llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-backend-amdgpu Author: Matt Arsenault (arsenm) <details> <summary>Changes</summary> With the IEEE bit disabled, the hardware instructions have the same behavior as these operations. --- Patch is 37.84 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/139145.diff 2 Files Affected: - (modified) llvm/test/CodeGen/AMDGPU/maximumnum.ll (+483) - (modified) llvm/test/CodeGen/AMDGPU/minimumnum.ll (+483) ``````````diff diff --git a/llvm/test/CodeGen/AMDGPU/maximumnum.ll b/llvm/test/CodeGen/AMDGPU/maximumnum.ll index df79534a0844e..f3ed13a737748 100644 --- a/llvm/test/CodeGen/AMDGPU/maximumnum.ll +++ b/llvm/test/CodeGen/AMDGPU/maximumnum.ll @@ -4202,3 +4202,486 @@ define <4 x double> @v_maximumnum_v4f64_nnan(<4 x double> %x, <4 x double> %y) { %result = call nnan <4 x double> @llvm.maximumnum.v4f64(<4 x double> %x, <4 x double> %y) ret <4 x double> %result } + +define half @v_maximumnum_f16_no_ieee(half %x, half %y) #0 { +; GFX7-LABEL: v_maximumnum_f16_no_ieee: +; GFX7: ; %bb.0: +; GFX7-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX7-NEXT: v_cvt_f16_f32_e32 v0, v0 +; GFX7-NEXT: v_cvt_f16_f32_e32 v1, v1 +; GFX7-NEXT: v_cvt_f32_f16_e32 v0, v0 +; GFX7-NEXT: v_cvt_f32_f16_e32 v1, v1 +; GFX7-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX7-NEXT: s_setpc_b64 s[30:31] +; +; GFX8-LABEL: v_maximumnum_f16_no_ieee: +; GFX8: ; %bb.0: +; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX8-NEXT: v_max_f16_e32 v1, v1, v1 +; GFX8-NEXT: v_max_f16_e32 v0, v0, v0 +; GFX8-NEXT: v_max_f16_e32 v0, v0, v1 +; GFX8-NEXT: s_setpc_b64 s[30:31] +; +; GFX9-LABEL: v_maximumnum_f16_no_ieee: +; GFX9: ; %bb.0: +; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX9-NEXT: v_max_f16_e32 v1, v1, v1 +; GFX9-NEXT: v_max_f16_e32 v0, v0, v0 +; GFX9-NEXT: v_max_f16_e32 v0, v0, v1 +; GFX9-NEXT: s_setpc_b64 s[30:31] +; +; GFX10-LABEL: v_maximumnum_f16_no_ieee: +; GFX10: ; %bb.0: +; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX10-NEXT: v_max_f16_e32 v1, v1, v1 +; GFX10-NEXT: v_max_f16_e32 v0, v0, v0 +; GFX10-NEXT: v_max_f16_e32 v0, v0, v1 +; GFX10-NEXT: s_setpc_b64 s[30:31] +; +; GFX11-TRUE16-LABEL: v_maximumnum_f16_no_ieee: +; GFX11-TRUE16: ; %bb.0: +; GFX11-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX11-TRUE16-NEXT: v_max_f16_e32 v0.h, v1.l, v1.l +; GFX11-TRUE16-NEXT: v_max_f16_e32 v0.l, v0.l, v0.l +; GFX11-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX11-TRUE16-NEXT: v_max_f16_e32 v0.l, v0.l, v0.h +; GFX11-TRUE16-NEXT: s_setpc_b64 s[30:31] +; +; GFX11-FAKE16-LABEL: v_maximumnum_f16_no_ieee: +; GFX11-FAKE16: ; %bb.0: +; GFX11-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX11-FAKE16-NEXT: v_max_f16_e32 v1, v1, v1 +; GFX11-FAKE16-NEXT: v_max_f16_e32 v0, v0, v0 +; GFX11-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX11-FAKE16-NEXT: v_max_f16_e32 v0, v0, v1 +; GFX11-FAKE16-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-TRUE16-LABEL: v_maximumnum_f16_no_ieee: +; GFX12-TRUE16: ; %bb.0: +; GFX12-TRUE16-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-TRUE16-NEXT: s_wait_expcnt 0x0 +; GFX12-TRUE16-NEXT: s_wait_samplecnt 0x0 +; GFX12-TRUE16-NEXT: s_wait_bvhcnt 0x0 +; GFX12-TRUE16-NEXT: s_wait_kmcnt 0x0 +; GFX12-TRUE16-NEXT: v_max_num_f16_e32 v0.h, v1.l, v1.l +; GFX12-TRUE16-NEXT: v_max_num_f16_e32 v0.l, v0.l, v0.l +; GFX12-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX12-TRUE16-NEXT: v_max_num_f16_e32 v0.l, v0.l, v0.h +; GFX12-TRUE16-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-FAKE16-LABEL: v_maximumnum_f16_no_ieee: +; GFX12-FAKE16: ; %bb.0: +; GFX12-FAKE16-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-FAKE16-NEXT: s_wait_expcnt 0x0 +; GFX12-FAKE16-NEXT: s_wait_samplecnt 0x0 +; GFX12-FAKE16-NEXT: s_wait_bvhcnt 0x0 +; GFX12-FAKE16-NEXT: s_wait_kmcnt 0x0 +; GFX12-FAKE16-NEXT: v_max_num_f16_e32 v1, v1, v1 +; GFX12-FAKE16-NEXT: v_max_num_f16_e32 v0, v0, v0 +; GFX12-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX12-FAKE16-NEXT: v_max_num_f16_e32 v0, v0, v1 +; GFX12-FAKE16-NEXT: s_setpc_b64 s[30:31] + %result = call half @llvm.maximumnum.f16(half %x, half %y) + ret half %result +} + +define half @v_maximumnum_f16_nan_no_ieee(half %x, half %y) #0 { +; GFX7-LABEL: v_maximumnum_f16_nan_no_ieee: +; GFX7: ; %bb.0: +; GFX7-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX7-NEXT: v_cvt_f16_f32_e32 v1, v1 +; GFX7-NEXT: v_cvt_f16_f32_e32 v0, v0 +; GFX7-NEXT: v_cvt_f32_f16_e32 v1, v1 +; GFX7-NEXT: v_cvt_f32_f16_e32 v0, v0 +; GFX7-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX7-NEXT: s_setpc_b64 s[30:31] +; +; GFX8-LABEL: v_maximumnum_f16_nan_no_ieee: +; GFX8: ; %bb.0: +; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX8-NEXT: v_max_f16_e32 v0, v0, v1 +; GFX8-NEXT: s_setpc_b64 s[30:31] +; +; GFX9-LABEL: v_maximumnum_f16_nan_no_ieee: +; GFX9: ; %bb.0: +; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX9-NEXT: v_max_f16_e32 v0, v0, v1 +; GFX9-NEXT: s_setpc_b64 s[30:31] +; +; GFX10-LABEL: v_maximumnum_f16_nan_no_ieee: +; GFX10: ; %bb.0: +; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX10-NEXT: v_max_f16_e32 v0, v0, v1 +; GFX10-NEXT: s_setpc_b64 s[30:31] +; +; GFX11-TRUE16-LABEL: v_maximumnum_f16_nan_no_ieee: +; GFX11-TRUE16: ; %bb.0: +; GFX11-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX11-TRUE16-NEXT: v_max_f16_e32 v0.l, v0.l, v1.l +; GFX11-TRUE16-NEXT: s_setpc_b64 s[30:31] +; +; GFX11-FAKE16-LABEL: v_maximumnum_f16_nan_no_ieee: +; GFX11-FAKE16: ; %bb.0: +; GFX11-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX11-FAKE16-NEXT: v_max_f16_e32 v0, v0, v1 +; GFX11-FAKE16-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-TRUE16-LABEL: v_maximumnum_f16_nan_no_ieee: +; GFX12-TRUE16: ; %bb.0: +; GFX12-TRUE16-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-TRUE16-NEXT: s_wait_expcnt 0x0 +; GFX12-TRUE16-NEXT: s_wait_samplecnt 0x0 +; GFX12-TRUE16-NEXT: s_wait_bvhcnt 0x0 +; GFX12-TRUE16-NEXT: s_wait_kmcnt 0x0 +; GFX12-TRUE16-NEXT: v_max_num_f16_e32 v0.l, v0.l, v1.l +; GFX12-TRUE16-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-FAKE16-LABEL: v_maximumnum_f16_nan_no_ieee: +; GFX12-FAKE16: ; %bb.0: +; GFX12-FAKE16-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-FAKE16-NEXT: s_wait_expcnt 0x0 +; GFX12-FAKE16-NEXT: s_wait_samplecnt 0x0 +; GFX12-FAKE16-NEXT: s_wait_bvhcnt 0x0 +; GFX12-FAKE16-NEXT: s_wait_kmcnt 0x0 +; GFX12-FAKE16-NEXT: v_max_num_f16_e32 v0, v0, v1 +; GFX12-FAKE16-NEXT: s_setpc_b64 s[30:31] + %result = call nnan half @llvm.maximumnum.f16(half %x, half %y) + ret half %result +} + +define float @v_maximumnum_f32_no_ieee(float %x, float %y) #0 { +; GFX7-LABEL: v_maximumnum_f32_no_ieee: +; GFX7: ; %bb.0: +; GFX7-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX7-NEXT: v_mul_f32_e32 v1, 1.0, v1 +; GFX7-NEXT: v_mul_f32_e32 v0, 1.0, v0 +; GFX7-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX7-NEXT: s_setpc_b64 s[30:31] +; +; GFX8-LABEL: v_maximumnum_f32_no_ieee: +; GFX8: ; %bb.0: +; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX8-NEXT: v_mul_f32_e32 v1, 1.0, v1 +; GFX8-NEXT: v_mul_f32_e32 v0, 1.0, v0 +; GFX8-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX8-NEXT: s_setpc_b64 s[30:31] +; +; GFX9-LABEL: v_maximumnum_f32_no_ieee: +; GFX9: ; %bb.0: +; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX9-NEXT: v_max_f32_e32 v1, v1, v1 +; GFX9-NEXT: v_max_f32_e32 v0, v0, v0 +; GFX9-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX9-NEXT: s_setpc_b64 s[30:31] +; +; GFX10-LABEL: v_maximumnum_f32_no_ieee: +; GFX10: ; %bb.0: +; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX10-NEXT: v_max_f32_e32 v1, v1, v1 +; GFX10-NEXT: v_max_f32_e32 v0, v0, v0 +; GFX10-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX10-NEXT: s_setpc_b64 s[30:31] +; +; GFX11-LABEL: v_maximumnum_f32_no_ieee: +; GFX11: ; %bb.0: +; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX11-NEXT: v_dual_max_f32 v1, v1, v1 :: v_dual_max_f32 v0, v0, v0 +; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX11-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX11-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-LABEL: v_maximumnum_f32_no_ieee: +; GFX12: ; %bb.0: +; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-NEXT: s_wait_expcnt 0x0 +; GFX12-NEXT: s_wait_samplecnt 0x0 +; GFX12-NEXT: s_wait_bvhcnt 0x0 +; GFX12-NEXT: s_wait_kmcnt 0x0 +; GFX12-NEXT: v_dual_max_num_f32 v1, v1, v1 :: v_dual_max_num_f32 v0, v0, v0 +; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX12-NEXT: v_max_num_f32_e32 v0, v0, v1 +; GFX12-NEXT: s_setpc_b64 s[30:31] + %result = call float @llvm.maximumnum.f32(float %x, float %y) + ret float %result +} + +define float @v_maximumnum_f32_nnan_no_ieee(float %x, float %y) #0 { +; GFX7-LABEL: v_maximumnum_f32_nnan_no_ieee: +; GFX7: ; %bb.0: +; GFX7-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX7-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX7-NEXT: s_setpc_b64 s[30:31] +; +; GFX8-LABEL: v_maximumnum_f32_nnan_no_ieee: +; GFX8: ; %bb.0: +; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX8-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX8-NEXT: s_setpc_b64 s[30:31] +; +; GFX9-LABEL: v_maximumnum_f32_nnan_no_ieee: +; GFX9: ; %bb.0: +; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX9-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX9-NEXT: s_setpc_b64 s[30:31] +; +; GFX10-LABEL: v_maximumnum_f32_nnan_no_ieee: +; GFX10: ; %bb.0: +; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX10-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX10-NEXT: s_setpc_b64 s[30:31] +; +; GFX11-LABEL: v_maximumnum_f32_nnan_no_ieee: +; GFX11: ; %bb.0: +; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX11-NEXT: v_max_f32_e32 v0, v0, v1 +; GFX11-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-LABEL: v_maximumnum_f32_nnan_no_ieee: +; GFX12: ; %bb.0: +; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-NEXT: s_wait_expcnt 0x0 +; GFX12-NEXT: s_wait_samplecnt 0x0 +; GFX12-NEXT: s_wait_bvhcnt 0x0 +; GFX12-NEXT: s_wait_kmcnt 0x0 +; GFX12-NEXT: v_max_num_f32_e32 v0, v0, v1 +; GFX12-NEXT: s_setpc_b64 s[30:31] + %result = call nnan float @llvm.maximumnum.f32(float %x, float %y) + ret float %result +} + +define double @v_maximumnum_f64_no_ieee(double %x, double %y) #0 { +; GFX7-LABEL: v_maximumnum_f64_no_ieee: +; GFX7: ; %bb.0: +; GFX7-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX7-NEXT: v_max_f64 v[2:3], v[2:3], v[2:3] +; GFX7-NEXT: v_max_f64 v[0:1], v[0:1], v[0:1] +; GFX7-NEXT: v_max_f64 v[0:1], v[0:1], v[2:3] +; GFX7-NEXT: s_setpc_b64 s[30:31] +; +; GFX8-LABEL: v_maximumnum_f64_no_ieee: +; GFX8: ; %bb.0: +; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX8-NEXT: v_max_f64 v[2:3], v[2:3], v[2:3] +; GFX8-NEXT: v_max_f64 v[0:1], v[0:1], v[0:1] +; GFX8-NEXT: v_max_f64 v[0:1], v[0:1], v[2:3] +; GFX8-NEXT: s_setpc_b64 s[30:31] +; +; GFX9-LABEL: v_maximumnum_f64_no_ieee: +; GFX9: ; %bb.0: +; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX9-NEXT: v_max_f64 v[2:3], v[2:3], v[2:3] +; GFX9-NEXT: v_max_f64 v[0:1], v[0:1], v[0:1] +; GFX9-NEXT: v_max_f64 v[0:1], v[0:1], v[2:3] +; GFX9-NEXT: s_setpc_b64 s[30:31] +; +; GFX10-LABEL: v_maximumnum_f64_no_ieee: +; GFX10: ; %bb.0: +; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX10-NEXT: v_max_f64 v[2:3], v[2:3], v[2:3] +; GFX10-NEXT: v_max_f64 v[0:1], v[0:1], v[0:1] +; GFX10-NEXT: v_max_f64 v[0:1], v[0:1], v[2:3] +; GFX10-NEXT: s_setpc_b64 s[30:31] +; +; GFX11-LABEL: v_maximumnum_f64_no_ieee: +; GFX11: ; %bb.0: +; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX11-NEXT: v_max_f64 v[2:3], v[2:3], v[2:3] +; GFX11-NEXT: v_max_f64 v[0:1], v[0:1], v[0:1] +; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX11-NEXT: v_max_f64 v[0:1], v[0:1], v[2:3] +; GFX11-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-LABEL: v_maximumnum_f64_no_ieee: +; GFX12: ; %bb.0: +; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-NEXT: s_wait_expcnt 0x0 +; GFX12-NEXT: s_wait_samplecnt 0x0 +; GFX12-NEXT: s_wait_bvhcnt 0x0 +; GFX12-NEXT: s_wait_kmcnt 0x0 +; GFX12-NEXT: v_max_num_f64_e32 v[2:3], v[2:3], v[2:3] +; GFX12-NEXT: v_max_num_f64_e32 v[0:1], v[0:1], v[0:1] +; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX12-NEXT: v_max_num_f64_e32 v[0:1], v[0:1], v[2:3] +; GFX12-NEXT: s_setpc_b64 s[30:31] + %result = call double @llvm.maximumnum.f64(double %x, double %y) + ret double %result +} + +define double @v_maximumnum_f64_nnan_no_ieee(double %x, double %y) #0 { +; GFX7-LABEL: v_maximumnum_f64_nnan_no_ieee: +; GFX7: ; %bb.0: +; GFX7-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX7-NEXT: v_max_f64 v[0:1], v[0:1], v[2:3] +; GFX7-NEXT: s_setpc_b64 s[30:31] +; +; GFX8-LABEL: v_maximumnum_f64_nnan_no_ieee: +; GFX8: ; %bb.0: +; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX8-NEXT: v_max_f64 v[0:1], v[0:1], v[2:3] +; GFX8-NEXT: s_setpc_b64 s[30:31] +; +; GFX9-LABEL: v_maximumnum_f64_nnan_no_ieee: +; GFX9: ; %bb.0: +; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX9-NEXT: v_max_f64 v[0:1], v[0:1], v[2:3] +; GFX9-NEXT: s_setpc_b64 s[30:31] +; +; GFX10-LABEL: v_maximumnum_f64_nnan_no_ieee: +; GFX10: ; %bb.0: +; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX10-NEXT: v_max_f64 v[0:1], v[0:1], v[2:3] +; GFX10-NEXT: s_setpc_b64 s[30:31] +; +; GFX11-LABEL: v_maximumnum_f64_nnan_no_ieee: +; GFX11: ; %bb.0: +; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX11-NEXT: v_max_f64 v[0:1], v[0:1], v[2:3] +; GFX11-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-LABEL: v_maximumnum_f64_nnan_no_ieee: +; GFX12: ; %bb.0: +; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-NEXT: s_wait_expcnt 0x0 +; GFX12-NEXT: s_wait_samplecnt 0x0 +; GFX12-NEXT: s_wait_bvhcnt 0x0 +; GFX12-NEXT: s_wait_kmcnt 0x0 +; GFX12-NEXT: v_max_num_f64_e32 v[0:1], v[0:1], v[2:3] +; GFX12-NEXT: s_setpc_b64 s[30:31] + %result = call nnan double @llvm.maximumnum.f64(double %x, double %y) + ret double %result +} + +define <2 x half> @v_maximumnum_v2f16_no_ieee(<2 x half> %x, <2 x half> %y) #0 { +; GFX7-LABEL: v_maximumnum_v2f16_no_ieee: +; GFX7: ; %bb.0: +; GFX7-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX7-NEXT: v_cvt_f16_f32_e32 v1, v1 +; GFX7-NEXT: v_cvt_f16_f32_e32 v0, v0 +; GFX7-NEXT: v_cvt_f16_f32_e32 v2, v2 +; GFX7-NEXT: v_cvt_f16_f32_e32 v3, v3 +; GFX7-NEXT: v_cvt_f32_f16_e32 v1, v1 +; GFX7-NEXT: v_cvt_f32_f16_e32 v0, v0 +; GFX7-NEXT: v_cvt_f32_f16_e32 v2, v2 +; GFX7-NEXT: v_cvt_f32_f16_e32 v3, v3 +; GFX7-NEXT: v_max_f32_e32 v0, v0, v2 +; GFX7-NEXT: v_max_f32_e32 v1, v1, v3 +; GFX7-NEXT: s_setpc_b64 s[30:31] +; +; GFX8-LABEL: v_maximumnum_v2f16_no_ieee: +; GFX8: ; %bb.0: +; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX8-NEXT: v_max_f16_sdwa v2, v1, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1 +; GFX8-NEXT: v_max_f16_sdwa v3, v0, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1 +; GFX8-NEXT: v_max_f16_e32 v1, v1, v1 +; GFX8-NEXT: v_max_f16_e32 v0, v0, v0 +; GFX8-NEXT: v_max_f16_sdwa v2, v3, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD +; GFX8-NEXT: v_max_f16_e32 v0, v0, v1 +; GFX8-NEXT: v_or_b32_e32 v0, v0, v2 +; GFX8-NEXT: s_setpc_b64 s[30:31] +; +; GFX900-LABEL: v_maximumnum_v2f16_no_ieee: +; GFX900: ; %bb.0: +; GFX900-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX900-NEXT: v_pk_max_f16 v1, v1, v1 +; GFX900-NEXT: v_pk_max_f16 v0, v0, v0 +; GFX900-NEXT: v_pk_max_f16 v0, v0, v1 +; GFX900-NEXT: s_setpc_b64 s[30:31] +; +; GFX950-LABEL: v_maximumnum_v2f16_no_ieee: +; GFX950: ; %bb.0: +; GFX950-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX950-NEXT: v_pk_max_f16 v1, v1, v1 +; GFX950-NEXT: v_pk_max_f16 v0, v0, v0 +; GFX950-NEXT: s_nop 0 +; GFX950-NEXT: v_pk_max_f16 v0, v0, v1 +; GFX950-NEXT: s_setpc_b64 s[30:31] +; +; GFX10-LABEL: v_maximumnum_v2f16_no_ieee: +; GFX10: ; %bb.0: +; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX10-NEXT: v_pk_max_f16 v1, v1, v1 +; GFX10-NEXT: v_pk_max_f16 v0, v0, v0 +; GFX10-NEXT: v_pk_max_f16 v0, v0, v1 +; GFX10-NEXT: s_setpc_b64 s[30:31] +; +; GFX11-LABEL: v_maximumnum_v2f16_no_ieee: +; GFX11: ; %bb.0: +; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX11-NEXT: v_pk_max_f16 v1, v1, v1 +; GFX11-NEXT: v_pk_max_f16 v0, v0, v0 +; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX11-NEXT: v_pk_max_f16 v0, v0, v1 +; GFX11-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-LABEL: v_maximumnum_v2f16_no_ieee: +; GFX12: ; %bb.0: +; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-NEXT: s_wait_expcnt 0x0 +; GFX12-NEXT: s_wait_samplecnt 0x0 +; GFX12-NEXT: s_wait_bvhcnt 0x0 +; GFX12-NEXT: s_wait_kmcnt 0x0 +; GFX12-NEXT: v_pk_max_num_f16 v1, v1, v1 +; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v0 +; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1) +; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v1 +; GFX12-NEXT: s_setpc_b64 s[30:31] + %result = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> %x, <2 x half> %y) + ret <2 x half> %result +} + +define <2 x half> @v_maximumnum_v2f16_nnan_no_ieee(<2 x half> %x, <2 x half> %y) #0 { +; GFX7-LABEL: v_maximumnum_v2f16_nnan_no_ieee: +; GFX7: ; %bb.0: +; GFX7-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX7-NEXT: v_cvt_f16_f32_e32 v3, v3 +; GFX7-NEXT: v_cvt_f16_f32_e32 v2, v2 +; GFX7-NEXT: v_cvt_f16_f32_e32 v0, v0 +; GFX7-NEXT: v_cvt_f16_f32_e32 v1, v1 +; GFX7-NEXT: v_cvt_f32_f16_e32 v3, v3 +; GFX7-NEXT: v_cvt_f32_f16_e32 v2, v2 +; GFX7-NEXT: v_cvt_f32_f16_e32 v0, v0 +; GFX7-NEXT: v_cvt_f32_f16_e32 v1, v1 +; GFX7-NEXT: v_max_f32_e32 v0, v0, v2 +; GFX7-NEXT: v_max_f32_e32 v1, v1, v3 +; GFX7-NEXT: s_setpc_b64 s[30:31] +; +; GFX8-LABEL: v_maximumnum_v2f16_nnan_no_ieee: +; GFX8: ; %bb.0: +; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX8-NEXT: v_max_f16_sdwa v2, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1 +; GFX8-NEXT: v_max_f16_e32 v0, v0, v1 +; GFX8-NEXT: v_or_b32_e32 v0, v0, v2 +; GFX8-NEXT: s_setpc_b64 s[30:31] +; +; GFX9-LABEL: v_maximumnum_v2f16_nnan_no_ieee: +; GFX9: ; %bb.0: +; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX9-NEXT: v_pk_max_f16 v0, v0, v1 +; GFX9-NEXT: s_setpc_b64 s[30:31] +; +; GFX10-LABEL: v_maximumnum_v2f16_nnan_no_ieee: +; GFX10: ; %bb.0: +; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX10-NEXT: v_pk_max_f16 v0, v0, v1 +; GFX10-NEXT: s_setpc_b64 s[30:31] +; +; GFX11-LABEL: v_maximumnum_v2f16_nnan_no_ieee: +; GFX11: ; %bb.0: +; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX11-NEXT: v_pk_max_f16 v0, v0, v1 +; GFX11-NEXT: s_setpc_b64 s[30:31] +; +; GFX12-LABEL: v_maximumnum_v2f16_nnan_no_ieee: +; GFX12: ; %bb.0: +; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0 +; GFX12-NEXT: s_wait_expcnt 0x0 +; GFX12-NEXT: s_wait_samplecnt 0x0 +; GFX12-NEXT: s_wait_bvhcnt 0x0 +; GFX12-NEXT: s_wait_kmcnt 0x0 +; GFX12-NEXT: v_pk_max_num_f16 v0, v0, v1 +; GFX12-NEXT: s_setpc_b64 s[30:31] + %result = call nnan <2 x half> @llvm.maximumnum.v2f16(<2 x half> %x, <2 x half> %y) + ret <2 x half> %result +} + +attributes #0 = { "amdgpu-ieee"="false" } diff --git a/llvm/test/CodeGen/AMDGPU/minimumnum.ll b/llvm/test/CodeGen/AMDGPU/minimumnum.ll index 03e5777d5b04c..a7aed9b2b48fa 100644 --- a/llvm/test/CodeGen/AMDGPU/minimumnum.ll +++ b/llvm/test/CodeGen/AMDGPU/minimumnum.ll @@ -4118,3 +4118,486 @@ define <4 x double> @v_minimumnum_v4f64_nnan(<4 x double> %x, <4 x double> %y) { %result = call nnan <4 x double> @llvm.minimumnum.v4f64(<4 x double> %x, <4 x double> %y) ret <4 x double> %result } + +define half @v_minimumnum_f16_no_ieee(half %x, half %y) #0 { +; GFX7-LABEL: v_minimumnum_f16_no_ieee: +; GFX7: ; %bb.0: +; GFX7-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX7-NEXT: v_cvt_f16_f32_e32 v0, v0 +; GFX7-NEXT: v_cvt_f16_f32_e32 v1, v1 +; GFX7-NEXT: v_cvt_f32_f16_e32 v0, v0 +; GFX7-NEXT: v_cvt_f32_f16_e32 v1, v1 +; GFX7-NEXT: v_min_f32_e32 v0, v0, v1 +; GFX7-NEXT: s_setpc_b64 s[30:31] +; +; GFX8-LABEL: v_minimumnum_f16_no_ieee: +; GFX8: ; %bb.0: +; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX8-NEXT: v_max_f16_e32 v1, v1, v1 +; GFX8-NEXT: v_max_f16_e32 v0, v0, v0 +; GFX8-... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/139145 _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
