[AMDGPU] Stop reserving $vcc_hi in wave32 mode (#87783)

This gives us one extra SGPR to play with. The comment suggested that it
could cause bugs, but I have tested it with Vulkan CTS with the default
wave size for compute shaders set to 32 and did not find any problems.

Author: jayfoad

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

@@ -612,13 +612,6 @@ BitVector SIRegisterInfo::getReservedRegs(const MachineFunction &MF) const {
   // Reserve null register - it shall never be allocated
   reserveRegisterTuples(Reserved, AMDGPU::SGPR_NULL64);
 
-  // Disallow vcc_hi allocation in wave32. It may be allocated but most likely
-  // will result in bugs.
-  if (isWave32) {
-    Reserved.set(AMDGPU::VCC);
-    Reserved.set(AMDGPU::VCC_HI);
-  }
-
   // Reserve SGPRs.
   //
   unsigned MaxNumSGPRs = ST.getMaxNumSGPRs(MF);

llvm/test/CodeGen/AMDGPU/bf16.ll

@@ -38342,12 +38342,11 @@ define <32 x bfloat> @v_vselect_v32bf16(<32 x i1> %cond, <32 x bfloat> %a, <32 x
 ; GFX10-NEXT:    v_and_b32_e32 v2, 1, v2
 ; GFX10-NEXT:    v_and_b32_e32 v4, 1, v4
 ; GFX10-NEXT:    v_and_b32_e32 v6, 1, v6
-; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    v_and_b32_e32 v8, 1, v8
 ; GFX10-NEXT:    v_and_b32_e32 v10, 1, v10
+; GFX10-NEXT:    v_writelane_b32 v40, s31, 1
 ; GFX10-NEXT:    v_and_b32_e32 v1, 1, v1
 ; GFX10-NEXT:    v_and_b32_e32 v3, 1, v3
-; GFX10-NEXT:    v_writelane_b32 v40, s34, 2
 ; GFX10-NEXT:    v_and_b32_e32 v5, 1, v5
 ; GFX10-NEXT:    v_and_b32_e32 v7, 1, v7
 ; GFX10-NEXT:    v_and_b32_e32 v9, 1, v9
@@ -38366,7 +38365,7 @@ define <32 x bfloat> @v_vselect_v32bf16(<32 x i1> %cond, <32 x bfloat> %a, <32 x
 ; GFX10-NEXT:    v_cmp_eq_u32_e64 s17, 1, v4
 ; GFX10-NEXT:    v_cmp_eq_u32_e64 s18, 1, v2
 ; GFX10-NEXT:    v_cmp_eq_u32_e64 s19, 1, v0
-; GFX10-NEXT:    v_writelane_b32 v40, s35, 3
+; GFX10-NEXT:    v_writelane_b32 v40, s34, 2
 ; GFX10-NEXT:    v_cmp_eq_u32_e64 s20, 1, v27
 ; GFX10-NEXT:    v_cmp_eq_u32_e64 s21, 1, v25
 ; GFX10-NEXT:    v_cmp_eq_u32_e64 s22, 1, v23
@@ -38377,10 +38376,10 @@ define <32 x bfloat> @v_vselect_v32bf16(<32 x i1> %cond, <32 x bfloat> %a, <32 x
 ; GFX10-NEXT:    v_cmp_eq_u32_e64 s27, 1, v13
 ; GFX10-NEXT:    v_cmp_eq_u32_e64 s28, 1, v11
 ; GFX10-NEXT:    v_cmp_eq_u32_e64 s29, 1, v7
-; GFX10-NEXT:    v_cmp_eq_u32_e64 s30, 1, v3
-; GFX10-NEXT:    v_cmp_eq_u32_e64 s31, 1, v1
-; GFX10-NEXT:    v_cmp_eq_u32_e64 s34, 1, v5
-; GFX10-NEXT:    v_cmp_eq_u32_e64 s35, 1, v9
+; GFX10-NEXT:    v_cmp_eq_u32_e64 vcc_hi, 1, v3
+; GFX10-NEXT:    v_cmp_eq_u32_e64 s30, 1, v1
+; GFX10-NEXT:    v_cmp_eq_u32_e64 s31, 1, v5
+; GFX10-NEXT:    v_cmp_eq_u32_e64 s34, 1, v9
 ; GFX10-NEXT:    s_waitcnt vmcnt(32)
 ; GFX10-NEXT:    v_lshrrev_b32_e32 v0, 16, v31
 ; GFX10-NEXT:    s_waitcnt vmcnt(31)
@@ -38460,10 +38459,10 @@ define <32 x bfloat> @v_vselect_v32bf16(<32 x i1> %cond, <32 x bfloat> %a, <32 x
 ; GFX10-NEXT:    v_cndmask_b32_e64 v6, v29, v39, s27
 ; GFX10-NEXT:    v_cndmask_b32_e64 v5, v28, v26, s28
 ; GFX10-NEXT:    v_cndmask_b32_e64 v20, v51, v20, s29
-; GFX10-NEXT:    v_cndmask_b32_e64 v0, v14, v12, s31
-; GFX10-NEXT:    v_cndmask_b32_e64 v1, v55, v16, s30
-; GFX10-NEXT:    v_cndmask_b32_e64 v2, v53, v18, s34
-; GFX10-NEXT:    v_cndmask_b32_e64 v12, v24, v22, s35
+; GFX10-NEXT:    v_cndmask_b32_e64 v0, v14, v12, s30
+; GFX10-NEXT:    v_cndmask_b32_e64 v1, v55, v16, vcc_hi
+; GFX10-NEXT:    v_cndmask_b32_e64 v2, v53, v18, s31
+; GFX10-NEXT:    v_cndmask_b32_e64 v12, v24, v22, s34
 ; GFX10-NEXT:    v_cndmask_b32_e64 v16, v4, v3, s4
 ; GFX10-NEXT:    v_perm_b32 v0, v0, v64, 0x5040100
 ; GFX10-NEXT:    v_perm_b32 v1, v1, v54, 0x5040100
@@ -38481,7 +38480,6 @@ define <32 x bfloat> @v_vselect_v32bf16(<32 x i1> %cond, <32 x bfloat> %a, <32 x
 ; GFX10-NEXT:    v_perm_b32 v13, v66, v13, 0x5040100
 ; GFX10-NEXT:    v_perm_b32 v14, v65, v17, 0x5040100
 ; GFX10-NEXT:    v_perm_b32 v15, v16, v15, 0x5040100
-; GFX10-NEXT:    v_readlane_b32 s35, v40, 3
 ; GFX10-NEXT:    v_readlane_b32 s34, v40, 2
 ; GFX10-NEXT:    v_readlane_b32 s31, v40, 1
 ; GFX10-NEXT:    v_readlane_b32 s30, v40, 0

llvm/test/CodeGen/AMDGPU/llvm.is.fpclass.f16.ll

@@ -1259,17 +1259,17 @@ define <4 x i1> @isnan_v4f16(<4 x half> %x) nounwind {
 ; GFX10SELDAG-LABEL: isnan_v4f16:
 ; GFX10SELDAG:       ; %bb.0:
 ; GFX10SELDAG-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX10SELDAG-NEXT:    v_mov_b32_e32 v2, 3
-; GFX10SELDAG-NEXT:    v_cmp_class_f16_e64 s5, v0, 3
-; GFX10SELDAG-NEXT:    v_cmp_class_f16_sdwa s4, v1, v2 src0_sel:WORD_1 src1_sel:DWORD
-; GFX10SELDAG-NEXT:    v_cndmask_b32_e64 v4, 0, 1, s5
-; GFX10SELDAG-NEXT:    v_cmp_class_f16_sdwa s5, v0, v2 src0_sel:WORD_1 src1_sel:DWORD
+; GFX10SELDAG-NEXT:    v_cmp_class_f16_e64 s4, v0, 3
+; GFX10SELDAG-NEXT:    v_mov_b32_e32 v3, 3
+; GFX10SELDAG-NEXT:    v_cndmask_b32_e64 v5, 0, 1, s4
+; GFX10SELDAG-NEXT:    v_cmp_class_f16_e64 s4, v1, 3
+; GFX10SELDAG-NEXT:    v_cndmask_b32_e64 v2, 0, 1, s4
+; GFX10SELDAG-NEXT:    v_cmp_class_f16_sdwa s4, v0, v3 src0_sel:WORD_1 src1_sel:DWORD
+; GFX10SELDAG-NEXT:    v_mov_b32_e32 v0, v5
+; GFX10SELDAG-NEXT:    v_cndmask_b32_e64 v4, 0, 1, s4
+; GFX10SELDAG-NEXT:    v_cmp_class_f16_sdwa s4, v1, v3 src0_sel:WORD_1 src1_sel:DWORD
+; GFX10SELDAG-NEXT:    v_mov_b32_e32 v1, v4
 ; GFX10SELDAG-NEXT:    v_cndmask_b32_e64 v3, 0, 1, s4
-; GFX10SELDAG-NEXT:    v_mov_b32_e32 v0, v4
-; GFX10SELDAG-NEXT:    v_cndmask_b32_e64 v5, 0, 1, s5
-; GFX10SELDAG-NEXT:    v_cmp_class_f16_e64 s5, v1, 3
-; GFX10SELDAG-NEXT:    v_mov_b32_e32 v1, v5
-; GFX10SELDAG-NEXT:    v_cndmask_b32_e64 v2, 0, 1, s5
 ; GFX10SELDAG-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX10GLISEL-LABEL: isnan_v4f16:

llvm/test/CodeGen/AMDGPU/load-constant-i16.ll

@@ -7404,35 +7404,35 @@ define amdgpu_kernel void @constant_sextload_v16i16_to_v16i64(ptr addrspace(1) %
 ; GFX12-NEXT:    v_dual_mov_b32 v4, s22 :: v_dual_mov_b32 v9, s31
 ; GFX12-NEXT:    v_dual_mov_b32 v8, s30 :: v_dual_mov_b32 v11, s35
 ; GFX12-NEXT:    v_dual_mov_b32 v10, s34 :: v_dual_mov_b32 v3, s5
-; GFX12-NEXT:    s_bfe_i64 s[10:11], s[0:1], 0x100000
-; GFX12-NEXT:    s_lshr_b32 s12, s0, 16
-; GFX12-NEXT:    s_mov_b32 s14, s1
-; GFX12-NEXT:    s_lshr_b32 s16, s1, 16
-; GFX12-NEXT:    s_bfe_i64 s[0:1], s[2:3], 0x100000
+; GFX12-NEXT:    s_bfe_i64 s[16:17], s[2:3], 0x100000
 ; GFX12-NEXT:    s_lshr_b32 s2, s2, 16
 ; GFX12-NEXT:    s_bfe_i64 s[6:7], s[6:7], 0x100000
 ; GFX12-NEXT:    v_dual_mov_b32 v0, s28 :: v_dual_mov_b32 v5, s23
 ; GFX12-NEXT:    v_dual_mov_b32 v2, s4 :: v_dual_mov_b32 v13, s25
+; GFX12-NEXT:    s_mov_b32 s12, s1
+; GFX12-NEXT:    s_lshr_b32 s14, s1, 16
 ; GFX12-NEXT:    s_bfe_i64 s[18:19], s[18:19], 0x100000
 ; GFX12-NEXT:    s_bfe_i64 s[20:21], s[20:21], 0x100000
 ; GFX12-NEXT:    v_dual_mov_b32 v12, s24 :: v_dual_mov_b32 v15, s27
 ; GFX12-NEXT:    v_dual_mov_b32 v14, s26 :: v_dual_mov_b32 v7, s7
+; GFX12-NEXT:    s_bfe_i64 s[10:11], s[0:1], 0x100000
+; GFX12-NEXT:    s_lshr_b32 s0, s0, 16
 ; GFX12-NEXT:    s_bfe_i64 s[2:3], s[2:3], 0x100000
 ; GFX12-NEXT:    v_dual_mov_b32 v6, s6 :: v_dual_mov_b32 v17, s19
+; GFX12-NEXT:    s_bfe_i64 s[12:13], s[12:13], 0x100000
 ; GFX12-NEXT:    s_bfe_i64 s[14:15], s[14:15], 0x100000
-; GFX12-NEXT:    s_bfe_i64 s[16:17], s[16:17], 0x100000
 ; GFX12-NEXT:    v_dual_mov_b32 v16, s18 :: v_dual_mov_b32 v19, s21
 ; GFX12-NEXT:    v_mov_b32_e32 v18, s20
-; GFX12-NEXT:    s_bfe_i64 s[12:13], s[12:13], 0x100000
+; GFX12-NEXT:    s_bfe_i64 s[0:1], s[0:1], 0x100000
 ; GFX12-NEXT:    s_clause 0x1
 ; GFX12-NEXT:    global_store_b128 v24, v[8:11], s[8:9] offset:80
 ; GFX12-NEXT:    global_store_b128 v24, v[0:3], s[8:9] offset:64
-; GFX12-NEXT:    v_dual_mov_b32 v1, s1 :: v_dual_mov_b32 v0, s0
+; GFX12-NEXT:    v_dual_mov_b32 v1, s17 :: v_dual_mov_b32 v0, s16
 ; GFX12-NEXT:    v_dual_mov_b32 v3, s3 :: v_dual_mov_b32 v2, s2
-; GFX12-NEXT:    v_dual_mov_b32 v9, s15 :: v_dual_mov_b32 v8, s14
-; GFX12-NEXT:    v_dual_mov_b32 v11, s17 :: v_dual_mov_b32 v10, s16
+; GFX12-NEXT:    v_dual_mov_b32 v9, s13 :: v_dual_mov_b32 v8, s12
+; GFX12-NEXT:    v_dual_mov_b32 v11, s15 :: v_dual_mov_b32 v10, s14
 ; GFX12-NEXT:    v_dual_mov_b32 v21, s11 :: v_dual_mov_b32 v20, s10
-; GFX12-NEXT:    v_dual_mov_b32 v23, s13 :: v_dual_mov_b32 v22, s12
+; GFX12-NEXT:    v_dual_mov_b32 v23, s1 :: v_dual_mov_b32 v22, s0
 ; GFX12-NEXT:    s_clause 0x5
 ; GFX12-NEXT:    global_store_b128 v24, v[12:15], s[8:9] offset:112
 ; GFX12-NEXT:    global_store_b128 v24, v[4:7], s[8:9] offset:96

llvm/test/CodeGen/AMDGPU/load-constant-i8.ll

@@ -8808,90 +8808,90 @@ define amdgpu_kernel void @constant_sextload_v32i8_to_v32i64(ptr addrspace(1) %o
 ; GFX12-NEXT:    v_lshrrev_b16 v2, 8, s6
 ; GFX12-NEXT:    v_lshrrev_b16 v4, 8, s5
 ; GFX12-NEXT:    v_lshrrev_b16 v8, 8, s2
-; GFX12-NEXT:    s_lshr_b32 s24, s7, 16
+; GFX12-NEXT:    s_lshr_b32 s22, s7, 16
 ; GFX12-NEXT:    v_bfe_i32 v31, v1, 0, 8
-; GFX12-NEXT:    s_lshr_b32 s42, s2, 24
-; GFX12-NEXT:    s_mov_b32 s48, s7
+; GFX12-NEXT:    s_lshr_b32 s40, s2, 24
+; GFX12-NEXT:    s_mov_b32 s46, s7
 ; GFX12-NEXT:    v_lshrrev_b16 v5, 8, s4
 ; GFX12-NEXT:    v_lshrrev_b16 v7, 8, s1
-; GFX12-NEXT:    s_lshr_b32 s26, s6, 16
-; GFX12-NEXT:    s_lshr_b32 s44, s1, 16
+; GFX12-NEXT:    s_lshr_b32 s24, s6, 16
+; GFX12-NEXT:    s_lshr_b32 s42, s1, 16
 ; GFX12-NEXT:    s_ashr_i64 s[58:59], s[6:7], 56
-; GFX12-NEXT:    s_bfe_i64 s[48:49], s[48:49], 0x80000
-; GFX12-NEXT:    s_bfe_i64 s[42:43], s[42:43], 0x80000
-; GFX12-NEXT:    s_bfe_i64 s[24:25], s[24:25], 0x80000
+; GFX12-NEXT:    s_bfe_i64 s[46:47], s[46:47], 0x80000
+; GFX12-NEXT:    s_bfe_i64 s[40:41], s[40:41], 0x80000
+; GFX12-NEXT:    s_bfe_i64 s[22:23], s[22:23], 0x80000
 ; GFX12-NEXT:    v_lshrrev_b16 v6, 8, s3
 ; GFX12-NEXT:    v_lshrrev_b16 v3, 8, s0
-; GFX12-NEXT:    v_dual_mov_b32 v0, 0 :: v_dual_mov_b32 v33, s24
-; GFX12-NEXT:    s_lshr_b32 s28, s6, 24
-; GFX12-NEXT:    s_lshr_b32 s30, s5, 16
-; GFX12-NEXT:    s_lshr_b32 s40, s2, 16
+; GFX12-NEXT:    v_dual_mov_b32 v0, 0 :: v_dual_mov_b32 v33, s22
+; GFX12-NEXT:    s_lshr_b32 s26, s6, 24
+; GFX12-NEXT:    s_lshr_b32 s28, s5, 16
+; GFX12-NEXT:    s_lshr_b32 s38, s2, 16
 ; GFX12-NEXT:    v_bfe_i32 v11, v8, 0, 8
 ; GFX12-NEXT:    v_bfe_i32 v23, v4, 0, 8
 ; GFX12-NEXT:    v_bfe_i32 v27, v2, 0, 8
 ; GFX12-NEXT:    v_ashrrev_i32_e32 v32, 31, v31
-; GFX12-NEXT:    s_bfe_i64 s[44:45], s[44:45], 0x80000
-; GFX12-NEXT:    s_bfe_i64 s[26:27], s[26:27], 0x80000
-; GFX12-NEXT:    v_dual_mov_b32 v34, s25 :: v_dual_mov_b32 v35, s58
-; GFX12-NEXT:    v_dual_mov_b32 v36, s59 :: v_dual_mov_b32 v37, s26
-; GFX12-NEXT:    v_dual_mov_b32 v56, s43 :: v_dual_mov_b32 v29, s48
-; GFX12-NEXT:    v_mov_b32_e32 v30, s49
-; GFX12-NEXT:    s_lshr_b32 s46, s0, 24
-; GFX12-NEXT:    s_mov_b32 s50, s5
-; GFX12-NEXT:    s_mov_b32 s52, s3
-; GFX12-NEXT:    s_lshr_b32 s34, s4, 16
-; GFX12-NEXT:    s_lshr_b32 s36, s4, 24
-; GFX12-NEXT:    s_ashr_i64 s[22:23], s[2:3], 56
+; GFX12-NEXT:    s_bfe_i64 s[42:43], s[42:43], 0x80000
+; GFX12-NEXT:    s_bfe_i64 s[24:25], s[24:25], 0x80000
+; GFX12-NEXT:    v_dual_mov_b32 v34, s23 :: v_dual_mov_b32 v35, s58
+; GFX12-NEXT:    v_dual_mov_b32 v36, s59 :: v_dual_mov_b32 v37, s24
+; GFX12-NEXT:    v_dual_mov_b32 v56, s41 :: v_dual_mov_b32 v29, s46
+; GFX12-NEXT:    v_mov_b32_e32 v30, s47
+; GFX12-NEXT:    s_lshr_b32 s44, s0, 24
+; GFX12-NEXT:    s_mov_b32 s48, s5
+; GFX12-NEXT:    s_mov_b32 s50, s3
+; GFX12-NEXT:    s_lshr_b32 s30, s4, 16
+; GFX12-NEXT:    s_lshr_b32 s34, s4, 24
+; GFX12-NEXT:    s_ashr_i64 s[54:55], s[2:3], 56
 ; GFX12-NEXT:    s_ashr_i64 s[56:57], s[4:5], 56
 ; GFX12-NEXT:    v_bfe_i32 v7, v7, 0, 8
 ; GFX12-NEXT:    v_bfe_i32 v19, v5, 0, 8
-; GFX12-NEXT:    s_bfe_i64 s[40:41], s[40:41], 0x80000
-; GFX12-NEXT:    s_bfe_i64 s[30:31], s[30:31], 0x80000
+; GFX12-NEXT:    s_bfe_i64 s[38:39], s[38:39], 0x80000
 ; GFX12-NEXT:    s_bfe_i64 s[28:29], s[28:29], 0x80000
-; GFX12-NEXT:    s_lshr_b32 s38, s3, 16
-; GFX12-NEXT:    s_mov_b32 s54, s1
+; GFX12-NEXT:    s_bfe_i64 s[26:27], s[26:27], 0x80000
+; GFX12-NEXT:    s_lshr_b32 s36, s3, 16
+; GFX12-NEXT:    s_mov_b32 s52, s1
 ; GFX12-NEXT:    s_bfe_i64 s[12:13], s[2:3], 0x80000
 ; GFX12-NEXT:    s_bfe_i64 s[14:15], s[4:5], 0x80000
 ; GFX12-NEXT:    s_bfe_i64 s[16:17], s[6:7], 0x80000
-; GFX12-NEXT:    s_bfe_i64 s[2:3], s[52:53], 0x80000
-; GFX12-NEXT:    s_bfe_i64 s[4:5], s[50:51], 0x80000
-; GFX12-NEXT:    s_bfe_i64 s[6:7], s[46:47], 0x80000
+; GFX12-NEXT:    s_bfe_i64 s[2:3], s[50:51], 0x80000
+; GFX12-NEXT:    s_bfe_i64 s[4:5], s[48:49], 0x80000
+; GFX12-NEXT:    s_bfe_i64 s[6:7], s[44:45], 0x80000
 ; GFX12-NEXT:    s_lshr_b32 s20, s0, 16
 ; GFX12-NEXT:    s_ashr_i64 s[18:19], s[0:1], 56
 ; GFX12-NEXT:    v_bfe_i32 v3, v3, 0, 8
 ; GFX12-NEXT:    v_bfe_i32 v15, v6, 0, 8
-; GFX12-NEXT:    s_bfe_i64 s[36:37], s[36:37], 0x80000
 ; GFX12-NEXT:    s_bfe_i64 s[34:35], s[34:35], 0x80000
-; GFX12-NEXT:    v_dual_mov_b32 v38, s27 :: v_dual_mov_b32 v39, s28
-; GFX12-NEXT:    v_dual_mov_b32 v40, s29 :: v_dual_mov_b32 v41, s30
-; GFX12-NEXT:    v_dual_mov_b32 v42, s31 :: v_dual_mov_b32 v43, s56
-; GFX12-NEXT:    v_dual_mov_b32 v44, s57 :: v_dual_mov_b32 v45, s34
-; GFX12-NEXT:    v_dual_mov_b32 v52, s23 :: v_dual_mov_b32 v53, s40
-; GFX12-NEXT:    v_dual_mov_b32 v54, s41 :: v_dual_mov_b32 v55, s42
+; GFX12-NEXT:    s_bfe_i64 s[30:31], s[30:31], 0x80000
+; GFX12-NEXT:    v_dual_mov_b32 v38, s25 :: v_dual_mov_b32 v39, s26
+; GFX12-NEXT:    v_dual_mov_b32 v40, s27 :: v_dual_mov_b32 v41, s28
+; GFX12-NEXT:    v_dual_mov_b32 v42, s29 :: v_dual_mov_b32 v43, s56
+; GFX12-NEXT:    v_dual_mov_b32 v44, s57 :: v_dual_mov_b32 v45, s30
+; GFX12-NEXT:    v_dual_mov_b32 v52, s55 :: v_dual_mov_b32 v53, s38
+; GFX12-NEXT:    v_dual_mov_b32 v54, s39 :: v_dual_mov_b32 v55, s40
 ; GFX12-NEXT:    s_bfe_i64 s[10:11], s[0:1], 0x80000
-; GFX12-NEXT:    s_bfe_i64 s[0:1], s[54:55], 0x80000
+; GFX12-NEXT:    s_bfe_i64 s[0:1], s[52:53], 0x80000
 ; GFX12-NEXT:    v_ashrrev_i32_e32 v12, 31, v11
 ; GFX12-NEXT:    v_ashrrev_i32_e32 v24, 31, v23
 ; GFX12-NEXT:    v_ashrrev_i32_e32 v28, 31, v27
 ; GFX12-NEXT:    global_store_b128 v0, v[33:36], s[8:9] offset:240
-; GFX12-NEXT:    v_mov_b32_e32 v33, s44
+; GFX12-NEXT:    v_mov_b32_e32 v33, s42
 ; GFX12-NEXT:    global_store_b128 v0, v[29:32], s[8:9] offset:224
 ; GFX12-NEXT:    v_dual_mov_b32 v25, s16 :: v_dual_mov_b32 v26, s17
 ; GFX12-NEXT:    v_dual_mov_b32 v32, s7 :: v_dual_mov_b32 v21, s4
 ; GFX12-NEXT:    v_dual_mov_b32 v22, s5 :: v_dual_mov_b32 v17, s14
 ; GFX12-NEXT:    v_dual_mov_b32 v14, s3 :: v_dual_mov_b32 v9, s12
 ; GFX12-NEXT:    v_dual_mov_b32 v10, s13 :: v_dual_mov_b32 v5, s0
 ; GFX12-NEXT:    s_bfe_i64 s[20:21], s[20:21], 0x80000
-; GFX12-NEXT:    s_bfe_i64 s[38:39], s[38:39], 0x80000
-; GFX12-NEXT:    v_dual_mov_b32 v46, s35 :: v_dual_mov_b32 v47, s36
-; GFX12-NEXT:    v_dual_mov_b32 v48, s37 :: v_dual_mov_b32 v49, s38
-; GFX12-NEXT:    v_dual_mov_b32 v34, s45 :: v_dual_mov_b32 v35, s18
+; GFX12-NEXT:    s_bfe_i64 s[36:37], s[36:37], 0x80000
+; GFX12-NEXT:    v_dual_mov_b32 v46, s31 :: v_dual_mov_b32 v47, s34
+; GFX12-NEXT:    v_dual_mov_b32 v48, s35 :: v_dual_mov_b32 v49, s36
+; GFX12-NEXT:    v_dual_mov_b32 v34, s43 :: v_dual_mov_b32 v35, s18
 ; GFX12-NEXT:    v_dual_mov_b32 v36, s19 :: v_dual_mov_b32 v29, s20
 ; GFX12-NEXT:    v_ashrrev_i32_e32 v8, 31, v7
 ; GFX12-NEXT:    v_ashrrev_i32_e32 v20, 31, v19
 ; GFX12-NEXT:    v_dual_mov_b32 v18, s15 :: v_dual_mov_b32 v13, s2
 ; GFX12-NEXT:    v_dual_mov_b32 v6, s1 :: v_dual_mov_b32 v1, s10
-; GFX12-NEXT:    v_dual_mov_b32 v50, s39 :: v_dual_mov_b32 v51, s22
+; GFX12-NEXT:    v_dual_mov_b32 v50, s37 :: v_dual_mov_b32 v51, s54
 ; GFX12-NEXT:    v_dual_mov_b32 v30, s21 :: v_dual_mov_b32 v31, s6
 ; GFX12-NEXT:    v_ashrrev_i32_e32 v4, 31, v3
 ; GFX12-NEXT:    v_ashrrev_i32_e32 v16, 31, v15