[llvm] 47f2904 - [AMDGPU] Fix a GlobalISel RUN line
Jay Foad via llvm-commits
llvm-commits at lists.llvm.org
Mon Nov 13 03:30:31 PST 2023
Author: Jay Foad
Date: 2023-11-13T11:30:15Z
New Revision: 47f29043f07e255e2372d3ed5a25df1c44c59370
URL: https://github.com/llvm/llvm-project/commit/47f29043f07e255e2372d3ed5a25df1c44c59370
DIFF: https://github.com/llvm/llvm-project/commit/47f29043f07e255e2372d3ed5a25df1c44c59370.diff
LOG: [AMDGPU] Fix a GlobalISel RUN line
This was added in D149795 without actually enabling GlobalISel.
Added:
Modified:
llvm/test/CodeGen/AMDGPU/GlobalISel/fp64-atomics-gfx90a.ll
Removed:
################################################################################
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/fp64-atomics-gfx90a.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/fp64-atomics-gfx90a.ll
index c6ea046f95a9199..3367949bc112da6 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/fp64-atomics-gfx90a.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/fp64-atomics-gfx90a.ll
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx90a -verify-machineinstrs < %s | FileCheck %s -check-prefix=GFX90A
-; RUN: llc < %s -march=amdgcn -mcpu=gfx940 -verify-machineinstrs | FileCheck %s -check-prefix=GFX940
+; RUN: llc -global-isel -march=amdgcn -mcpu=gfx940 -verify-machineinstrs < %s | FileCheck %s -check-prefix=GFX940
declare double @llvm.amdgcn.struct.buffer.atomic.fadd.f64(double, <4 x i32>, i32, i32, i32, i32 immarg)
declare double @llvm.amdgcn.struct.ptr.buffer.atomic.fadd.f64(double, ptr addrspace(8), i32, i32, i32, i32 immarg)
@@ -1033,8 +1033,7 @@ define amdgpu_kernel void @global_atomic_fadd_f64_noret(ptr addrspace(1) %ptr, d
; GFX940-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v0, s2
-; GFX940-NEXT: v_mov_b32_e32 v1, s3
+; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
; GFX940-NEXT: global_atomic_add_f64 v2, v[0:1], s[0:1]
; GFX940-NEXT: s_endpgm
main_body:
@@ -1057,8 +1056,7 @@ define amdgpu_kernel void @global_atomic_fmin_f64_noret(ptr addrspace(1) %ptr, d
; GFX940-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v0, s2
-; GFX940-NEXT: v_mov_b32_e32 v1, s3
+; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
; GFX940-NEXT: global_atomic_min_f64 v2, v[0:1], s[0:1]
; GFX940-NEXT: s_endpgm
main_body:
@@ -1081,8 +1079,7 @@ define amdgpu_kernel void @global_atomic_fmax_f64_noret(ptr addrspace(1) %ptr, d
; GFX940-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v0, s2
-; GFX940-NEXT: v_mov_b32_e32 v1, s3
+; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
; GFX940-NEXT: global_atomic_max_f64 v2, v[0:1], s[0:1]
; GFX940-NEXT: s_endpgm
main_body:
@@ -1120,8 +1117,8 @@ define amdgpu_kernel void @global_atomic_fadd_f64_noret_pat(ptr addrspace(1) %pt
; GFX940-LABEL: global_atomic_fadd_f64_noret_pat:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
-; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: v_mov_b64_e32 v[0:1], 4.0
+; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: global_atomic_add_f64 v2, v[0:1], s[0:1] sc1
@@ -1149,8 +1146,8 @@ define amdgpu_kernel void @global_atomic_fadd_f64_noret_pat_agent(ptr addrspace(
; GFX940-LABEL: global_atomic_fadd_f64_noret_pat_agent:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
-; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: v_mov_b64_e32 v[0:1], 4.0
+; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: global_atomic_add_f64 v2, v[0:1], s[0:1]
@@ -1192,8 +1189,8 @@ define amdgpu_kernel void @global_atomic_fadd_f64_noret_pat_system(ptr addrspace
; GFX940-LABEL: global_atomic_fadd_f64_noret_pat_system:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
-; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: v_mov_b64_e32 v[0:1], 4.0
+; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: global_atomic_add_f64 v2, v[0:1], s[0:1] sc1
@@ -1221,8 +1218,8 @@ define amdgpu_kernel void @global_atomic_fadd_f64_noret_pat_flush(ptr addrspace(
; GFX940-LABEL: global_atomic_fadd_f64_noret_pat_flush:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
-; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: v_mov_b64_e32 v[0:1], 4.0
+; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: global_atomic_add_f64 v2, v[0:1], s[0:1]
@@ -1430,8 +1427,8 @@ define amdgpu_kernel void @global_atomic_fadd_f64_noret_pat_agent_safe(ptr addrs
; GFX940-LABEL: global_atomic_fadd_f64_noret_pat_agent_safe:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
-; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: v_mov_b64_e32 v[0:1], 4.0
+; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: global_atomic_add_f64 v2, v[0:1], s[0:1]
@@ -1473,12 +1470,12 @@ define amdgpu_kernel void @flat_atomic_fadd_f64_noret_pat(ptr %ptr) #1 {
; GFX940-LABEL: flat_atomic_fadd_f64_noret_pat:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
-; GFX940-NEXT: v_mov_b64_e32 v[0:1], 4.0
+; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: v_mov_b64_e32 v[2:3], s[0:1]
+; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
-; GFX940-NEXT: flat_atomic_add_f64 v[2:3], v[0:1] sc1
+; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[2:3] sc1
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: buffer_inv sc0 sc1
; GFX940-NEXT: s_endpgm
@@ -1504,12 +1501,12 @@ define amdgpu_kernel void @flat_atomic_fadd_f64_noret_pat_agent(ptr %ptr) #1 {
; GFX940-LABEL: flat_atomic_fadd_f64_noret_pat_agent:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
-; GFX940-NEXT: v_mov_b64_e32 v[0:1], 4.0
+; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: v_mov_b64_e32 v[2:3], s[0:1]
+; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
-; GFX940-NEXT: flat_atomic_add_f64 v[2:3], v[0:1]
+; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[2:3]
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: buffer_inv sc1
; GFX940-NEXT: s_endpgm
@@ -1549,12 +1546,12 @@ define amdgpu_kernel void @flat_atomic_fadd_f64_noret_pat_system(ptr %ptr) #1 {
; GFX940-LABEL: flat_atomic_fadd_f64_noret_pat_system:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
-; GFX940-NEXT: v_mov_b64_e32 v[0:1], 4.0
+; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: v_mov_b64_e32 v[2:3], s[0:1]
+; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0)
-; GFX940-NEXT: flat_atomic_add_f64 v[2:3], v[0:1] sc1
+; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[2:3] sc1
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: buffer_inv sc0 sc1
; GFX940-NEXT: s_endpgm
@@ -1690,10 +1687,8 @@ define amdgpu_kernel void @flat_atomic_fadd_f64_noret(ptr %ptr, double %data) {
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v0, s0
-; GFX940-NEXT: v_mov_b32_e32 v1, s1
-; GFX940-NEXT: v_mov_b32_e32 v2, s2
-; GFX940-NEXT: v_mov_b32_e32 v3, s3
+; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
+; GFX940-NEXT: v_mov_b64_e32 v[2:3], s[2:3]
; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[2:3]
; GFX940-NEXT: s_endpgm
main_body:
@@ -1748,12 +1743,12 @@ define amdgpu_kernel void @flat_atomic_fadd_f64_noret_pat_agent_safe(ptr %ptr) {
; GFX940-LABEL: flat_atomic_fadd_f64_noret_pat_agent_safe:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
-; GFX940-NEXT: v_mov_b64_e32 v[0:1], 4.0
+; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: v_mov_b64_e32 v[2:3], s[0:1]
+; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
-; GFX940-NEXT: flat_atomic_add_f64 v[2:3], v[0:1]
+; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[2:3]
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: buffer_inv sc1
; GFX940-NEXT: s_endpgm
@@ -1776,10 +1771,8 @@ define amdgpu_kernel void @flat_atomic_fmin_f64_noret(ptr %ptr, double %data) {
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v0, s0
-; GFX940-NEXT: v_mov_b32_e32 v1, s1
-; GFX940-NEXT: v_mov_b32_e32 v2, s2
-; GFX940-NEXT: v_mov_b32_e32 v3, s3
+; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
+; GFX940-NEXT: v_mov_b64_e32 v[2:3], s[2:3]
; GFX940-NEXT: flat_atomic_min_f64 v[0:1], v[2:3]
; GFX940-NEXT: s_endpgm
main_body:
@@ -1820,10 +1813,8 @@ define amdgpu_kernel void @flat_atomic_fmax_f64_noret(ptr %ptr, double %data) {
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v0, s0
-; GFX940-NEXT: v_mov_b32_e32 v1, s1
-; GFX940-NEXT: v_mov_b32_e32 v2, s2
-; GFX940-NEXT: v_mov_b32_e32 v3, s3
+; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
+; GFX940-NEXT: v_mov_b64_e32 v[2:3], s[2:3]
; GFX940-NEXT: flat_atomic_max_f64 v[0:1], v[2:3]
; GFX940-NEXT: s_endpgm
main_body:
@@ -1888,9 +1879,9 @@ define double @local_atomic_fadd_f64_rtn(ptr addrspace(3) %ptr, double %data) {
; GFX940-LABEL: local_atomic_fadd_f64_rtn:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v3, v2
-; GFX940-NEXT: v_mov_b32_e32 v2, v1
-; GFX940-NEXT: ds_add_rtn_f64 v[0:1], v0, v[2:3]
+; GFX940-NEXT: v_mov_b32_e32 v4, v1
+; GFX940-NEXT: v_mov_b32_e32 v5, v2
+; GFX940-NEXT: ds_add_rtn_f64 v[0:1], v0, v[4:5]
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
@@ -2042,9 +2033,9 @@ define double @local_atomic_fadd_f64_rtn_ieee_unsafe(ptr addrspace(3) %ptr, doub
; GFX940-LABEL: local_atomic_fadd_f64_rtn_ieee_unsafe:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v3, v2
-; GFX940-NEXT: v_mov_b32_e32 v2, v1
-; GFX940-NEXT: ds_add_rtn_f64 v[0:1], v0, v[2:3]
+; GFX940-NEXT: v_mov_b32_e32 v4, v1
+; GFX940-NEXT: v_mov_b32_e32 v5, v2
+; GFX940-NEXT: ds_add_rtn_f64 v[0:1], v0, v[4:5]
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
@@ -2065,9 +2056,9 @@ define double @local_atomic_fadd_f64_rtn_ieee_safe(ptr addrspace(3) %ptr, double
; GFX940-LABEL: local_atomic_fadd_f64_rtn_ieee_safe:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v3, v2
-; GFX940-NEXT: v_mov_b32_e32 v2, v1
-; GFX940-NEXT: ds_add_rtn_f64 v[0:1], v0, v[2:3]
+; GFX940-NEXT: v_mov_b32_e32 v4, v1
+; GFX940-NEXT: v_mov_b32_e32 v5, v2
+; GFX940-NEXT: ds_add_rtn_f64 v[0:1], v0, v[4:5]
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
More information about the llvm-commits
mailing list