diff options
| author | Mingming Liu <mingmingl@google.com> | 2025-09-10 15:25:31 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-09-10 15:25:31 -0700 |
| commit | 1417dafa1db9cb1b2b09438aa9f53ea5ab6e36e2 (patch) | |
| tree | 57f4b1f313c8cf74eed8819870f39c36ea263c68 /llvm/test/CodeGen/AMDGPU/bf16-conversions.ll | |
| parent | 898b813bc8a6d0276bf0f4769f5f2f64b34e632d (diff) | |
| parent | b8cefcb601ddaa18482555c4ff363c01a270c2fe (diff) | |
Merge branch 'main' into users/mingmingl-llvm/samplefdo-profile-formatusers/mingmingl-llvm/samplefdo-profile-format
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/bf16-conversions.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/bf16-conversions.ll | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/bf16-conversions.ll b/llvm/test/CodeGen/AMDGPU/bf16-conversions.ll index 02ead572145f..752a87ac3cb7 100644 --- a/llvm/test/CodeGen/AMDGPU/bf16-conversions.ll +++ b/llvm/test/CodeGen/AMDGPU/bf16-conversions.ll @@ -344,7 +344,7 @@ define amdgpu_ps void @fptrunc_f32_to_bf16(float %a, ptr %out) { ; GFX1250: ; %bb.0: ; %entry ; GFX1250-NEXT: v_dual_mov_b32 v3, v2 :: v_dual_mov_b32 v2, v1 ; GFX1250-NEXT: v_cvt_pk_bf16_f32 v0, v0, s0 -; GFX1250-NEXT: flat_store_b16 v[2:3], v0 scope:SCOPE_SE +; GFX1250-NEXT: flat_store_b16 v[2:3], v0 ; GFX1250-NEXT: s_endpgm entry: %a.cvt = fptrunc float %a to bfloat @@ -380,7 +380,7 @@ define amdgpu_ps void @fptrunc_f32_to_bf16_abs(float %a, ptr %out) { ; GFX1250: ; %bb.0: ; %entry ; GFX1250-NEXT: v_dual_mov_b32 v3, v2 :: v_dual_mov_b32 v2, v1 ; GFX1250-NEXT: v_cvt_pk_bf16_f32 v0, |v0|, s0 -; GFX1250-NEXT: flat_store_b16 v[2:3], v0 scope:SCOPE_SE +; GFX1250-NEXT: flat_store_b16 v[2:3], v0 ; GFX1250-NEXT: s_endpgm entry: %a.abs = call float @llvm.fabs.f32(float %a) @@ -417,7 +417,7 @@ define amdgpu_ps void @fptrunc_f32_to_bf16_neg(float %a, ptr %out) { ; GFX1250: ; %bb.0: ; %entry ; GFX1250-NEXT: v_dual_mov_b32 v3, v2 :: v_dual_mov_b32 v2, v1 ; GFX1250-NEXT: v_cvt_pk_bf16_f32 v0, -v0, s0 -; GFX1250-NEXT: flat_store_b16 v[2:3], v0 scope:SCOPE_SE +; GFX1250-NEXT: flat_store_b16 v[2:3], v0 ; GFX1250-NEXT: s_endpgm entry: %a.neg = fneg float %a @@ -480,7 +480,7 @@ define amdgpu_ps void @fptrunc_f64_to_bf16(double %a, ptr %out) { ; GFX1250-NEXT: s_or_b32 vcc_lo, vcc_lo, s0 ; GFX1250-NEXT: v_cndmask_b32_e32 v0, v0, v6, vcc_lo ; GFX1250-NEXT: v_cvt_pk_bf16_f32 v0, v0, s0 -; GFX1250-NEXT: flat_store_b16 v[2:3], v0 scope:SCOPE_SE +; GFX1250-NEXT: flat_store_b16 v[2:3], v0 ; GFX1250-NEXT: s_endpgm entry: %a.cvt = fptrunc double %a to bfloat @@ -543,7 +543,7 @@ define amdgpu_ps void @fptrunc_f64_to_bf16_neg(double %a, ptr %out) { ; GFX1250-NEXT: v_cndmask_b32_e32 v0, v0, v6, vcc_lo ; GFX1250-NEXT: s_delay_alu instid0(VALU_DEP_1) ; GFX1250-NEXT: v_cvt_pk_bf16_f32 v0, v0, s0 -; GFX1250-NEXT: flat_store_b16 v[2:3], v0 scope:SCOPE_SE +; GFX1250-NEXT: flat_store_b16 v[2:3], v0 ; GFX1250-NEXT: s_endpgm entry: %a.neg = fneg double %a @@ -607,7 +607,7 @@ define amdgpu_ps void @fptrunc_f64_to_bf16_abs(double %a, ptr %out) { ; GFX1250-NEXT: v_cndmask_b32_e32 v0, v0, v6, vcc_lo ; GFX1250-NEXT: s_delay_alu instid0(VALU_DEP_1) ; GFX1250-NEXT: v_cvt_pk_bf16_f32 v0, v0, s0 -; GFX1250-NEXT: flat_store_b16 v[2:3], v0 scope:SCOPE_SE +; GFX1250-NEXT: flat_store_b16 v[2:3], v0 ; GFX1250-NEXT: s_endpgm entry: %a.abs = call double @llvm.fabs.f64(double %a) |