ; %bb.0:
-; SDAG-GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; SDAG-GFX9-NEXT:    s_movk_i32 s4, 0xff
-; SDAG-GFX9-NEXT:    v_pk_min_i16 v0, v0, s4 op_sel_hi:[1,0]
-; SDAG-GFX9-NEXT:    v_pk_max_i16 v0, v0, 0
-; SDAG-GFX9-NEXT:    s_setpc_b64 s[30:31]
+; GFX9-LABEL: vec_smin_smax:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    v_sat_pk_u8_i16_e32 v0, v0
+; GFX9-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX11-LABEL: vec_smin_smax:
 ; GFX11:       ; %bb.0:
 ; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
-; GFX11-NEXT:    v_pk_min_i16 v0, 0xff, v0 op_sel_hi:[0,1]
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX11-NEXT:    v_pk_max_i16 v0, v0, 0
+; GFX11-NEXT:    v_sat_pk_u8_i16_e32 v0, v0
 ; GFX11-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GISEL-VI-LABEL: vec_smin_smax:
@@ -311,14 +243,6 @@
 ; GISEL-VI-NEXT:    v_max_i16_sdwa v0, v0, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
 ; GISEL-VI-NEXT:    v_or_b32_e32 v0, v1, v0
 ; GISEL-VI-NEXT:    s_setpc_b64 s[30:31]
-;
-; GISEL-GFX9-LABEL: vec_smin_smax:
-; GISEL-GFX9:       ; %bb.0:
-; GISEL-GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GISEL-GFX9-NEXT:    v_mov_b32_e32 v1, 0xff00ff
-; GISEL-GFX9-NEXT:    v_pk_min_i16 v0, v0, v1
-; GISEL-GFX9-NEXT:    v_pk_max_i16 v0, v0, 0
-; GISEL-GFX9-NEXT:    s_setpc_b64 s[30:31]
   %src.min = call <2 x i16> @llvm.smin.v2i16(<2 x i16> %src, <2 x i16> <i16 255, i16 255>)
   %src.clamp = call <2 x i16> @llvm.smax.v2i16(<2 x i16> %src.min, <2 x i16> <i16 0, i16 0>)
   ret <2 x i16> %src.clamp