aboutsummaryrefslogtreecommitdiff
path: root/llvm/test/CodeGen/AMDGPU/spillv16.ll
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/spillv16.ll')
-rw-r--r--llvm/test/CodeGen/AMDGPU/spillv16.ll235
1 files changed, 235 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/spillv16.ll b/llvm/test/CodeGen/AMDGPU/spillv16.ll
index 0e45df2..2d54ac8 100644
--- a/llvm/test/CodeGen/AMDGPU/spillv16.ll
+++ b/llvm/test/CodeGen/AMDGPU/spillv16.ll
@@ -1,6 +1,8 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -mattr=+real-true16 -enable-misched=0 -post-RA-scheduler=0 -stress-regalloc=8 < %s | FileCheck %s -check-prefixes=GCN,GCN-TRUE16
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -mattr=-real-true16 -enable-misched=0 -post-RA-scheduler=0 -stress-regalloc=8 < %s | FileCheck %s -check-prefixes=GCN,GCN-FAKE16
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 -mattr=+real-true16 -enable-misched=0 -post-RA-scheduler=0 -stress-regalloc=8 < %s | FileCheck %s -check-prefixes=GFX1250,GFX1250-TRUE16
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 -mattr=-real-true16 -enable-misched=0 -post-RA-scheduler=0 -stress-regalloc=8 < %s | FileCheck %s -check-prefixes=GFX1250,GFX1250-FAKE16
define void @spill_i16_alu() {
; GCN-TRUE16-LABEL: spill_i16_alu:
@@ -32,6 +34,41 @@ define void @spill_i16_alu() {
; GCN-FAKE16-NEXT: scratch_store_b16 off, v0, s32 dlc
; GCN-FAKE16-NEXT: s_waitcnt_vscnt null, 0x0
; GCN-FAKE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX1250-TRUE16-LABEL: spill_i16_alu:
+; GFX1250-TRUE16: ; %bb.0: ; %entry
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-TRUE16-NEXT: s_wait_kmcnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_load_u16 v0, off, s32 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: v_add_nc_u16 v0.l, 0x7b, v0.l
+; GFX1250-TRUE16-NEXT: scratch_store_b16 off, v0, s32 offset:2 ; 2-byte Folded Spill
+; GFX1250-TRUE16-NEXT: s_wait_xcnt 0x0
+; GFX1250-TRUE16-NEXT: ;;#ASMSTART
+; GFX1250-TRUE16-NEXT: ;;#ASMEND
+; GFX1250-TRUE16-NEXT: scratch_load_u16 v1, off, s32 offset:2 th:TH_LOAD_LU ; 2-byte Folded Reload
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: v_mov_b16_e32 v0.l, v1.l
+; GFX1250-TRUE16-NEXT: scratch_store_b16 off, v0, s32 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-TRUE16-NEXT: s_set_pc_i64 s[30:31]
+;
+; GFX1250-FAKE16-LABEL: spill_i16_alu:
+; GFX1250-FAKE16: ; %bb.0: ; %entry
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-FAKE16-NEXT: s_wait_kmcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_load_u16 v0, off, s32 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: v_add_nc_u16 v0, 0x7b, v0
+; GFX1250-FAKE16-NEXT: scratch_store_b32 off, v0, s32 offset:4 ; 4-byte Folded Spill
+; GFX1250-FAKE16-NEXT: s_wait_xcnt 0x0
+; GFX1250-FAKE16-NEXT: ;;#ASMSTART
+; GFX1250-FAKE16-NEXT: ;;#ASMEND
+; GFX1250-FAKE16-NEXT: scratch_load_b32 v0, off, s32 offset:4 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_store_b16 off, v0, s32 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-FAKE16-NEXT: s_set_pc_i64 s[30:31]
entry:
%alloca = alloca i16, i32 1, align 4, addrspace(5)
@@ -88,6 +125,51 @@ define void @spill_i16_alu_two_vals() {
; GCN-FAKE16-NEXT: scratch_store_b16 off, v0, s32 offset:4 dlc
; GCN-FAKE16-NEXT: s_waitcnt_vscnt null, 0x0
; GCN-FAKE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX1250-TRUE16-LABEL: spill_i16_alu_two_vals:
+; GFX1250-TRUE16: ; %bb.0: ; %entry
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-TRUE16-NEXT: s_wait_kmcnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_load_u16 v0, off, s32 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: v_add_nc_u16 v0.l, 0x7b, v0.l
+; GFX1250-TRUE16-NEXT: scratch_store_b16 off, v0, s32 offset:6 ; 2-byte Folded Spill
+; GFX1250-TRUE16-NEXT: s_wait_xcnt 0x0
+; GFX1250-TRUE16-NEXT: ;;#ASMSTART
+; GFX1250-TRUE16-NEXT: ;;#ASMEND
+; GFX1250-TRUE16-NEXT: scratch_load_u16 v0, off, s32 offset:4 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_load_u16 v1, off, s32 offset:6 th:TH_LOAD_LU ; 2-byte Folded Reload
+; GFX1250-TRUE16-NEXT: v_add_nc_u16 v0.l, 0x7b, v0.l
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: v_mov_b16_e32 v0.h, v1.l
+; GFX1250-TRUE16-NEXT: scratch_store_d16_hi_b16 off, v0, s32 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_store_b16 off, v0, s32 offset:4 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-TRUE16-NEXT: s_set_pc_i64 s[30:31]
+;
+; GFX1250-FAKE16-LABEL: spill_i16_alu_two_vals:
+; GFX1250-FAKE16: ; %bb.0: ; %entry
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-FAKE16-NEXT: s_wait_kmcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_load_u16 v0, off, s32 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: v_add_nc_u16 v0, 0x7b, v0
+; GFX1250-FAKE16-NEXT: scratch_store_b32 off, v0, s32 offset:8 ; 4-byte Folded Spill
+; GFX1250-FAKE16-NEXT: s_wait_xcnt 0x0
+; GFX1250-FAKE16-NEXT: ;;#ASMSTART
+; GFX1250-FAKE16-NEXT: ;;#ASMEND
+; GFX1250-FAKE16-NEXT: scratch_load_u16 v0, off, s32 offset:4 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_load_b32 v1, off, s32 offset:8 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-FAKE16-NEXT: v_add_nc_u16 v0, 0x7b, v0
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_store_b16 off, v1, s32 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_store_b16 off, v0, s32 offset:4 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-FAKE16-NEXT: s_set_pc_i64 s[30:31]
entry:
%alloca = alloca i16, i32 1, align 4, addrspace(5)
%alloca2 = alloca i16, i32 1, align 4, addrspace(5)
@@ -140,6 +222,22 @@ define void @spill_i16() {
; GCN-FAKE16-NEXT: scratch_store_b16 off, v0, s32 dlc
; GCN-FAKE16-NEXT: s_waitcnt_vscnt null, 0x0
; GCN-FAKE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX1250-LABEL: spill_i16:
+; GFX1250: ; %bb.0: ; %entry
+; GFX1250-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-NEXT: s_wait_kmcnt 0x0
+; GFX1250-NEXT: scratch_load_u16 v0, off, s32 scope:SCOPE_SYS
+; GFX1250-NEXT: s_wait_loadcnt 0x0
+; GFX1250-NEXT: scratch_store_b32 off, v0, s32 offset:4 ; 4-byte Folded Spill
+; GFX1250-NEXT: s_wait_xcnt 0x0
+; GFX1250-NEXT: ;;#ASMSTART
+; GFX1250-NEXT: ;;#ASMEND
+; GFX1250-NEXT: scratch_load_b32 v0, off, s32 offset:4 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-NEXT: s_wait_loadcnt 0x0
+; GFX1250-NEXT: scratch_store_b16 off, v0, s32 scope:SCOPE_SYS
+; GFX1250-NEXT: s_wait_storecnt 0x0
+; GFX1250-NEXT: s_set_pc_i64 s[30:31]
entry:
%alloca = alloca i16, i32 1, align 4, addrspace(5)
@@ -183,6 +281,22 @@ define void @spill_half() {
; GCN-FAKE16-NEXT: scratch_store_b16 off, v0, s32 dlc
; GCN-FAKE16-NEXT: s_waitcnt_vscnt null, 0x0
; GCN-FAKE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX1250-LABEL: spill_half:
+; GFX1250: ; %bb.0: ; %entry
+; GFX1250-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-NEXT: s_wait_kmcnt 0x0
+; GFX1250-NEXT: scratch_load_u16 v0, off, s32 scope:SCOPE_SYS
+; GFX1250-NEXT: s_wait_loadcnt 0x0
+; GFX1250-NEXT: scratch_store_b32 off, v0, s32 offset:4 ; 4-byte Folded Spill
+; GFX1250-NEXT: s_wait_xcnt 0x0
+; GFX1250-NEXT: ;;#ASMSTART
+; GFX1250-NEXT: ;;#ASMEND
+; GFX1250-NEXT: scratch_load_b32 v0, off, s32 offset:4 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-NEXT: s_wait_loadcnt 0x0
+; GFX1250-NEXT: scratch_store_b16 off, v0, s32 scope:SCOPE_SYS
+; GFX1250-NEXT: s_wait_storecnt 0x0
+; GFX1250-NEXT: s_set_pc_i64 s[30:31]
entry:
%alloca = alloca half, i32 1, align 4, addrspace(5)
@@ -226,6 +340,22 @@ define void @spill_i16_from_v2i16() {
; GCN-FAKE16-NEXT: scratch_store_b16 off, v0, s32 offset:2 dlc
; GCN-FAKE16-NEXT: s_waitcnt_vscnt null, 0x0
; GCN-FAKE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX1250-LABEL: spill_i16_from_v2i16:
+; GFX1250: ; %bb.0: ; %entry
+; GFX1250-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-NEXT: s_wait_kmcnt 0x0
+; GFX1250-NEXT: scratch_load_u16 v0, off, s32 offset:2 scope:SCOPE_SYS
+; GFX1250-NEXT: s_wait_loadcnt 0x0
+; GFX1250-NEXT: scratch_store_b32 off, v0, s32 offset:8 ; 4-byte Folded Spill
+; GFX1250-NEXT: s_wait_xcnt 0x0
+; GFX1250-NEXT: ;;#ASMSTART
+; GFX1250-NEXT: ;;#ASMEND
+; GFX1250-NEXT: scratch_load_b32 v0, off, s32 offset:8 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-NEXT: s_wait_loadcnt 0x0
+; GFX1250-NEXT: scratch_store_b16 off, v0, s32 offset:2 scope:SCOPE_SYS
+; GFX1250-NEXT: s_wait_storecnt 0x0
+; GFX1250-NEXT: s_set_pc_i64 s[30:31]
entry:
%alloca = alloca <2 x i16>, i32 2, align 1, addrspace(5)
@@ -283,6 +413,54 @@ define void @spill_2xi16_from_v2i16() {
; GCN-FAKE16-NEXT: scratch_store_b16 off, v0, s32 dlc
; GCN-FAKE16-NEXT: s_waitcnt_vscnt null, 0x0
; GCN-FAKE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX1250-TRUE16-LABEL: spill_2xi16_from_v2i16:
+; GFX1250-TRUE16: ; %bb.0: ; %entry
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-TRUE16-NEXT: s_wait_kmcnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_load_u16 v0, off, s32 offset:2 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: s_clause 0x1
+; GFX1250-TRUE16-NEXT: scratch_store_b32 off, v0, s32 offset:12
+; GFX1250-TRUE16-NEXT: scratch_load_u16 v0, off, s32 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_store_b32 off, v0, s32 offset:8 ; 4-byte Folded Spill
+; GFX1250-TRUE16-NEXT: s_wait_xcnt 0x0
+; GFX1250-TRUE16-NEXT: ;;#ASMSTART
+; GFX1250-TRUE16-NEXT: ;;#ASMEND
+; GFX1250-TRUE16-NEXT: scratch_load_b32 v0, off, s32 offset:12 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_store_b16 off, v0, s32 offset:2 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_load_b32 v0, off, s32 offset:8 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_store_b16 off, v0, s32 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-TRUE16-NEXT: s_set_pc_i64 s[30:31]
+;
+; GFX1250-FAKE16-LABEL: spill_2xi16_from_v2i16:
+; GFX1250-FAKE16: ; %bb.0: ; %entry
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-FAKE16-NEXT: s_wait_kmcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_load_u16 v0, off, s32 offset:2 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: s_clause 0x1
+; GFX1250-FAKE16-NEXT: scratch_store_b32 off, v0, s32 offset:8
+; GFX1250-FAKE16-NEXT: scratch_load_u16 v0, off, s32 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_store_b32 off, v0, s32 offset:12 ; 4-byte Folded Spill
+; GFX1250-FAKE16-NEXT: s_wait_xcnt 0x0
+; GFX1250-FAKE16-NEXT: ;;#ASMSTART
+; GFX1250-FAKE16-NEXT: ;;#ASMEND
+; GFX1250-FAKE16-NEXT: scratch_load_b32 v0, off, s32 offset:8 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_store_b16 off, v0, s32 offset:2 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_load_b32 v0, off, s32 offset:12 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_store_b16 off, v0, s32 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-FAKE16-NEXT: s_set_pc_i64 s[30:31]
entry:
%alloca = alloca <2 x i16>, i32 2, align 1, addrspace(5)
@@ -341,6 +519,47 @@ define void @spill_2xi16_from_v2i16_one_free_reg() {
; GCN-FAKE16-NEXT: scratch_store_b16 off, v0, s32 dlc
; GCN-FAKE16-NEXT: s_waitcnt_vscnt null, 0x0
; GCN-FAKE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX1250-TRUE16-LABEL: spill_2xi16_from_v2i16_one_free_reg:
+; GFX1250-TRUE16: ; %bb.0: ; %entry
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-TRUE16-NEXT: s_wait_kmcnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_load_u16 v7, off, s32 offset:2 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_load_u16 v0, off, s32 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_store_b32 off, v0, s32 offset:8 ; 4-byte Folded Spill
+; GFX1250-TRUE16-NEXT: s_wait_xcnt 0x0
+; GFX1250-TRUE16-NEXT: ;;#ASMSTART
+; GFX1250-TRUE16-NEXT: ;;#ASMEND
+; GFX1250-TRUE16-NEXT: v_mov_b16_e32 v0.l, v7.l
+; GFX1250-TRUE16-NEXT: scratch_store_b16 off, v0, s32 offset:2 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_load_b32 v0, off, s32 offset:8 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-TRUE16-NEXT: scratch_store_b16 off, v0, s32 scope:SCOPE_SYS
+; GFX1250-TRUE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-TRUE16-NEXT: s_set_pc_i64 s[30:31]
+;
+; GFX1250-FAKE16-LABEL: spill_2xi16_from_v2i16_one_free_reg:
+; GFX1250-FAKE16: ; %bb.0: ; %entry
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-FAKE16-NEXT: s_wait_kmcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_load_u16 v7, off, s32 offset:2 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_load_u16 v0, off, s32 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_store_b32 off, v0, s32 offset:8 ; 4-byte Folded Spill
+; GFX1250-FAKE16-NEXT: s_wait_xcnt 0x0
+; GFX1250-FAKE16-NEXT: ;;#ASMSTART
+; GFX1250-FAKE16-NEXT: ;;#ASMEND
+; GFX1250-FAKE16-NEXT: scratch_store_b16 off, v7, s32 offset:2 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_load_b32 v0, off, s32 offset:8 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1250-FAKE16-NEXT: scratch_store_b16 off, v0, s32 scope:SCOPE_SYS
+; GFX1250-FAKE16-NEXT: s_wait_storecnt 0x0
+; GFX1250-FAKE16-NEXT: s_set_pc_i64 s[30:31]
entry:
%alloca = alloca <2 x i16>, i32 2, align 1, addrspace(5)
@@ -375,6 +594,22 @@ define void @spill_v2i16() {
; GCN-NEXT: scratch_store_b32 off, v0, s32 offset:4 dlc
; GCN-NEXT: s_waitcnt_vscnt null, 0x0
; GCN-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX1250-LABEL: spill_v2i16:
+; GFX1250: ; %bb.0: ; %entry
+; GFX1250-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX1250-NEXT: s_wait_kmcnt 0x0
+; GFX1250-NEXT: scratch_load_b32 v0, off, s32 offset:4 scope:SCOPE_SYS
+; GFX1250-NEXT: s_wait_loadcnt 0x0
+; GFX1250-NEXT: scratch_store_b32 off, v0, s32 offset:8 ; 4-byte Folded Spill
+; GFX1250-NEXT: s_wait_xcnt 0x0
+; GFX1250-NEXT: ;;#ASMSTART
+; GFX1250-NEXT: ;;#ASMEND
+; GFX1250-NEXT: scratch_load_b32 v0, off, s32 offset:8 th:TH_LOAD_LU ; 4-byte Folded Reload
+; GFX1250-NEXT: s_wait_loadcnt 0x0
+; GFX1250-NEXT: scratch_store_b32 off, v0, s32 offset:4 scope:SCOPE_SYS
+; GFX1250-NEXT: s_wait_storecnt 0x0
+; GFX1250-NEXT: s_set_pc_i64 s[30:31]
entry:
%alloca = alloca <2 x i16>, i32 2, align 1, addrspace(5)
generated by cgit v1.1 at 2025-11-01 17:04:32 +0000