Page MenuHomePhabricator
Differential D134953 Diff 464265 llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-ext-mul.ll

Changeset View

Standalone View

View Options

llvm/test/CodeGen/AMDGPU/GlobalISel/combine-fma-add-ext-mul.ll

Show First 20 Lines • Show All 44 Lines • ▼ Show 20 Lines.entry:
%b = fpext half %a to float %b = fpext half %a to float
%c = fadd fast float %z, %b %c = fadd fast float %z, %b
ret float %c ret float %c
} }
define amdgpu_vs <5 x float> @test_5xf16_5xf32_add_ext_mul(<5 x half> inreg %x, <5 x half> inreg %y, <5 x float> inreg %z) { define amdgpu_vs <5 x float> @test_5xf16_5xf32_add_ext_mul(<5 x half> inreg %x, <5 x half> inreg %y, <5 x float> inreg %z) {
; GFX9-FAST-DENORM-LABEL: test_5xf16_5xf32_add_ext_mul: ; GFX9-FAST-DENORM-LABEL: test_5xf16_5xf32_add_ext_mul:
; GFX9-FAST-DENORM: ; %bb.0: ; %.entry ; GFX9-FAST-DENORM: ; %bb.0: ; %.entry
; GFX9-FAST-DENORM-NEXT: s_pack_lh_b32_b16 s3, s3, s3
; GFX9-FAST-DENORM-NEXT: s_pack_lh_b32_b16 s4, s4, s4
; GFX9-FAST-DENORM-NEXT: s_pack_lh_b32_b16 s0, s0, s0
; GFX9-FAST-DENORM-NEXT: s_pack_lh_b32_b16 s1, s1, s1
; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v0, s3 ; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v0, s3
; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v1, s4 ; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v1, s4
; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v2, s5 ; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v2, s5
; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v0, s0, v0 ; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v0, s0, v0
; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v1, s1, v1 ; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v1, s1, v1
; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v2, s2, v2 ; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v2, s2, v2
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v3, v0 ; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v3, v0
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_sdwa v4, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 ; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_sdwa v4, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
▲ Show 20 Lines • Show All 95 Lines • Show Last 20 Lines