diff options
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/llvm.minimum.f64.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/llvm.minimum.f64.ll | 98 |
1 files changed, 48 insertions, 50 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.minimum.f64.ll b/llvm/test/CodeGen/AMDGPU/llvm.minimum.f64.ll index 37fe2e958e62..d8462ec22024 100644 --- a/llvm/test/CodeGen/AMDGPU/llvm.minimum.f64.ll +++ b/llvm/test/CodeGen/AMDGPU/llvm.minimum.f64.ll @@ -2868,74 +2868,72 @@ define <16 x double> @v_minimum_v16f64(<16 x double> %src0, <16 x double> %src1) ; GFX12-NEXT: s_wait_samplecnt 0x0 ; GFX12-NEXT: s_wait_bvhcnt 0x0 ; GFX12-NEXT: s_wait_kmcnt 0x0 -; GFX12-NEXT: s_clause 0x1b +; GFX12-NEXT: s_clause 0x1f +; GFX12-NEXT: scratch_load_b32 v31, off, s32 ; GFX12-NEXT: scratch_load_b32 v33, off, s32 offset:8 ; GFX12-NEXT: scratch_load_b32 v32, off, s32 offset:4 ; GFX12-NEXT: scratch_load_b32 v35, off, s32 offset:16 ; GFX12-NEXT: scratch_load_b32 v34, off, s32 offset:12 -; GFX12-NEXT: scratch_load_b32 v31, off, s32 -; GFX12-NEXT: scratch_load_b32 v37, off, s32 offset:120 -; GFX12-NEXT: scratch_load_b32 v39, off, s32 offset:104 -; GFX12-NEXT: scratch_load_b32 v49, off, s32 offset:24 -; GFX12-NEXT: scratch_load_b32 v48, off, s32 offset:20 -; GFX12-NEXT: scratch_load_b32 v51, off, s32 offset:32 -; GFX12-NEXT: scratch_load_b32 v50, off, s32 offset:28 -; GFX12-NEXT: scratch_load_b32 v53, off, s32 offset:40 -; GFX12-NEXT: scratch_load_b32 v52, off, s32 offset:36 -; GFX12-NEXT: scratch_load_b32 v55, off, s32 offset:48 -; GFX12-NEXT: scratch_load_b32 v54, off, s32 offset:44 -; GFX12-NEXT: scratch_load_b32 v65, off, s32 offset:56 -; GFX12-NEXT: scratch_load_b32 v64, off, s32 offset:52 -; GFX12-NEXT: scratch_load_b32 v67, off, s32 offset:64 -; GFX12-NEXT: scratch_load_b32 v66, off, s32 offset:60 -; GFX12-NEXT: scratch_load_b32 v69, off, s32 offset:72 -; GFX12-NEXT: scratch_load_b32 v68, off, s32 offset:68 -; GFX12-NEXT: scratch_load_b32 v71, off, s32 offset:80 -; GFX12-NEXT: scratch_load_b32 v70, off, s32 offset:76 -; GFX12-NEXT: scratch_load_b32 v81, off, s32 offset:88 -; GFX12-NEXT: scratch_load_b32 v80, off, s32 offset:84 -; GFX12-NEXT: scratch_load_b32 v83, off, s32 offset:96 -; GFX12-NEXT: scratch_load_b32 v82, off, s32 offset:92 -; GFX12-NEXT: scratch_load_b32 v38, off, s32 offset:100 -; GFX12-NEXT: s_wait_loadcnt 0x1a +; GFX12-NEXT: scratch_load_b32 v37, off, s32 offset:24 +; GFX12-NEXT: scratch_load_b32 v36, off, s32 offset:20 +; GFX12-NEXT: scratch_load_b32 v39, off, s32 offset:32 +; GFX12-NEXT: scratch_load_b32 v38, off, s32 offset:28 +; GFX12-NEXT: scratch_load_b32 v49, off, s32 offset:40 +; GFX12-NEXT: scratch_load_b32 v48, off, s32 offset:36 +; GFX12-NEXT: scratch_load_b32 v51, off, s32 offset:48 +; GFX12-NEXT: scratch_load_b32 v50, off, s32 offset:44 +; GFX12-NEXT: scratch_load_b32 v53, off, s32 offset:56 +; GFX12-NEXT: scratch_load_b32 v52, off, s32 offset:52 +; GFX12-NEXT: scratch_load_b32 v55, off, s32 offset:64 +; GFX12-NEXT: scratch_load_b32 v54, off, s32 offset:60 +; GFX12-NEXT: scratch_load_b32 v65, off, s32 offset:72 +; GFX12-NEXT: scratch_load_b32 v64, off, s32 offset:68 +; GFX12-NEXT: scratch_load_b32 v67, off, s32 offset:80 +; GFX12-NEXT: scratch_load_b32 v66, off, s32 offset:76 +; GFX12-NEXT: scratch_load_b32 v69, off, s32 offset:88 +; GFX12-NEXT: scratch_load_b32 v68, off, s32 offset:84 +; GFX12-NEXT: scratch_load_b32 v71, off, s32 offset:96 +; GFX12-NEXT: scratch_load_b32 v70, off, s32 offset:92 +; GFX12-NEXT: scratch_load_b32 v81, off, s32 offset:104 +; GFX12-NEXT: scratch_load_b32 v80, off, s32 offset:100 +; GFX12-NEXT: scratch_load_b32 v83, off, s32 offset:112 +; GFX12-NEXT: scratch_load_b32 v82, off, s32 offset:108 +; GFX12-NEXT: scratch_load_b32 v85, off, s32 offset:120 +; GFX12-NEXT: scratch_load_b32 v84, off, s32 offset:116 +; GFX12-NEXT: scratch_load_b32 v87, off, s32 offset:128 +; GFX12-NEXT: scratch_load_b32 v86, off, s32 offset:124 +; GFX12-NEXT: s_wait_loadcnt 0x1e ; GFX12-NEXT: v_minimum_f64 v[0:1], v[0:1], v[32:33] -; GFX12-NEXT: s_clause 0x2 -; GFX12-NEXT: scratch_load_b32 v33, off, s32 offset:112 -; GFX12-NEXT: scratch_load_b32 v32, off, s32 offset:108 -; GFX12-NEXT: scratch_load_b32 v36, off, s32 offset:116 -; GFX12-NEXT: s_wait_loadcnt 0x1b +; GFX12-NEXT: s_wait_loadcnt 0x1c ; GFX12-NEXT: v_minimum_f64 v[2:3], v[2:3], v[34:35] -; GFX12-NEXT: s_clause 0x1 -; GFX12-NEXT: scratch_load_b32 v35, off, s32 offset:128 -; GFX12-NEXT: scratch_load_b32 v34, off, s32 offset:124 +; GFX12-NEXT: s_wait_loadcnt 0x1a +; GFX12-NEXT: v_minimum_f64 v[4:5], v[4:5], v[36:37] ; GFX12-NEXT: s_wait_loadcnt 0x18 -; GFX12-NEXT: v_minimum_f64 v[4:5], v[4:5], v[48:49] +; GFX12-NEXT: v_minimum_f64 v[6:7], v[6:7], v[38:39] ; GFX12-NEXT: s_wait_loadcnt 0x16 -; GFX12-NEXT: v_minimum_f64 v[6:7], v[6:7], v[50:51] +; GFX12-NEXT: v_minimum_f64 v[8:9], v[8:9], v[48:49] ; GFX12-NEXT: s_wait_loadcnt 0x14 -; GFX12-NEXT: v_minimum_f64 v[8:9], v[8:9], v[52:53] +; GFX12-NEXT: v_minimum_f64 v[10:11], v[10:11], v[50:51] ; GFX12-NEXT: s_wait_loadcnt 0x12 -; GFX12-NEXT: v_minimum_f64 v[10:11], v[10:11], v[54:55] +; GFX12-NEXT: v_minimum_f64 v[12:13], v[12:13], v[52:53] ; GFX12-NEXT: s_wait_loadcnt 0x10 -; GFX12-NEXT: v_minimum_f64 v[12:13], v[12:13], v[64:65] +; GFX12-NEXT: v_minimum_f64 v[14:15], v[14:15], v[54:55] ; GFX12-NEXT: s_wait_loadcnt 0xe -; GFX12-NEXT: v_minimum_f64 v[14:15], v[14:15], v[66:67] +; GFX12-NEXT: v_minimum_f64 v[16:17], v[16:17], v[64:65] ; GFX12-NEXT: s_wait_loadcnt 0xc -; GFX12-NEXT: v_minimum_f64 v[16:17], v[16:17], v[68:69] +; GFX12-NEXT: v_minimum_f64 v[18:19], v[18:19], v[66:67] ; GFX12-NEXT: s_wait_loadcnt 0xa -; GFX12-NEXT: v_minimum_f64 v[18:19], v[18:19], v[70:71] +; GFX12-NEXT: v_minimum_f64 v[20:21], v[20:21], v[68:69] ; GFX12-NEXT: s_wait_loadcnt 0x8 -; GFX12-NEXT: v_minimum_f64 v[20:21], v[20:21], v[80:81] +; GFX12-NEXT: v_minimum_f64 v[22:23], v[22:23], v[70:71] ; GFX12-NEXT: s_wait_loadcnt 0x6 -; GFX12-NEXT: v_minimum_f64 v[22:23], v[22:23], v[82:83] -; GFX12-NEXT: s_wait_loadcnt 0x5 -; GFX12-NEXT: v_minimum_f64 v[24:25], v[24:25], v[38:39] -; GFX12-NEXT: s_wait_loadcnt 0x3 -; GFX12-NEXT: v_minimum_f64 v[26:27], v[26:27], v[32:33] +; GFX12-NEXT: v_minimum_f64 v[24:25], v[24:25], v[80:81] +; GFX12-NEXT: s_wait_loadcnt 0x4 +; GFX12-NEXT: v_minimum_f64 v[26:27], v[26:27], v[82:83] ; GFX12-NEXT: s_wait_loadcnt 0x2 -; GFX12-NEXT: v_minimum_f64 v[28:29], v[28:29], v[36:37] +; GFX12-NEXT: v_minimum_f64 v[28:29], v[28:29], v[84:85] ; GFX12-NEXT: s_wait_loadcnt 0x0 -; GFX12-NEXT: v_minimum_f64 v[30:31], v[30:31], v[34:35] +; GFX12-NEXT: v_minimum_f64 v[30:31], v[30:31], v[86:87] ; GFX12-NEXT: s_setpc_b64 s[30:31] %op = call <16 x double> @llvm.minimum.v16f64(<16 x double> %src0, <16 x double> %src1) ret <16 x double> %op |
